IJSRET Volume 11 Issue 3, May-Jun-2025

AI- Based Predictive Healthcare Finetuning And Handwriting Recongnizer_141

Authors: Ajay Singh, Aditya Marathe, Aniket Gaikwad, Om ahire, Jay modiya, Utkarsh musale

 

Abstract: Artificial Intelligence (AI) continues to play a transformative role in healthcare, particularly through advancements in large language models (LLMs) and computer vision (CV). These technologies are now being increasingly applied in predictive healthcare systems to improve diagnosis, reduce human error, and enhance patient engagement. However, general-purpose pre-trained models often underperform in specialized medical contexts where accuracy, domain-specific knowledge, and multimodal understanding are essential. This research proposes a hybrid AI framework that combines natural language processing (NLP) and computer vision to support predictive and interactive healthcare use cases. In the NLP component of the system, we perform a comparative evaluation of six leading open-source LLMs—Mistral, FLAN-T5, GPT-Neo, DialoGPT, LLaMA, and Ollama—analyzing their adaptability to domain-specific tasks such as symptom triage, patient education, and medical question answering. These models were fine-tuned using full parameter updates and reinforcement learning from human feedback (RLHF), which allowed the models to better align their outputs with the nuanced communication styles and ethical expectations in clinical settings. In parallel, the CV module addresses a critical real-world challenge: automated prescription handwriting recognition, which is essential for minimizing misinterpretation of medication names and dosages. To tackle the variability and complexity of handwritten medical prescriptions, we utilize convolutional neural networks—specifically VGG16 and EfficientNet—for image-based classification and text recognition. A custom dataset of handwritten prescription images was created and annotated using domain knowledge, and the models were trained to map image inputs to structured medicine names. Our experiments reveal that EfficientNet, with its compound scaling and optimized architecture, outperforms VGG16 in both accuracy and training efficiency, particularly under noisy or low-resolution input conditions. By integrating these two components, we build a multimodal chatbot capable of receiving an image of a handwritten prescription, recognizing the medication using a CNN model, and generating an informative or advisory response using an LLM fine-tuned for medical NLP. This enables seamless user interaction, allowing patients or practitioners to interact with the system using both text and image inputs. Such a system has practical applications in telemedicine, hospital kiosks, pharmacy automation, and rural health outreach, where both human expertise and infrastructure may be limited. Our results demonstrate the effectiveness of combining LLM fine-tuning and CNN-based vision models for predictive healthcare. While larger LLMs like LLaMA and FLAN-T5 achieve higher accuracy in clinical language tasks, lighter models like DialoGPT and Mistral offer faster, more cost-effective deployment options. On the CV side, EfficientNet offers superior generalization with fewer parameters compared to legacy architectures. This research provides a comprehensive performance analysis and design framework for AI systems in healthcare, offering actionable insights into how different model configurations, training strategies, and hardware choices affect outcome quality and deployment feasibility.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.119

 

EASYHEALS CHATBOT AI- BASED PREDICTIVE HEALTHCARE

Authors: Ajay Singh, Aditya Marathe, Aniket Gaikwad, Om ahire, Jay modiya, Utkarsh musale

 

Abstract: Artificial Intelligence (AI) continues to play a transformative role in healthcare, particularly through advancements in large language models (LLMs) and computer vision (CV). These technologies are now being increasingly applied in predictive healthcare systems to improve diagnosis, reduce human error, and enhance patient engagement. However, general-purpose pre-trained models often underperform in specialized medical contexts where accuracy, domain-specific knowledge, and multimodal understanding are essential. This research proposes a hybrid AI framework that combines natural language processing (NLP) and computer vision to support predictive and interactive healthcare use cases. In the NLP component of the system, we perform a comparative evaluation of six leading open-source LLMs—Mistral, FLAN-T5, GPT-Neo, DialoGPT, LLaMA, and Ollama—analyzing their adaptability to domain-specific tasks such as symptom triage, patient education, and medical question answering. These models were fine-tuned using full parameter updates and reinforcement learning from human feedback (RLHF), which allowed the models to better align their outputs with the nuanced communication styles and ethical expectations in clinical settings. In parallel, the CV module addresses a critical real-world challenge: automated prescription handwriting recognition, which is essential for minimizing misinterpretation of medication names and dosages. To tackle the variability and complexity of handwritten medical prescriptions, we utilize convolutional neural networks—specifically VGG16 and EfficientNet—for image-based classification and text recognition. A custom dataset of handwritten prescription images was created and annotated using domain knowledge, and the models were trained to map image inputs to structured medicine names. Our experiments reveal that EfficientNet, with its compound scaling and optimized architecture, outperforms VGG16 in both accuracy and training efficiency, particularly under noisy or low-resolution input conditions. By integrating these two components, we build a multimodal chatbot capable of receiving an image of a handwritten prescription, recognizing the medication using a CNN model, and generating an informative or advisory response using an LLM fine-tuned for medical NLP. This enables seamless user interaction, allowing patients or practitioners to interact with the system using both text and image inputs. Such a system has practical applications in telemedicine, hospital kiosks, pharmacy automation, and rural health outreach, where both human expertise and infrastructure may be limited. Our results demonstrate the effectiveness of combining LLM fine-tuning and CNN-based vision models for predictive healthcare. While larger LLMs like LLaMA and FLAN-T5 achieve higher accuracy in clinical language tasks, lighter models like DialoGPT and Mistral offer faster, more cost-effective deployment options. This research provides a comprehensive performance analysis and design framework for AI systems in healthcare, offering actionable insights into how different model configurations, training strategies, and hardware choices affect outcome quality and deployment feasibility.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.118

 

Real-Time Vehicle Counting And Classification Using OpenCV

Authors: Jamila J, M. Sathya, R. Priyadharshini, J. Jenshya, V. Vinothini

Abstract: Urban areas face growing challenges in managing parking efficiently due to increased vehicle density. This paper proposes a real-time parking occupancy detection system using OpenCV, a powerful open- source computer vision library. By analyzing live video feeds from strategically positioned cameras, the system detects, classifies, and tracks vehicles using advanced object detection techniques, such as YOLO and SSD. This enables continuous monitoring of parking spaces and accurate assessment of their occupancy status. The system operates in three core stages: vehicle detection, classification of parked or moving vehicles, and real-time tracking using algorithms like Kalman filters or optical flow. Occupancy data is dynamically updated and shared via user-friendly interfaces such as mobile apps or digital displays, helping drivers find available spots efficiently. The system is developed using Python and OpenCV to ensure flexibility and ease of deployment across different parking environments. Performance evaluation was carried out using real-world datasets under various lighting and environmental conditions, demonstrating high accuracy and responsiveness. The proposed solution is scalable, adaptable to various camera setups, and suitable for deployment in street parking, garages, and smart city infrastructure. By improving parking space utilization and reducing the time spent searching for parking, this system contributes to easing traffic congestion, reducing fuel consumption, and enhancing the urban driving experience. With potential features such as safety compliance monitoring and modular architecture, the proposed system represents a significant step toward intelligent and efficient parking management in modern cities.

 

 

Analysis Of Factors Influencing On Digital Banking Adaption By Senior Citizen In Public License Commercial Banks In Colombo District

Authors: P.K.C.Ashara Rathnasinghe

Abstract: This document derives an analysis of factors influencing on digital banking adaptation by senior citizen in public license commercial banks in Colombo district and to know the dimensions driven by solutions for digital banking adaptation and the associated value proposition for senior citizen customers. The convenient function of digital banking has replaced interactions with physical money and reduced transaction time, better meeting the convenience needs in modern society life styles with the technological development. As digital banking concept plays an important role in day-to-day functions, understanding the factors which attracting consumers of senior citizen category by their age to use digital banking method will bring more opportunities for development, and further significantly improve the output in convenient way. This study discusses how to further influence the factors of digital banking adaptation by senior citizens who use public license commercial banks in Colombo district. This is based on the main theoretical framework of the selected 5 factors from several factors. In this study, data analysis is implemented by for the purpose of verifying the research model and hypotheses. The research results show that factors such as awareness of the service, lack of knowledge / training, cost of service, online security, perceived ease of use have selected as independent variables influence on senior citizens (age above 60 years) to adapt to use digital banking concept for their financial transactions. Three hundred and eighty-five number of samples will plan to select to the study and sample was consisted of random sampling technique. Statistical analysis and Regression analysis going to be used to confirm the impact of these five factors on digital bank adaptation.

Analysis Of Factors Influencing On Digital Banking Adaption By Senior Citizen In Public License Commercial Banks In Colombo District

Authors: P.K.C.Ashara Rathnasinghe

Abstract: This document derives an analysis of factors influencing on digital banking adaptation by senior citizen in public license commercial banks in Colombo district and to know the dimensions driven by solutions for digital banking adaptation and the associated value proposition for senior citizen customers. The convenient function of digital banking has replaced interactions with physical money and reduced transaction time, better meeting the convenience needs in modern society life styles with the technological development. As digital banking concept plays an important role in day-to-day functions, understanding the factors which attracting consumers of senior citizen category by their age to use digital banking method will bring more opportunities for development, and further significantly improve the output in convenient way. This study discusses how to further influence the factors of digital banking adaptation by senior citizens who use public license commercial banks in Colombo district. This is based on the main theoretical framework of the selected 5 factors from several factors. In this study, data analysis is implemented by for the purpose of verifying the research model and hypotheses. The research results show that factors such as awareness of the service, lack of knowledge / training, cost of service, online security, perceived ease of use have selected as independent variables influence on senior citizens (age above 60 years) to adapt to use digital banking concept for their financial transactions. Three hundred and eighty-five number of samples will plan to select to the study and sample was consisted of random sampling technique. Statistical analysis and Regression analysis going to be used to confirm the impact of these five factors on digital bank adaptation.

Neuroimaging Stroke Analysis With Machine And Deep Learning

Authors: Dinnesh Gr, Manoj Jai Sudhan, Mrs. A. Jeyanthi, Mrs.G.Priyaa Sri

Abstract: Stroke is a major global health challenge, contributing significantly to mortality and disability, and placing a heavy burden on healthcare systems. Timely and accurate diagnosis is critical to mitigate long-term complications and improve patient outcomes. This study introduces a hybrid deep learning framework for automated stroke detection in brain CT images, integrating Vision Transformer (ViT), LASSO regression, and DenseNet121 to enhance diagnostic accuracy and efficiency. Utilizing a Kaggle dataset of 1900 CT images (950 stroke, 950 normal), the system employs preprocessing techniques, including resizing to 224×224 pixels, grayscale-to-RGB conversion, and data augmentation (flipping, rotation, blurring), to ensure model robustness and adaptability. The ViT model extracts high-level semantic features, capturing global dependencies through self-attention mechanisms, which are then refined using LASSO regression for feature selection to reduce dimensionality and prevent overfitting. The refined features are fed into DenseNet121, a convolutional neural network optimized for efficient parameter usage and gradient flow, for binary classification (stroke vs. normal). A Tkinter-based graphical user interface facilitates seamless interaction, allowing radiologists to upload images and receive real-time predictions, enhancing clinical workflows. The system is designed for scalability, local deployment, and integration with hospital systems like PACS, addressing challenges of diagnostic delays and inter-observer variability. Evaluation on the dataset demonstrates robust performance, with an accuracy of 92.69%, precision of 91.36%, recall of 94.03%, and F1-score of 92.68%. These metrics underscore the system’s reliability in minimizing false negatives, critical for clinical applications. This framework advances automated stroke diagnosis by combining transformer and convolutional architectures, offering a scalable, interpretable solution for emergency settings and laying the groundwork for future enhancements in multi-class stroke classification and real-time deployment.

 

 

Cyber Security

Authors: Goswami Jaygiri

Abstract: With the recent explosion of technology, cybersecurity is now a necessity to protect sensitive data, critical systems, and individual privacy. This review paper examines the existing state of cybersecurity, detailing some of the principal threats and countermeasures, related problems, and future paths. We particularly concentrate on AI, zero-trust architecture, blockchain, and quantum-resilient cryptography from a security viewpoint. We also touch on human factors, governance, and other cyber risk avoidance measures that deserve more research. This article provides a comprehensive overview of present and future directions in cybersecurity while assisting scholars, decision makers, and practitioners of cybersecurity.

 

Generative AI And Human-Centered Design: Sustainable Solutions For Software Development Challenges And Cross-Functional Collaboration

Authors: Viraj P. Tathavadekar

Abstract: This study investigates the use of generative AI and human-centered design for sustainable solutions to the ever-more pervasive problems within software development processes with a particular view to improving cross-functional collaboration. The modeling of modern Software Development Life Cycles (SDLCs) is further complicated by such things as vague requirements, continuous changes, and integration problems, all of which delay projects and increase their cost. The enormous integration gaps that the present study identifies are connecting AI-driven technologies with human-centered design practices, especially in creating collaboration among varied teams but ensuring technology sustainability. Research objectives consist of studying generative AI’s role in enhancing requirements gathering, design processes, and further automated intelligent decision-making in testing, application deployment, and maintenance. It also aims at understanding the challenges key stakeholders confront across different SDLC phases. This is being done through a mixed-methods research approach combining quantitative data on AI tool effectiveness: reducing technical debt and increasing efficiency in teams, with correspondent qualitative insights from industry case studies. The major outcomes indicate that AI-driven tools do not just improve the efficiency of processes, but are also conducive to sustainable development practice as they reduce resource consumption, promote better collaboration. Implications are that generative AI and human-centered design can transform SDLC practices leading to higher-quality products and much lower maintenance costs as well as overall sustainability in software development projects.

Wireless Charging System For Electric Vehicles

Authors: Assistant Professor Mr. Pramodh H K, Chandan M J, Mithun Gowda H C, Lokesh T S, Samskruthi A Y

Abstract: This article presents a comprehensive overview and proposes a system design that integrates wireless power transfer with an automated electric vehicle (EV) platform for real-time voltage monitoring and mobility. Utilizing inductive coupling technology, the system transmits power wirelessly from a stationary transmitter coil to a mobile receiver coil mounted on the EV prototype. A voltage sensor, in conjunction with an ESP8266 microcontroller, measures the received voltage, which is displayed on an LCD screen for user feedback. A motor driver and DC motors allow the vehicle to move, demonstrating the system’s ability to function while wirelessly charging. This approach aims to improve efficiency in EV charging infrastructure by minimizing manual intervention and enabling autonomous, wireless power reception. The article discusses both existing charging systems and the implementation of the proposed prototype.

Power Predict: Unlocking The Future Of Electrical Energy With ML

Authors: Assistant Professor Sourabh Jain, Prachi Gupta, Manish Yadav, Pooja Srivastava

Abstract: In this day and age when we need to manage resources prudently, accurately predicting how much energy one would require is an extremely important task. In this abstract, we showcase how the application of advanced technologies – machine learning, data mining, and artificial intelligence techniques can be blended with energy management systems to enhance the efficiency of forecasting energy consumption rates. The sample we use in this research contains a wide array of data, including casual and seasonal weather data, time, building occupancy figures, as well as the figures attained for energy consumption during the various time slices. Some of the various approaches to solve the problem we are working on that we analyze include: linear regression, decision tree regression, random forest regression, and artificial neural networks. It is vital to accurately predict future power consumption considering factors like resource optimization and sustainable energy management. This work describes an approach that uses advanced methodologies in machine learning techniques for precise forecasting based on historical data alongside a variety of descriptive features to predict energy consumption within the foreseeable future. In this research, we use an extensive dataset containing weather data, timestamps, occupancy statistics, and previous energy consumption data. We apply many algorithms that include linear regression, decision trees, random forests, and neural networks to energy consumption prediction and analyze which model best performs the prediction task.

3D Modelling Of A Stilt + 4 Storey Residential Building Using Revit Architecture Software

Authors: Mohammed Moiz1, Mohd Habban Ahmed, Mohammad Shanawaz

Abstract: This academic project showcases the architectural modeling and visualization of a stilt-plus-four-story residential building using Revit Architecture and AutoCAD. The study aims to create a digitally simulated residential structure that balances functional efficiency with modern urban housing requirements. The building’s design, situated on a 40×60 feet plot with a southeast orientation, prioritizes climate responsiveness and natural daylight optimization for improved ventilation and thermal comfort. The project workflow begins with conceptual planning in AutoCAD, transitioning to detailed 3D modeling in Revit Architecture. This process integrates architectural elements, including walls, doors, windows, and roofing systems, while incorporating features like lighting, ventilation, and staircase design. The stilt floor accommodates parking, reflecting urban planning demands and space optimization. By leveraging Revit’s Building Information Modeling (BIM) capabilities, the project achieves high design coordination, visualization, and parametric control. The digital model enables efficient generation of construction documentation, elevations, and sections. Sustainability aspects are incorporated through passive design elements, reducing potential design conflicts and material wastage. This project highlights the benefits of advanced architectural software tools in residential building design, enhancing precision, creativity, and efficiency in the field.

Enhancing Virtual Machine Placement Security: A Comprehensive Analysis Of Techniques In Cloud Computing Environments

Authors: Dr. Nitin Kumar Patel

Abstract: Cloud computing’s extensive adoption has made Virtual Machine (VM) placement a critical aspect of resource management. Beyond performance and cost optimization, securing VM placement is paramount to mitigating several threats, including co-residency attacks, data breaches, and denial- of-service attacks. This article offers a comprehensive analysis of techniques designed to enhance VM placement security in cloud environments. I explore a variety of security considerations, encompassing physical security, logical isolation, and data protection, and examine how they influence VM placement strategies. Specifically, we delve into techniques like anti-collocation policies, affinity and anti-affinity rules, trust-based VM placement, security-aware scheduling algorithms, and dynamic VM migration strategies. Furthermore, I analyse the trade-offs between security, performance, and cost associated with each technique. By evaluating the strengths and weaknesses of existing approaches, this paper identifies research gaps and highlights promising directions for future research in securing VM placement. I accomplish this by advocating for a holistic, multi-layered approach to VM placement security that integrates diverse techniques and adapts dynamically to evolving threat landscapes in cloud computing environments. This research purposes to provide valuable insights for cloud providers and consumers seeking to enhance the security posture of their cloud infrastructure through optimized VM placement strategies.

Global Mutual Fund Industry: Growth, Trends and Digital Transformation

Authors: Dr. A. Saravanakumar

Abstract: The advent of new technologies has streamlined business transactions, enhancing the buying experience for both companies and customers. Digital marketing, in particular, has enabled mutual fund companies to expand their investor base while providing potential investors with convenient access to information. In this context, the primary objective of this study is to examine the impact of digital marketing on investors’ decisions to invest in mutual funds, with a focus on identifying key demographic factors influencing online investments.

Robotic Arm Controlled By Potentiometers

Authors: Professor Sheetal N. Mindolkar, Mr. Naveen Gamanagatti, Mr. Pratap R Goudar, Mr. Sammed Belavi

Abstract: Controlling a robot arm can be made simple and intuitive using basic electronic components like potentiometers and an Arduino microcontroller. By directly linking each potentiometer’s rotation to a specific joint on the robotic arm, users experience a tangible and immediate connection between their input and the arm’s movement. This straightforward setup offers an accessible introduction to robotics, ideal for beginners exploring mechatronics, sensor interfacing, and basic control principles. The affordability and ease of the Arduino platform further enhance its educational value, allowing hands-on learning without complex equipment. Building and operating the system reveals the essential control loop of robotics: the robot “senses” user input via electrical signals from potentiometers, the Arduino processes this data, and servo motors execute the movements. While this open-loop system lacks advanced accuracy and autonomy, it provides a clear, practical understanding of how robots respond to control signals, laying the foundation for more sophisticated robotics concepts in the future.

Automatic Power Theft Detection And iot-Based Load Control

Authors: Kuraganti Syam Kumar, Palineti Karthik, Thodindala Siva Teja, Shaik Anwar Mohiddeen, Syed Mohammad Waseem

Abstract: Electricity theft remains a major challenge for power distribution systems, leading to significant financial losses and reduced supply reliability. This paper presents a smart and automated solution for detecting unauthorized electricity usage and enabling remote load control through the Internet of Things (IoT). The proposed system continuously monitors electrical parameters such as current and voltage using embedded sensors. Anomalies indicative of theft such as elevated current without corresponding voltage change trigger an automatic disconnection of the power supply via a relay module. Simultaneously, a GSM module transmits an alert message containing GPS coordinates to the concerned authorities, enabling quick response and location-based intervention. The system also supports cloud integration for real-time monitoring, data logging, and consumption analysis. Leveraging the ESP32 microcontroller, this approach offers a cost- effective, scalable, and energy-efficient framework applicable to residential, commercial, and industrial environments. The integration of automated theft detection, instant notification, and IoT-based control enhances grid transparency, reduces human intervention, and ensures equitable power distribution.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.117

Paraphrase Detection in Indian Language

Authors: Professor Smita Chunamari, Sahil Tejam, Bhavesh Sonawane, Yash Daund, Janhvi Pawar

Abstract: Paraphrase detection is a crucial task in Natural Language Processing (NLP) that helps systems understand when two sentences mean the same thing, even if they’re phrased differently. While this has been explored extensively in English and a few other global languages, regional languages—rich in diversity and nuance—remain significantly underrepresented. In this study, we explore the challenges and opportunities of building paraphrase detection systems for regional languages, focusing on the unique linguistic features such as dialect variations, code- mixing, and syntactic differences. We develop a multilingual model trained on both parallel and non-parallel regional datasets, enhanced with data augmentation techniques and semantic similarity measures. We also introduce a small but diverse paraphrase corpus for select Indian languages as a benchmark. Our results show that transformer-based models fine-tuned on language-specific data outperform traditional ap- proaches, highlighting the importance of contextual embeddings in low-resource settings. This work not only advances the field of NLP in regional languages but also opens the door for more inclusive and accessible language technologies, ranging from intelligent search systems to educational tools that truly understand the linguistic richness of everyday users.

Blood Group Prediction Using Fingerprint Using Simple CNN

Authors: Yashas D R, Vinutha H N, Merlin B, Soundarya R, Chethan V

Abstract: Identification of an existent’s blood group is pivotal in exigency situations, for identity authentication, and in population analysis. It would else involve drawing a blood sample and assaying it in a laboratory, which is painful, tedious and requires trained labor force and installations. Herein, we suggest a way to prognosticate blood groups without blood through the use of point images and a Convolutional Neural Network (CNN). Since fingerprints are distinct in each existent, we suppose they could have patterns associated with natural characteristics similar as blood type. We gathered point images with eight colorful blood groups marked and used them to train a CNN model to classify them. We estimated the performance of the trained model using criteria similar as delicacy, perfection, recall, and F1- score upon testing. Our findings were encouraging, indicating that fingerprints may be potentially employed to cast blood groups using deep literacy. In the future, we will expand our dataset with fresh samples, try out bettered CNN models, and work on securing individualities’ data. This system has the implicit to offer an invasive-free, hastily, and easier system for blood group vaticination, particularly in locales with no lab setup.

Assessment Of AI Based Digital Tools For Automated Operation Of Supply Chain System For FMCG Sector

Authors: Pratichi Dhar

Abstract: – This study explores the effect of AI-powered technologies on productivity, cost reduction, and decision-making within the “Supply Chain Management (SCM)” of “Fast-Moving Consumer Goods (FMCG)”. It aims to explore the ways in which AI enhances operational performance and sustainability. Academic research identifies inadequate infrastructure, particularly in underprivileged regions, high implementation costs, and data privacy concerns as significant challenges. This study reached conclusions by utilizing both primary and secondary data through a combination of research methods. AI solutions enhance logistics, inventory management, and resource allocation, minimizing waste and errors while boosting cost efficiency. The use of AI in predictive analytics and real-time decision-making enhances strategic planning and improves supply chain agility. The advantages of AI surpass its disadvantages, including integration with legacy systems and significant upfront expenses. The results show that AI enhances the resilience and sustainability of FMCG supply chains. There is a need for research on data security, implementation methods, and scalability to fully realize its potential. AI has the ability to revolutionize supply chains entirely, making it crucial for organizations to stay competitive in the ever-evolving global market.

Green Networking: Ai-Enabled Energy Optimization in Next-Gen Communication Systems

Authors: Aashika .K, Assistant Professor Dr.M.kathiresan

Abstract: With the rapid expansion of digital infrastructure, energy consumption by communication networks has become a critical concern. This paper presents an AI-enabled framework for energy-efficient routing and traffic management in next-generation networks. It utilizes machine learning to predict network demand and optimize energy use dynamically, reducing the carbon footprint of data transmission. The system incorporates renewable energy tracking, load balancing, and carbon-aware routing to achieve green networking. Our simulation results show a significant reduction in energy usage without compromising performance, aligning network operations with global sustainability goals.

AI- Based Predictive Healthcare Finetuning And Handwriting Recongnizer

Authors: Ajay Singh, Aditya Marathe, Aniket Gaikwad, Om ahire, Jay modiya, Utkarsh musale

Abstract: Artificial Intelligence (AI) continues to play a transformative role in healthcare, particularly through advancements in large language models (LLMs) and computer vision (CV). These technologies are now being increasingly applied in predictive healthcare systems to improve diagnosis, reduce human error, and enhance patient engagement. However, general-purpose pre-trained models often underperform in specialized medical contexts where accuracy, domain-specific knowledge, and multimodal understanding are essential. This research proposes a hybrid AI framework that combines natural language processing (NLP) and computer vision to support predictive and interactive healthcare use cases. In the NLP component of the system, we perform a comparative evaluation of six leading open-source LLMs—Mistral, FLAN-T5, GPT-Neo, DialoGPT, LLaMA, and Ollama—analyzing their adaptability to domain-specific tasks such as symptom triage, patient education, and medical question answering. These models were fine-tuned using full parameter updates and reinforcement learning from human feedback (RLHF), which allowed the models to better align their outputs with the nuanced communication styles and ethical expectations in clinical settings. In parallel, the CV module addresses a critical real-world challenge: automated prescription handwriting recognition, which is essential for minimizing misinterpretation of medication names and dosages. To tackle the variability and complexity of handwritten medical prescriptions, we utilize convolutional neural networks—specifically VGG16 and EfficientNet—for image-based classification and text recognition. A custom dataset of handwritten prescription images was created and annotated using domain knowledge, and the models were trained to map image inputs to structured medicine names. Our experiments reveal that EfficientNet, with its compound scaling and optimized architecture, outperforms VGG16 in both accuracy and training efficiency, particularly under noisy or low-resolution input conditions. By integrating these two components, we build a multimodal chatbot capable of receiving an image of a handwritten prescription, recognizing the medication using a CNN model, and generating an informative or advisory response using an LLM fine-tuned for medical NLP. This enables seamless user interaction, allowing patients or practitioners to interact with the system using both text and image inputs. Such a system has practical applications in telemedicine, hospital kiosks, pharmacy automation, and rural health outreach, where both human expertise and infrastructure may be limited. Our results demonstrate the effectiveness of combining LLM fine-tuning and CNN-based vision models for predictive healthcare. While larger LLMs like LLaMA and FLAN-T5 achieve higher accuracy in clinical language tasks, lighter models like DialoGPT and Mistral offer faster, more cost-effective deployment options. This research provides a comprehensive performance analysis and design framework for AI systems in healthcare, offering actionable insights into how different model configurations, training strategies, and hardware choices affect outcome quality and deployment feasibility.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.118

Analysis And Evaluation Of Security And Privacy In Mobile Social Networks

Authors: Mobin Erteghaie

Abstract: The revolution in the two dimensions of information and communication has changed and transformed various aspects of human life. In other words, the behaviors and interactions of individuals have been greatly affected by the changes and transformations in the two aforementioned dimensions. The emergence of new technologies in both dimensions has provided very powerful platforms and tools for the formation of thoughts and communication between different people from different places. In line with these remarkable developments, everyone has been able to provide a lot of new information in various ways and in a wide range of dimensions and scope to a wide range of their fellow human beings. One of the most important communication and information tools between individual humans is mobile phones, especially smart phones. Also, the expansion of social networks in the Internet space, which is actually considered one of the foundations of the new revolution, has provided a very powerful and suitable platform for exchanging information and communicating between different people. Mobile social networks are a comprehensive software platform and a cyberspace in which smartphones that are physically close to each other can create a wireless network. So that people can easily carry out a dating process in public spaces such as airports, coffee shops, and theaters by sharing their interests with those who are nearby. With this development and increased use, there is still a concern in the hearts of people. Given that a lot of information and data is stored and shared in people’s personal profiles, the most important issue in such situations is security and personalization. In this study, an attempt has been made to introduce and fully investigate a secure dating protocol in mobile social networks. The present study, focusing on a model of a secure dating process in mobile social networks, examines its impact on social networks and analyzes existing problems. So that by using this profile protocol, users are able to communicate with each other without being fully familiar with each other’s complete personal details. In the following, to improve the execution time of the protocol, a high-performance encryption algorithm is used and it is shown that by applying this algorithm and the possibility of using a long-length encryption key while maintaining efficiency, the security of the protocol is significantly increased. The results of the implementation and experiments as well as the evaluations indicate that the efficiency of the proposed protocol in terms of execution time has been significantly improved.

Anomaly Detection In Pacemaker Signal Patterns

Authors: Ashu Gulia, Ajay Dagar, Dr.Sangeeta Rani, Ms. Monika Saini

Abstract: Pacemakers serve as critical medical devices for monitoring and regulating heart rhythms within patients afflicted with arrhythmias or heart failure. Truly ensuring their accuracy, with reliability and cybersecurity, is paramount. This paper here explores the usage of Support Vector Machines (SVM), and particularly one-class SVM, for the anomaly detection of pacemaker signal patterns. Effectively, deviations showing device failure, cardiac irregularities, or potential cyberattacks can be identified via training models to recognize “normal” cardiac signals. Drawing on methodologies from malware anomaly detection [1][2][3], we adapt as well as repurpose these machine learning techniques to the medical context. The study presents several implementation steps and deployment challenges. The study gives a comparative evaluation with many detection methods, contributing to a safer, clever, and secure pacemaker infrastructure.

THE FUTURE OF DIGITAL MARKETING .EXPLORING INNOVATIONS AND PROJECTING TRENDS IN A RAPIDLY EVOLVING DIGITAL LANDCAPE.

Authors: Anchal Kashyap

Abstract: This research investigates the transformative impact of emerging technologies on digital marketing strategies. Focusing on artificial intelligence (AI), machine learning, augmented reality (AR), and virtual reality (VR), the study examines how these innovations enhance customer engagement and personalization. The paper also explores the evolution of social media platforms into e-commerce hubs, the growing significance of influencer marketing, and the critical importance of data privacy and ethical practices. By analyzing current trends and consumer behaviors, the research provides insights into effective digital marketing strategies that align with technological advancements and ethical considerations.

SKIN DISEASE DETECTION SYSTEM USING IMAGE PROCESSING AND DEEP LEARNING

Authors: Sachin Sing, Neelanshu Pande, Jay Prakash Pandey, Yatharth Singh

Abstract: Skin conditions are among the most widespread health concerns globally, often triggered by factors such as fungal and bacterial infections, allergies, viruses, genetic predispositions, or exposure to chemicals. Additionally, environmental influences—such as ultraviolet (UV) radiation, pollution, and varying climate conditions—play a significant role in the development of skin disorders. Early detection and diagnosis are crucial for effective treatment. Traditionally, skin diseases have been identified through biopsies and manual assessment by dermatologists. However, advancements in laser and photonics-based medical technologies have significantly enhanced the speed and precision of skin disease diagnosis. Despite this progress, such high-end diagnostic tools remain costly and less accessible. As a cost-effective alternative, image processing techniques have emerged, enabling the creation of automated dermatological screening systems at preliminary stages. In this work, we introduce a hybrid diagnostic model that integrates deep learning (DL) and machine learning (ML) approaches. Patients submit images of affected skin areas, which serve as input to the system. The primary goal of this project is to accurately identify the specific type of skin disease and suggest appropriate treatments. Employing a range of ML and DL algorithms, the proposed method not only enhances diagnostic accuracy but also accelerates the entire process.

Design And Implementation Of (256*256) Booth’s Multiplier And Its Applications

Authors: Assistant Professor Mainka Saharan

Abstract: This Paper describes the high speed multiplier by using Booth Algorithm. Booth algorithm produces less delay in comparison with a normal multiplication process and it also moderates the number of partial products. We also proposed a new hybrid CLA from the existing hierarchical CLA which exhibits high performance in terms of computation, power consumption and area. Area, delay and power complexities of the resulting design are reported. Booth algorithm gives a procedure for multiplying binary integers in signed 2’s complement representation in efficient way, i.e., less number of additions/subtractions required.

Easyheals Chatbot AI- Based Predictive Healthcare Fine-Tunning LLM’s

Authors: Ajay Singh, Aditya Marathe, Aniket Gaikwad, Om ahire, Jay modiya, Utkarsh musale

Abstract: Artificial Intelligence (AI) continues to play a transformative role in healthcare, particularly through advancements in large language models (LLMs) and computer vision (CV). These technologies are now being increasingly applied in predictive healthcare systems to improve diagnosis, reduce human error, and enhance patient engagement. However, general-purpose pre-trained models often underperform in specialized medical contexts where accuracy, domain-specific knowledge, and multimodal understanding are essential. This research proposes a hybrid AI framework that combines natural language processing (NLP) and computer vision to support predictive and interactive healthcare use cases. In the NLP component of the system, we perform a comparative evaluation of six leading open-source LLMs—Mistral, FLAN-T5, GPT-Neo, DialoGPT, LLaMA, and Ollama—analyzing their adaptability to domain-specific tasks such as symptom triage, patient education, and medical question answering. These models were fine-tuned using full parameter updates and reinforcement learning from human feedback (RLHF), which allowed the models to better align their outputs with the nuanced communication styles and ethical expectations in clinical settings. In parallel, the CV module addresses a critical real-world challenge: automated prescription handwriting recognition, which is essential for minimizing misinterpretation of medication names and dosages. To tackle the variability and complexity of handwritten medical prescriptions, we utilize convolutional neural networks—specifically VGG16 and EfficientNet—for image-based classification and text recognition. A custom dataset of handwritten prescription images was created and annotated using domain knowledge, and the models were trained to map image inputs to structured medicine names. Our experiments reveal that EfficientNet, with its compound scaling and optimized architecture, outperforms VGG16 in both accuracy and training efficiency, particularly under noisy or low-resolution input conditions. By integrating these two components, we build a multimodal chatbot capable of receiving an image of a handwritten prescription, recognizing the medication using a CNN model, and generating an informative or advisory response using an LLM fine-tuned for medical NLP. This enables seamless user interaction, allowing patients or practitioners to interact with the system using both text and image inputs. Such a system has practical applications in telemedicine, hospital kiosks, pharmacy automation, and rural health outreach, where both human expertise and infrastructure may be limited. Our results demonstrate the effectiveness of combining LLM fine-tuning and CNN-based vision models for predictive healthcare. While larger LLMs like LLaMA and FLAN-T5 achieve higher accuracy in clinical language tasks, lighter models like DialoGPT and Mistral offer faster, more cost-effective deployment options. On the CV side, EfficientNet offers superior generalization with fewer parameters compared to legacy architectures. This research provides a comprehensive performance analysis and design framework for AI systems in healthcare, offering actionable insights into how different model configurations, training strategies, and hardware choices affect outcome quality and deployment feasibility.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.119

Electric Vehicle Wireless Charging Station

Authors: Professor Deepak V Lokare, Mr. Mahmadtoufik Rajjusab Mekamungali, Mr. Vijay Byadagi, Mr. Vishal Navilkar, Mr. Sachin Basavaraj Padesur

Abstract: This paper introduces a design and realization of an Automated Wireless Charging System based on Arduino microcontroller. The reader is configured to sense presence of a device in an assigned slot and automatically switch on wireless charging. The system consists of ultrasonic sensors, relay modules and an LCD display to efficiently regulate the charging slots. You put your charging device in front of it and under the ultrasonic sensors, and the distance that is detected switch the relay by the Arduino to start or stop the charging. A 16×2 LCD Display through I2C communication for real time feedback about the charging status, which slot is occupied (either Slot 1 or Slot 2). The system works at two voltages, 5V and 2.5V. The goal is to make charging all the more convenient – in the simplest turn of the wrist power transmission is activated free of contact, without any cables and connectors getting involved. It’s especially great for wireless charging pads, smart furniture, and industrial automation. Experimental results show that the system can perform accurate object detection, activate the charging process, and reflect slot status in real time.

Fire Fighting Robotic Vehicle Using IOT

Authors: Yashmita Mudgal, M Akhila, E Abhishek, G Sravan, S Praveena

Abstract: Fire incidents are hazardous events that can result in the loss of lives, significant property damage, and severe environmental consequences. This project introduces a fire-fighting robotic vehicle capable of detecting and extinguishing fires autonomously, thereby minimizing human involvement and improving overall safety. The robotic vehicle employs flame sensors for accurate fire detection and an Arduino UNO microcontroller to control its operations. Equipped with gear motors, motor driver, and servo- controlled water pump, the robot navigates toward the fire source and extinguishes it. It also includes a GSM module to send SMS alerts and a Bluetooth module for manual override via mobile. This system provides a practical, scalable, and intelligent solution to fire emergencies, particularly in industrial and hazardous environments.

Zero-Water Cooling For Modern AI Data Centers

Authors: Girish Kishor Ingavale

Abstract: The exponential growth of various technologies, including artificial intelligence (AI), cloud computing, and big data analytics, has led to an unprecedented surge in the computational demands placed on data centers. This paper provides a detailed review of innovative zero-water cooling technologies that offer an alternative to traditional water-based cooling systems, ensuring optimal operating temperatures for AI hardware. We examine various waterless cooling methods, including immersion cooling, air-cooled heat sinks, and phase-change materials, assessing their effectiveness, energy efficiency, and environmental impact. Recent advancements in these technologies have significantly transformed thermal management practices in AI data centers, demonstrating a reduction of up to 50% in energy consumption while completely eliminating water usage in high-performance computing environments. We analyse recent innovations such as two-phase immersion cooling and advanced heat exchange systems, discussing their implementation in large-scale AI infrastructure. Additionally, the article examines the Closed Loop, Zero-Water Evaporation Design technique and its impact on Power Usage Effectiveness (PUE) and Water Usage Effectiveness (WUE). The findings highlight the potential of these technologies to enhance sustainability and operational efficiency in data center cooling, offering a promising solution to the thermal management challenges posed by the growing demand for AI workloads.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.121

Reinforcement Learning-Based Optimal Control For Real-Time Electric Vehicle Energy Management

Authors: Professor Adel Elgammal

Abstract: It is within this context of the growing popularity of electric vehicles (EVs) that the development of smart energy management, which can optimally manage the power consumption, increase the battery life, and enhance the vehicle efficiency in various driving patterns and conditions, has become essential. Conventional control strategies such as rule-based strategies and model predictive control can work well in controlled environments, but may be insufficiently resilient to the real-world complexity of changing traffic, gradients, and driver actions. In this work, a new real-time energy management strategy for EVs is developed by means of a RL-based optimal control framework, where DQN is adopted to dynamically optimize decisions about energy utilization. The proposed RL controller learns the optimal policies by exploring the real-time high-fidelity EV simulation environment, which accounts for vehicle dynamics, battery attributes, and external driving conditions. Unlike classical controllers, the RL-based solution does not require any predefined models or future prediction horizon to operate, as it continually learns from its own experience to decide in real-time on the power split between the electrical machine and auxiliary systems. The reward functions are designed to optimize for, for instance, energy efficiency, battery health, and driving performance features e.g. acceleration and driving smoothness. Simulation results show that the proposed RL-based controller can outperform benchmark strategies in various driving scenarios, obtaining up to 18% better energy efficiency and increased adaptability to changing situations. Moreover, the learned policy is robust in controlling battery temperature and state of charge (SOC) fluctuation which results in an increased battery life. This research reveals the capabilities of reinforcement learning as a promising scalable and self-adaptive technique for energy control in future EVs. For future works, we plan to further consider practical applications, multi-agent vehicle coordination, and integrating the proposed algorithm with V2I to realize cooperative energy optimization in smart transportation networks.

A Comparative Study On Additive Cross-Modal Attention Network (ACMA) For Depression Detection Based On Audio And Textual Features

Authors: Asif S Majeed, Evelyn Treasa Jaison, Fathima S, Arunlal M L, Dr. Jyothi R L, Swathi S

Abstract: This study introduces an approach for depression detection through an Additive Cross-Modal Attention Network (ACMA) that integrates audio and textual data to improve diagnostic accuracy without relying on self-report questionnaires. Traditional depression assessments often depend on patient- disclosed information, which may not always be accurate due to stigma or personal reluctance, leading to potential underdiagno- sis. The ACMA model addresses these limitations by leveraging cross-modal attention mechanisms within a Bidirectional Long Short-Term Memory (BiLSTM) and Transformer model to cap- ture and assign optimal weights to relevant features across audio and text modalities. This enables the model to effectively detect depressive symptoms by analyzing both linguistic and acoustic cues. The model is designed for both binary classification (depressed vs. non-depressed) and regression tasks to estimate depression severity, utilizing the DAIC-WOZ dataset for evaluation. ACMA demonstrates significant improvements over baseline models, achieving high accuracy, recall, and F1 scores. Additionally, the model’s adaptability across different datasets underscores its potential as a robust, non-intrusive tool for clinical applications in mental health diagnostics. This work advances the field of au- tomated depression detection, providing a foundation for further research in cross-modal mental health assessment systems.

Balancing Monetization And Player Experience In Free-to-Play (F2P) Games

Authors: Parth Rastogi

Abstract: The gaming industry has witnessed an absolute change because of the Free-to-Play (F2P) model, which not only provides everyone with the chance to enjoy games free of charge but also produces substantial revenue through in-game purchases. The potential threats to the player experience posed by intrusive monetization methods, in particular, loot boxes and pay-2-win mechanics, can result in decreased user engagement and long-run dissatisfaction. This survey studies the ways in which a game developer can achieve the balance between monetization optimization and a player experience – maintaining a high-quality player experience. A research that used a mixed-methods approach was carried out by the authors, including surveys, interviews, and sentiment analysis. The preliminary results support the idea that ethical, viable monetization schemes, like digital clothes in shop and game passes, are good methods for revenue generation and maintaining the player base. On the contrary, those that use exploitative measures will often encounter dislike and a high churn rate, as well. -seen in the gamers’ reactions to this interaction. The strategies include the most suitable ones for fair, transparent, and sustainable monetization in F2P games.

A Smart Iot-Based Water Pollution Monitoring and Alert System for Industrial Waste Management

Authors: Sishank Singh Rawat, Satyam Dhar, Assistant Professor Dr. Prakash

Abstract: With rising expectations for instant, contactless, and personalized retail experiences, companies like Mars Inc., a global leader in the confectionery industry, are looking to modernize their vending operations. Traditional vending systems are constrained by static inventory models, manual restocking, and a lack of real-time adaptability—leading to stockouts, waste, and poor customer satisfaction. This paper introduces the Intelligent Vending Machine Optimization System, a smart retail solution designed to transform Mars Inc.’s global vending infrastructure. The system integrates IoT sensors, Azure-based Medallion architecture, machine learning, and edge computing to deliver predictive restocking, autonomous maintenance, and real-time customer insights. Voice and gesture-based interfaces improve accessibility, while Power BI dashboards offer centralized monitoring. This approach ensures scalable, energy-efficient, and intelligent vending operations, enabling Mars Inc. to lead the future of automated retail with data-driven precision.

EduTracker Association Platform

Authors: Assistant Professor Priya Tyagi, Assistant Professor Dr. A.P Srivastava, Sandeep Kumar Yadav, Sahil Gupta

Abstract: The Edu Tracker Association Platform is a comprehensive web-based application developed using the MERN stack (MongoDB, Express.js, React.js, Node.js) that aims to streamline and enhance the management of educational activities, associations, and student performance tracking within academic institutions. The platform serves as a centralized hub for administrators, faculty, and students to interact, monitor, and manage academic and extracurricular engagements efficiently. By leveraging the full-stack capabilities of MERN, the system ensures a highly responsive user interface (React.js), robust server-side logic (Node.js and Express.js), and scalable data storage (MongoDB). Key features include student profile management, real-time performance tracking, association membership management, event scheduling, and detailed reporting tools. Role-based access control ensures secure data handling and personalized user experiences for students, faculty, and administrators. The Edu Tracker Association Platform enhances transparency, encourages student engagement in academic and non-academic activities, and simplifies the evaluation process. With its modular architecture and RESTful API integration, the platform is designed for scalability, future expansion, and integration with existing educational systems.

Oral Cancer Detection Using Deep Learning

Authors: Assistant Professor Mrs. G. Sangeetha Lakshmi, Mrs. S. Hemalatha

Abstract: Early and precise detection of oral cancer is critical for improving patient outcomes, yet conventional diagnostic methods often involve manual analysis, which can be slow and susceptible to human error. To overcome these limitations, this research introduces an automated detection system that combines deep learning for feature extraction with the Random Forest algorithm for classification. By analyzing medical images, the deep learning component identifies essential features such as texture, color inconsistencies, and irregular tissue structures. These features are then processed by the Random Forest classifier, which utilizes an ensemble of decision trees to enhance classification accuracy and minimize errors. Trained on a dedicated dataset of oral cancer images, the model effectively differentiates between malignant and benign tissues. Experimental findings reveal that this hybrid approach outperforms standard machine learning techniques, offering a faster and more dependable diagnostic tool to aid clinicians in early oral cancer detection and improve patient survival rates.

Lung Cancer Prediction

Authors: Md Shareef, P Sri Sindu, M Surya Teja, B Prasun Reddy

Abstract: Lung cancer remains a leading cause of cancer-related mortality worldwide, underscoring the critical need for effective predictive models to aid in early detection and intervention. This study presents a comprehensive approach to lung cancer prediction, leveraging advanced machine learning techniques and multimodal data integration. By incorporating diverse sources of information, including medical imaging scans, clinical records, and genetic markers, our proposed model aims to capture the complex interplay of factors influencing lung cancer risk. We employ a combination of feature engineering, feature selection, and ensemble learning methods to develop robust predictive models capable of accurately identifying individuals at elevated risk of developing lung cancer. Furthermore, we explore the interpretability of our models to gain insights into the underlying factors driving lung cancer susceptibility. Through extensive experimentation and validation on large-scale datasets, we demonstrate the efficacy of our approach in achieving superior predictive performance compared to existing methods. The proposed model holds significant promise for facilitating early detection, personalized risk assessment, and targeted interventions in lung cancer management, ultimately improving patient outcomes and reducing the burden of this devastating disease.

Lifelong Learning And Risk Management In Smes: Economic Practices For A Sutainable Future

Authors: Nishant Verma, Associate Professor Dr. Mehak

Abstract: This paper explores risk management practices in Small and Medium Enterprises (SMEs) through the interdisciplinary lenses of psychology, economics, and linguistics, emphasizing the role of lifelong learning in achieving sustainable futures. By examining how SMEs perceive, communicate, and economically strategize around risk, we uncover the cognitive, communicative, and systemic factors shaping risk resilience. This study draws on empirical data, theoretical frameworks, and case studies to advocate for integrative, adaptive, and continuous learning mechanisms to enhance SMEs’ sustainability and competitiveness in an increasingly volatile global market.Risk management is a critical component of business strategy, particularly for Small and Medium Enterprises (SMES) that often lack the resources of larger corporations. This paper investigates the risk management practices adopted by SMES, exploring their effectiveness, challenges, and the role of organizational culture, awareness, and external support. Using a mixed-methods approach, the study identifies common risks faced by SMES, evaluates current mitigation strategies, and proposes a framework for improved risk management. The findings highlight a need for enhanced awareness, training, and integration of risk management into business planning. This paper investigates the current landscape of risk management practices among SMES, with a focus on how they perceive, assess, and respond to various types of risks. Drawing on a mixed-methods research approach, including quantitative surveys and qualitative interviews with SME owners and managers, the study reveals that while most SMES recognize the existence of critical risks, few possess structured or formal risk management systems. Instead, risk responses are often reactive, ad hoc, and based on the intuition and personal experiences of the business owner rather than systematic analysis.

Synchronization Algorithm For Local And Cloud Files For Streamlining Management And Resolving Conflict Effectively

Authors: Mr. Akshay M. Bodule, Dr. D.N. Chaudhari, Dr. A.P. Jadhao, Professor D.G. Ingale

Abstract: With the exponential rise in cloud storage usage and the growing demand for cross-platform accessibility, efficient file synchronization has become a critical requirement in modern computing environments. Traditional synchronization techniques, which often rely on full-file transfers and timestamp-based comparisons, are no longer sufficient—particularly in bandwidth-constrained or resource-limited scenarios such as mobile networks and edge computing systems. This paper presents a hybrid synchronization approach that integrates Two-Way Synchronization and Differential Synchronization to improve efficiency, reduce bandwidth consumption, and enhance data consistency. Two-Way Synchronization enables the detection and resolution of file changes from both local and cloud sources, supporting intelligent decision-making for conflict resolution, deletion propagation, and duplicate handling. Differential Synchronization enhances this process by transmitting only the modified segments of files, using techniques such as block-level comparison and rolling hashes, thereby significantly minimizing data transfer volume and synchronization time. The paper outlines the architecture, entities, processes, and data flows involved in each technique, along with corresponding algorithms and flowcharts. Finally, the paper identifies future challenges, focusing on component-level implementation, delta generation, metadata management, and cloud integration. The proposed solution offers a scalable and bandwidth-efficient synchronization framework suitable for real-time collaboration, offline-to-online transitions, and deployment in distributed and hybrid cloud environments.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.120

Development Of A Smart Wearable System For Monitoring Student Attendance And Activity Participation Through ID Scanning

Authors: Amuncio, Jun Rey, Crisostomo, Kenneth, Gatinao, Hannah Michaela G, Palomo, Gerber Jay L, Paculanan, Kristian Jay C, Cedie E. Gabriel MIT

Abstract: The study presents the development and evaluation of a smart wearable system to monitor student appearance and activity participation through ID scanning at South East Asian Institute of Technology (SEAIT), Tupi, South Kotabato. Methods of traditional appearance in educational institutions are often disabled, error-prone and susceptible to manipulation. The project integrates human-computer interaction (HCI) principles into a smart wearable device that uses ID scanning to automate the attendance and recording of student participation. The system aims to improve accuracy, reduce administrative burden, and increase the user experience through user -friendly interfaces and real -time data processing. The purposeful test and performance assessment demonstrated that the system provides more efficiency and satisfaction than traditional methods, although some users expressed concern over the need for privacy and additional support. Overall, the system shows strong ability to increase institutional operations in the resource-limit environment.

Development Of A Smart Wearable System For Monitoring Student Attendance And Activity Participation Through ID Scanning

Authors: Amuncio, Jun Rey, Crisostomo, Kenneth, Gatinao, Hannah Michaela G, Palomo, Gerber Jay L, Paculanan, Kristian Jay C, Cedie E. Gabriel MIT

Abstract: The study presents the development and evaluation of a smart wearable system to monitor student appearance and activity participation through ID scanning at South East Asian Institute of Technology (SEAIT), Tupi, South Kotabato. Methods of traditional appearance in educational institutions are often disabled, error-prone and susceptible to manipulation. The project integrates human-computer interaction (HCI) principles into a smart wearable device that uses ID scanning to automate the attendance and recording of student participation. The system aims to improve accuracy, reduce administrative burden, and increase the user experience through user -friendly interfaces and real -time data processing. The purposeful test and performance assessment demonstrated that the system provides more efficiency and satisfaction than traditional methods, although some users expressed concern over the need for privacy and additional support. Overall, the system shows strong ability to increase institutional operations in the resource-limit environment.

Analysis Of Anomaly Detection Of Malware Using SVM

Authors: Ashu Gulia, Sangeeta Rani, Monika Saini

Abstract: In the realm of cybersecurity, the continuous evolution and sophistication of malware pose significant challenges to the detection and mitigation of cyber threats. This research paper delves into the analysis of anomaly detection of malware using Support Vector Machines (SVM), a powerful machine learning algorithm known for its effectiveness in classification tasks. By leveraging SVM for anomaly detection, this study aims to explore the potential of SVM in identifying malicious behavior patterns that deviate from normal system activities. The paper provides insights into implementing SVM-based anomaly detection for malware, including data preprocessing, feature extraction, model training, and evaluation. Furthermore, the research investigates the performance of SVM in detecting various types of malware and assesses its effectiveness in real-world scenarios. Through a comprehensive analysis, this paper contributes to the understanding of SVM-based anomaly detection techniques for malware. It provides valuable insights into the efficacy and limitations of SVM in combating cyber threats.

Significance Of Risk Management In Oil & Gas Industry

Authors: Sandhya Sharma

Abstract: The oil and gas sector are recognized as one of the most complex and high-risk industries worldwide, requiring substantial capital and operating across multiple hazardous domains. Activities ranging from exploration and extraction to processing and distribution expose the industry to significant challenges, including technical failures, volatile market dynamics, environmental impacts, and stringent regulatory demands. In this high-stakes context, risk management is essential for proactively identifying, evaluating, and mitigating threats to personnel safety, environmental integrity, and operational continuity. It also plays a crucial role in ensuring regulatory compliance, protecting financial assets, and maintaining stakeholder trust. This paper examines the critical importance of risk management in the oil and gas industry, focusing on its role in enhancing health and safety standards, supporting financial and operational stability, and guiding strategic decisions. As expectations for environmental responsibility and corporate transparency continue to grow, the adoption of comprehensive risk management practices is increasingly seen as a fundamental element of sustainable and accountable energy operations.

A DETAILED ANALYSIS OF ELECTRIC VEHICLE TECHNOLOGY ADVANCEMENTS AND FUTURE PROSPECTS

Authors: Ms. Geeta Raut, Pusp Ranjan

Abstract: The financial sector is undergoing rapid digital transformation, accompanied by a surge in cyber threats and fraud. Traditional centralized machine learning approaches for fraud detection are increasingly limited by privacy concerns, data-sharing restrictions, and regulatory compliance issues. Federated Learning (FL) offers a decentralized alternative by enabling collaborative model training across institutions without sharing sensitive data. This survey explores the application of FL in financial security, focusing on its foundations, privacy-preserving mechanisms, and real-world use cases such as fraud detection, credit scoring, and customer behavior analysis. We compare FL with existing centralized techniques in terms of accuracy, privacy, adaptability, and scalability. Additionally, we examine how FL integrates with emerging technologies like blockchain, Explainable AI (XAI), and Secure Multi-Party Computation (SMPC). The paper highlights key challenges, research gaps, and future directions, providing a comprehensive overview of FL’s potential to revolutionize secure and intelligent financial systems.

The Dawn Of Quantum Computing

Authors: Assistant Professor Bharathi V, Divya Bairavi

Abstract: Quantum computing represents a paradigm shift from classical computing by leveraging the principles of quantum mechanics—superposition, entanglement, and quantum interference—to solve problems that were previously considered intractable. This chapter provides a comprehensive introduction to quantum computing, tracing its evolution from theoretical foundations laid by Feynman and Deutsch to landmark achievements such as Google’s demonstration of quantum supremacy. We explore the fundamental differences between classical bits and quantum bits (qubits), elucidating how quantum phenomena empower new algorithmic capabilities exemplified by Shor’s and Grover’s algorithms. The discussion highlights transformative applications across cryptography, optimization, molecular simulation, and artificial intelligence, emphasizing the disruptive potential of quantum machine learning and quantum neural networks. Despite its promise, quantum computing faces critical engineering and theoretical challenges, including qubit decoherence, error correction, and scalability. However, with rapid advancements in quantum hardware and algorithms, the technology is poised to redefine computing in the 21st century. This chapter invites readers to engage with the unfolding narrative of quantum computing, a frontier where science fiction converges with computational reality.

House Price Prediction Using Machine Learning

Authors: Assistant professor Mrs. R. Bhuvaneshwari, Ms. T. Misha

Abstract: Predicting house prices is both vital and complex due to the ever-changing nature of the real estate market. Conventional statistical approaches often fall short in identifying intricate data trends, making machine learning a more suitable solution. This project adopts the Support Vector Machine (SVM) algorithm to forecast housing prices by analyzing historical data and key market influences. Known for its ability to manage high-dimensional datasets and model nonlinear relationships, SVM proves to be a dependable method for accurate price prediction. The system evaluates multiple factors including geographic location, property dimensions, prevailing market trends, and economic conditions to improve prediction precision. Through SVM’s capabilities in both classification and regression, the model delivers strong, data-informed insights that assist homebuyers, sellers, and investors in navigating the dynamic real estate environment effectively.

House Price Prediction Using Machine Learning

Authors: Assistant professor Mrs. R. Bhuvaneshwari, Ms. T. Misha

Abstract: Predicting house prices is both vital and complex due to the ever-changing nature of the real estate market. Conventional statistical approaches often fall short in identifying intricate data trends, making machine learning a more suitable solution. This project adopts the Support Vector Machine (SVM) algorithm to forecast housing prices by analyzing historical data and key market influences. Known for its ability to manage high-dimensional datasets and model nonlinear relationships, SVM proves to be a dependable method for accurate price prediction. The system evaluates multiple factors including geographic location, property dimensions, prevailing market trends, and economic conditions to improve prediction precision. Through SVM’s capabilities in both classification and regression, the model delivers strong, data-informed insights that assist homebuyers, sellers, and investors in navigating the dynamic real estate environment effectively.

Investigation Of Progressive Encryption Methods For Enrichment In Safety Of Big Data In Cloud Computing

Authors: Ms. Rashmi, Professor Gaurav Aggarwal

Abstract: As technology advances, the development of lightweight yet secure encryption algorithms and improved key management strategies will play a crucial role in addressing emerging challenges. Ultimately, progressive encryption stands out as a vital component in fortifying cloud computing infrastructures against cyber threats, ensuring trust and reliability in the digital era.In this paper discussion will be made on the researches based on how we secure big data in cloud computing. Discussion of security algorithm has been made that are capable to secure data. Reduction of packet size using packet reduction logic leads to less space and time consumption. Mat lab based simulation will represent the working comparative analysis of time taken between tradition and proposed work after load balancing will conclude that proposed model will take less time. The main concentration of this research is towards the strategies of energy-efficient resource arrangement and security of data over cloud.

Zero-Water Cooling For Modern AI Data Centers

Authors: Girish Kishor Ingavale

Abstract: The exponential growth of various technologies, including artificial intelligence (AI), cloud computing, and big data analytics, has led to an unprecedented surge in the computational demands placed on data centers. This paper provides a detailed review of innovative zero-water cooling technologies that offer an alternative to traditional water-based cooling systems, ensuring optimal operating temperatures for AI hardware. We examine various waterless cooling methods, including immersion cooling, air-cooled heat sinks, and phase-change materials, assessing their effectiveness, energy efficiency, and environmental impact. Recent advancements in these technologies have significantly transformed thermal management practices in AI data centers, demonstrating a reduction of up to 50% in energy consumption while completely eliminating water usage in high-performance computing environments. We analyse recent innovations such as two-phase immersion cooling and advanced heat exchange systems, discussing their implementation in large-scale AI infrastructure. Additionally, the article examines the Closed Loop, Zero-Water Evaporation Design technique and its impact on Power Usage Effectiveness (PUE) and Water Usage Effectiveness (WUE). The findings highlight the potential of these technologies to enhance sustainability and operational efficiency in data center cooling, offering a promising solution to the thermal management challenges posed by the growing demand for AI workloads.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.121

AI In Cybersecurity: Transforming Digital Defense

Authors: Parash Pandey, Siddarth Gupta, Abhishek Kumar, Anmol Choudhary

Abstract: Artificial Intelligence (AI) is rapidly becoming a key part of modern cybersecurity. This paper explores how AI is changing digital security systems by automating threat detection, analyzing patterns, and helping respond to attacks faster than ever. AI helps detect cyber threats, protect data, and reduce the need for manual monitoring. But it also introduces new risks, such as biased algorithms, adversarial attacks, and privacy concerns. This paper highlights current applications, advantages, and challenges of AI in cybersecurity, and suggests ways to ensure responsible use of this powerful technology.

Design And Development Of Pyramid Solar Still Using Phase Change Material

Authors: Shriram Deshpande, Shridhar Dhaduti, Rahul Meeshi, Daneshwari Jambagi

Abstract: Adequate quality and reliability of drinking water is vital for all inhabitants and for agriculture and industrial applications. Solar desalination is impactful method for getting potable water from brackish/wastewater in hot climatic condition and/or remote area where the scarcity of water as well as for electricity. In recent years, attention has been focused on development of various designs of solar still in order to overcome limitations possesses by conventional single basin single slope solar still. Pyramid solar still is one of the outcomes of such a development. This project reviews the development in the field of pyramid solar still as well as the various techniques to improve the performance of still. From the review on research carried out by the various researchers, it has been found that pyramid solar still is more efficient and economical in compare to conventional single slope single basin still.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.122

Artificial Intelligence In Healthcare: A Comprehensive Review

Authors: Siddharth Gupta, Vineet Gupta, Muskan Jaiswal, Karishma Priya Dwivedi

Abstract: Artificial Intelligence (AI) is rapidly transforming healthcare by enhancing diagnostics, optimizing treatments, and improving operational efficiency. This paper presents a detailed analysis of AI applications in healthcare, case studies, data insights, challenges, risks, and future directions. It leverages clinical datasets and published research to examine the practical impact of AI on patient care and hospital systems.

Role Of Operations Research In Car Rental Industry

Authors: Raghu V. Kaspa, Kevin Camenzuli, Salai S

Abstract: The car rental industry faces increasingly complex challenges in optimizing fleet utilization, responding to demand variability, and managing operational costs. As competition intensifies and consumer expectations evolve, effective fleet management has become more vital than ever. Operations Research (OR) provides a suite of mathematical models, optimization techniques, and decision-making frameworks that help car rental firms streamline their operations. This paper explores how OR methodologies can be applied to key aspects of fleet management, including demand forecasting, fleet sizing and composition, vehicle allocation and relocation, and dynamic pricing. It also analyzes real-world case studies where OR tools have been successfully implemented and examines current challenges and future directions for the industry. By employing OR, car rental companies can improve operational efficiency, boost profitability, and offer better customer experiences.

DOI: 10.61137/ijsret.vol.11.issue3.123

Simulated Annealing As A Machine Learning Model: Principles, Applications, And Comparative Analysis

Authors: Raghu V Kaspa, Ramya K Cherukuvada

Abstract: Simulated Annealing (SA) is a probabilistic technique used for approximating the global optimum of a given function, with origins in statistical mechanics. It has found widespread utility in optimization problems central to machine learning (ML), particularly where the solution space is large and complex. This paper investigates the theoretical underpinnings of SA, explores its applications within ML domains, compares it with other optimization algorithms, and evaluates its performance. The work concludes with a discussion on SA’s strengths and limitations in the context of modern ML challenges. The purpose of this research is to position SA as a viable tool in the ML optimization toolkit, particularly for tasks involving large, multi-modal search spaces where deterministic methods may falter.

DOI: 10.61137/ijsret.vol.11.issue3.124

Simulated Annealing As A Machine Learning Model: Principles, Applications, And Comparative Analysis

Authors: Raghu V Kaspa, Ramya K Cherukuvada

Abstract: Simulated Annealing (SA) is a probabilistic technique used for approximating the global optimum of a given function, with origins in statistical mechanics. It has found widespread utility in optimization problems central to machine learning (ML), particularly where the solution space is large and complex. This paper investigates the theoretical underpinnings of SA, explores its applications within ML domains, compares it with other optimization algorithms, and evaluates its performance. The work concludes with a discussion on SA’s strengths and limitations in the context of modern ML challenges. The purpose of this research is to position SA as a viable tool in the ML optimization toolkit, particularly for tasks involving large, multi-modal search spaces where deterministic methods may falter.

DOI: 10.61137/ijsret.vol.11.issue3.124

Status Of The Revised Computerization Program And Organizational Performance In The Division Of San Pedro City: Basis For A Proposed status Of The Revised Computerization Program And Organizational Performance In The Division Of San Pedro City: Basis For A Proposed Intervention Scheme Intervention Scheme

Authors: MA. Michelle V. Valles

Abstract: This study investigates the implementation of the Revised Computerization Program (D.O. No. 16, s. 2023) and its impact on organizational performance within the San Pedro City Schools Division. Utilizing a descriptive research design, data were collected from 345 respondents (supervisors, school administrators, teachers, and non-teaching personnel) through surveys and documentary analysis. The study employed statistical tools such as weighted mean, ANOVA, Pearson correlation, and t-test to analyze the data. Findings reveal that while the program is generally implemented, significant challenges persist, particularly concerning inadequate hardware infrastructure, insufficient teacher training, and unreliable internet connectivity. Despite these challenges, a strong positive correlation was found between the program’s implementation and organizational performance. Based on these findings, a proposed intervention scheme (PACTS: Program for Advancing Computerization and Technologies in Schools) is presented and deemed highly acceptable by respondents. This scheme, which includes targeted strategies for hardware upgrades, enhanced teacher training, and improved internet access, is recommended for implementation to further enhance the effectiveness of the Revised Computerization Program and optimize organizational performance within the San Pedro City Schools Division.

Development and Fabrication of a Plastic Waste to Fuel Conversion Unit

Authors: Harshita Shukla, Archit Budiyal, Assistant Professor Er. Vivek Agnihotri

Abstract: The global rise in energy demand and environmental degradation, largely due to industrialization and rapid population growth, has highlighted the urgent need for sustainable waste management and alternative energy solutions. Plastic waste, in particular, poses a serious ecological challenge because of its non-biodegradable nature and the drawbacks of traditional disposal methods like landfilling, incineration, and mechanical recycling, which often result in harmful environmental and health impacts. This study focuses on pyrolysis, a thermochemical process conducted in the absence of oxygen, to convert plastic waste—specifically polypropylene—into valuable fuel products such as pyrolytic oil, non- condensable gases, and char. The pyrolytic oil obtained from this process has calorific properties similar to conventional fossil fuels, making it a promising substitute. Pyrolysis is also capable of processing mixed and unwashed plastics, reducing the need for pre- treatment and minimizing toxic emissions compared to incineration. This research explores the efficiency and fuel yield of plastic waste pyrolysis under controlled conditions, demonstrating its potential as a sustainable waste-to-energy method. The findings support the integration of pyrolysis into circular economy strategies by addressing plastic pollution and contributing to clean energy generation.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.125

UPI: A Digital Nexus And Catalyst For Financial Inclusion And Economic Growth

Authors: Mitali Vashishtha

Abstract: This paper explores Unified Payments Interface (UPI), a digital payment system developed in India. It examines how it connects with banks, reduces environmental impact through digital transactions, and promotes financial inclusion. The paper examines the role of the Unified Payments Interface (UPI) in promoting sustainability in finance. It highlights how UPI has transformed digital payments by integrating seamlessly with banks, fostering financial inclusion, and reducing reliance on physical infrastructure. The research explores its contributions to economic sustainability, by lowering transaction costs and enabling cashless ecosystems, and environmental sustainability , through paperless transactions and reduced carbon footprints. Additionally, the paper discusses UPI’s integration with the banking ecosystem, its challenges, and its potential as a model for sustainable digital finance.

Performance, Evaluation And Suggestion Study Of ETP Of Galvanising Unit- A Case Study On KEC Industry

Authors: Deepshikha Jain, Associate Professor R.K.Bhatia

Abstract: The purpose is to investigate the sources and physio-chemical characteristics of effluent generated by the galvanizing industry. This study aims to highlight the potential environmental impacts of such effluents and to identify the specific metallic pollutants present.Study Design/Methodology/ApproachA comprehensive analysis was conducted on effluent samples collected from various galvanizing facilities. The study employed standard analytical techniques to measure key physio-chemical parameters, including pH, biochemical oxygen demand (BOD), and chemical oxygen demand (COD). Finding.The analysis revealed that the effluent exhibited an acidic pH, indicating a significant deviation from neutral conditions. High levels of BOD and COD were detected, suggesting a substantial organic load that could negatively impact aquatic ecosystems. These findings underscore the pressing need for effective treatment and management strategies to mitigate the environmental risks associated with galvanizing industry effluents. Originality This study contributes to the existing body of knowledge by providing a detailed characterization of galvanizing industry effluents. The identification of specific metallic pollutants offers valuable insights for regulatory agencies and industry stakeholders. The findings serve as a foundation for future research aimed at enhancing effluent treatment processes and promoting sustainable practices within the galvanizing sector.

DOI: 10.61137/ijsret.vol.11.issue3.126

Cluster Head Selection Model Energy Balancing In IOT Heterogeneous WSN

Authors: Aakansha Deshmukh, Professor Amit Thakur

Abstract: Internet-of-Things (IoT)-based Heterogeneous Wireless Sensor Network (HWSN) has emerged as a prevalent technology that plays a significant role in developing various human-centric applications. Like in a wireless sensor network (WSN), energy is also the most crucial resource in IoT-based HWSN. The researchers have proposed many works to achieve energy-efficient network operations by minimizing energy usage. A vast proportion of these works emphasize using the clustering approach, which has proved its worth to a great extent. However, most schemes require the repeated formation of clusters incurring a significant amount of nodes’ energy in the clustering process. The protocol design of such schemes also varies with the changing levels of heterogeneity. In this work, a hybrid clustering scheme- An Energy-Efficient Hybrid Clustering Technique (EEHCT) has been proposed for IoT-based HWSN that minimizes the energy consumption in clusters’ formation and distributes the network load evenly irrespective of the heterogeneity level to prolong network lifetime. It appropriately utilizes dynamic and static clustering strategies to formulate the load-balanced clusters in the network.

DOI: http://doi.org/

Wearable IOT With Artificial Intelligence Approach Solution For Reliable Smart Health Care.

Authors: Madhvi Sharma, Professor Amit Thakur

Abstract: The revolution of Internet of Things (IoT) is pervading many facets of our everyday life. Among the multiple IoT application domains, well-being is becoming one of the popular scenarios in IoT which aims to offer new services including smart fitness. This paper focuses on smart fitness covering IoT-based solutions for this domain as well as the impacts of artificial intelligence and social-IoT. IoT-based smart fitness is divided into three categories: Fitness trackers (including wearable and non-wearable sensors), movement analysis and fitness applications. Data collected from IoT-based smart fitness and users could be used for enhancing training performance by Artificial Intelligence (AI)-based algorithms. Sensor to sensor relationship is another notable topic which can be implemented by social-IoT that can share data, information and experiences of users’ training from different places and times. In this his study a comprehensive review on different types of fitness trackers and fitness applications in provided and followed by a review of AI algorithms used in smart fitness scenarios. Lastly detail discussions on the benefits and the potential problems of smart fitness are presented and a shortlist of existing gaps and potential future work have been identified and proposed.

Energy Aware Clustering Based Routing Protocol For WSN Bases IOT

Authors: Professor Amit Thakur, Tanishka Mangal

Abstract: Clustering in wireless sensor network (WSN) is an efficient approach to provide prolonged network life time, scalability and data aggregation. Clustering also conserves the limited energy resources, for this reason in this work; we propose an energy aware static clustering routing protocol for WSN. The specificity of this work is that the network is partitioned into static clusters that contain a Primary Cluster Head (P-CH) and a Secondary Cluster Head (S-CH) and both of them are selected based on energy. The simulation results show that the new protocol proposed in this work extends the network lifetime and balances the energy consumption of the network nodes.

Deaf And Mute Language Identification Using Machine Learning

Authors: Vaishnavi Yelnare, Dr.Santosh Gaikwad, Dr. A. A. Khan, Dr. R. S. Deshpandes

Abstract: This research undertakes an in-depth exploration into the utilization of machine learning algorithms for the recognition and classification of sign languages commonly used by individuals within the deaf and mute communities. We evaluate different models, such as CNNs, LSTMs, and hybrid networks, for gesture recogni- tion, image processing, and sequence classification. Chal- lenges including lighting, occlusion, inter-user variability, and data scarcity are addressed. Experiments are con- ducted on real-world datasets like RWTH-BOSTON and American Sign Language (ASL) to benchmark model performance. Our study contributes a scalable, real-time framework for sign language recognition, which aids in bridging communication gaps for the hearing-impaired community.

EXPLORING THE DIFFICULTIES AND PROSPECTS BROUGHT WITH THE ADOPTION OF COMPUTER STUDIES IN PUBLIC LEARNING INSTITUTIONS: A CASE STUDY OF FOUR SELECTED PUBLIC DAY SECONDARY SCHOOLS IN LUWINGU DISTRICT OF NORTHERN PROVINCE, ZAMBIA.

Authors: Francis Mumba

Abstract: Exploring The Difficulties And Prospects Brought With The Adoption Of Computer Studies In Public Learning Institutions: A Case Study Of Four Selected Public Day Secondary Schools In Luwingu District Of Northern Province, Zambia

DOI:

Efficient Information Exchange Algorithm For Biomedical IOT Based On AI And Block Chain.

Authors: Nilesh Shrivas, Amit Thakur

Abstract: The development of artificial intelligence (AI) based medical Internet of Things (IoT) technology plays a crucial role in making the collection and exchange of medical information more convenient. However, security, privacy, and efficiency issues during information exchange have become pressing challenges. While many scholars have proposed solutions based on AI and blockchain to address these issues, few have focused on the impact of the slow consensus algorithm of blockchain on the efficiency of information exchange. To improve the efficiency of information exchange, we propose an information exchange approach based on AI and DA Genabled blockchain, providing a secure and efficient environment for information exchange in the medical IoT. Additionally, to enhance the efficiency of information exchange in the medical IoT, a novel tip selection algorithm is introduced to reduce the time delay in reaching consensus, thereby enabling faster acquisition of trusted information via blockchain. Simulation results demonstrate that compared to methods based on traditional DAG-enabled blockchain, the approach proposed in this paper improves the efficiency of information exchange.

Utilizing And Application Of AI And IOT Technology For Different Risk Factor Of Sports

Authors: Prabhakar Tripathi, Amit Thakur

Abstract: Engaging in physical activity and exercise is essential for maintaining a healthy lifestyle and is a key factor in preventing and enhancing health. However, certain sports and physical activities may present an inherent risk of injury. Some intrinsic, extrinsic, mutable, non-mutable and initiating events may contribute as causes of injury in sports. This thematic review will provide an overview of the mechanisms that lead to sports injuries and the various elements that influence them. It will also explore the effects of sports injuries, how technology and innovation can be used to manage these risks and injuries, the significance of early risk analysis, and finally, future trends and directions in artificial intelligence research to reduce the risk of sports injuries and the strategies for managing them. By amalgamating the current state of knowledge within this field, the author aims to enhance our comprehension of the complex interplay and intricate relationship between the mechanisms of sports injuries and the prevention, management, and treatment of such injuries using emerging and evolving technologies. It’s essential to emphasize and underscore that advanced technologies should be seen as a complement and augmenting the role of healthcare professionals rather than substituting them, given the recognized limitations of the current system and the imperative necessity for personalized and tailored treatments that can vary from one athlete to another.

 

 

A Comprehensive Review On The Need For Data Driven Automated Handover Mechanisms In Future Generation Wireless Networks

Authors: Vijay Bisen, Dr. N.K. Singh

Abstract: Automated handovers are critically important for maintaining the Quality of Service (QoS) in wireless networks, typically in mobile UE scenarios.. With increasing number of users and multimedia applications, bandwidth efficiency in cellular networks has become a critical aspect for system design. Bandwidth is a vital resource shared by wireless networks. Hence its in critical to enhance bandwidth efficiency. Orthogonal Frequency Division Multiplexing (OFDM) and Non-Orthogonal Multiple access (NOMA) have been the leading contenders for modern wireless networks. NOMA is a technique in which multiple users data is separated in the power domain. A typical wireless system generally has the capability of automatic fall back or handover. In such cases, there can be a switching from one of the technologies to another parallel or co-existing technology in case of changes in system parameters such as Bit Error Rate (BER) etc. This paper presents a review on existing machine learning based approaches for handover prediction in future generation wireless networks. The salient features of each of the approaches has been highlighted along with identifying potential research gaps, rendering insights into potential search avenues in the domain.

 

 

Initiating Automated Handovers In Wireless Networks Employing Data Driven CSI

Authors: Vijay Bisen, Dr. N.K. Singh

Abstract: One of the key issues in ensuring uninterrupted service is the handover process — the transition of a mobile device’s connection from one base station to another. Traditional handover mechanisms, while functional, often struggle with the dynamic and complex environments of modern networks. This has led to increasing interest in leveraging machine learning (ML) to optimize and automate the handover process, enhancing both performance and user experience. Orthogonal Frequency Division Multiplexing (OFDM) and Non-Orthogonal Multiple access (NOMA) have been the leading contenders for modern wireless networks. NOMA is a technique in which multiple users data is separated in the power domain. In the proposed approach , a machine learning based handover mechanism between OFDM and NOMA has been proposed based on channel conditions. The condition for switching or handover has been chosen as the BER of the system. A comparative analysis with existing work indicates that the proposed scheme outperforms the existing techniques in terms of SNR requirement thereby making the system more practically useful for fading channel conditions.

 

 

Enhancing Contextual Emotion Recognition Using Large Vision-Language Models

Authors: Vaishnavi Chevale, Dr.Santosh Gaikwad, Dr. A. A. Khan, Dr. R. S. Deshpande§

 

 

Abstract: Contextual Emotion Recognition (CER) is crucial for human-computer interaction, requiring an understanding of emotions from linguistic and visual cues. This paper explores the integration of Large Vision- Language Models (LVLMs) to improve CER accuracy. The proposed framework employs multimodal learning to capture contextual dependencies, reduce biases, and enhance generalization. Experimental results demon- strate superior performance in real-world scenarios, de- creasing ambiguity and increasing robustness compared to traditional methods.

DOI: http://doi.org/

Causes Of Poor Academic Performance Of Pupils In Rural Primary Schools In Nsama District Of Northern Province – Zambia

Authors: Dionysius Makumba

Abstract: The Zambian education system has evolved over the years since independence. Zambia inherited it’s education system from Britain and has continued mostly in the same line of the British education system. The Zambian government has been working hard to improve on the education system and the education standards of it’s citizens. The performance of pupils is of great importance to government as well as the general citizenry. According to Nelson Mandela, “Education is the greatest weapon which you can use to change the world. “Thus, government has been doing everything possible to improve on the performance of pupils in schools. Measures such as free education policy by the United Party for National Development (UPND) government evidenced by overwhelming enrollments recorded in many schools for the past three years . Consequently, over enrollment has caused poor academic performance for example the number of pupils enrolled does not match with the infrastructure and number of teachers. Most teachers have gone to towns. Another cause is that most parents or guardians do not encourage their children to go to school because of their low educational attainment. They are the ones who send their children to do something else when they are suppose to be in school thereby contributing more to high rate of absenteeism. The nature of the district also is another cause to poor academic performance for instance, the road network is extremely bad which did not facilitate movement of standard officers to monitor schools. Vehicles break down on the way therefore schools that are far away from the district education board secretary’s (DEBS) office are often not monitored.

 

BlockChain, IOT and Deep Learning in Logistics Supply Chain Management

Authors:SNEHA, Professor Amit Thakur

Abstract: Efficient supply chain management has emerged as a crucial determinant of organizational performance in the contemporary dynamic corporate environment. The incorporation of nascent technology, such as machine learning and blockchain, is revolutionizing how enterprises manage their supply chain operations. By examining extensive datasets, machine learning algorithms can predict future demand, optimize inventory levels, and improve the planning of routes. By discerning regularities and deviations within datasets, these algorithms facilitate enterprises in making well-informed choices and managing potential hazards. Additionally, the utilization of machine learning facilitates the automation of monotonous jobs, hence mitigating the occurrence of human fallibility and augmenting the overall efficacy of supply chain operations. The utilization of blockchain technology, renowned for its decentralized and unalterable ledger system, effectively tackles several critical issues encountered in the realm of supply chain management.

Analysis of IOT Driven Accessibility in WSN

Authors:Aman Gautam, Professor Amit Thakur

Abstract: Information may be accessed from a distance thanks to computer networks. Wireless or wired networks are also possible. Due to recent developments in wireless infrastructure, wireless sensor networks (WSNs) were developed. Activities or events occurring in the environment are monitored, recorded, and managed by WSN. Through a variety of routing techniques, data relaying is done in these systems. The fourth industrial revolution, or Industry 4.0, is defined as the integration of complex physical automation systems made up of machinery and devices connected by sensors and managed by software. This is done to boost the efficiency and reliability of operations. Industry 4.0 is viewed as a possibility because of industrial IoT, the concept of leveraging IoT technology in manufacturing. Delivering, in an industrial setting, a means of connecting engines, power grids, and sensors to the cloud. In this essay, we’ll try to comprehend how the Internet of Things (IoT) works in wireless sensor networks and how it might be used in various situations.

Conceptual Differential Study of IOT and AI Based Computing Disease Detection Technique

Authors:Archishman Dwivedi, Professor Amit Thakur

Abstract: The emergence of different computing methods such as cloud-, fog-, and edge-based Internet of Things (IoT) systems has provided the opportunity to develop intelligent systems for disease detection. Compared to other machine learning models, deep learning models have gained more attention from the research community, as they have shown better results with a large volume of data compared to shallow learning. However, no comprehensive survey has been conducted on integrated IoT- and computing-based systems that deploy deep learning for disease detection. This study evaluated different machine learning and deep learning algorithms and their hybrid and optimized algorithms for IoT-based disease detection, using the most recent papers on IoT-based disease detection systems that include computing approaches, such as cloud, edge, and fog. Their analysis focused on an IoT deep learning architecture suitable for disease detection. It also recognizes the different factors that require the attention of researchers to develop better IoT disease detection systems. This study can be helpful to researchers interested in developing better IoT-based disease detection and prediction systems based on deep learning using hybrid algorithms.

Accent And Passion Identification Using Large Language Models For Speech Recognition

Authors: Alim Shaikh, Dr.Santosh Gaikwad, Dr. A. A. Khan, Dr. R. S. Deshpande

Abstract: Speech-based interaction with large lan- guage models (LLMs) is revolutionizing human-computer communication by enabling natural, voice-driven inter- faces. This study explores methods to prompt LLMs through automatic speech recognition (ASR) while ad- dressing challenges such as transcription errors, noise interference, latency, and prompt optimization. The proposed framework integrates ASR with LLMs using noise reduction, structured prompt engineering, and contextual adaptation. Experimental evaluations using models like OpenAI Whisper and GPT-4 demonstrate improvements in performance metrics such as Word Error Rate (WER) and response latency. Applications span healthcare, accessibility, and customer support, and future work will focus on expanding multimodal capabilities and enhancing ethical and energy efficiency aspects.

DOI: http://doi.org/

Digital Log Website For Biotechnology Lab

Authors: R.Aswathi, Dr.Karthikeyan S, K.Mehar Banu, Dr.Manimegalai R M.

Abstract: The platform’s intuitive user interface is designed for ease of use by This paper presents the design and development of a Digital Log Website tailored for biotechnology laboratories, aimed at enhancing the accuracy, efficiency, and compliance of scientific data documentation. In many research and clinical environments, traditional paper-based lab notebooks remain the norm, despite being prone to a variety of issues including data loss, transcription errors, lack of standardization, and limited accessibility across teams. These limitations pose significant challenges for reproducibility, collaboration, and regulatory compliance. The proposed digital log system offers a centralized, web-based platform that addresses these challenges by enabling real-time data entry, seamless integration with laboratory instruments, and streamlined communication among team members. Built using modern cloud technologies, the system supports scalability, remote access, and automated backups, ensuring data integrity and availability. Key features include secure user authentication, role-based access control, version tracking, and comprehensive audit trails to meet regulatory standards such as FDA 21 CFR Part 11 and GLP requirements. Students and lab technicians, minimizing training time while maximizing productivity. By transitioning from paper to digital documentation, laboratories can significantly improve data about instrument , reduce data loss risks, and enhance overall record quality and compliance readiness.

DOI: http://doi.org/

 

 

Impact Of Deforestation On Biodiversity In The Northeastern States Of India

Authors: Assistant Professor Dr. Ritu Jain, Himanshu Kasaudhan

Abstract: The Northeastern region of India, comprising the states of Arunachal Pradesh, Assam, Manipur, Meghalaya, Mizoram, Nagaland, Sikkim, and Tripura, represents a critical ecological zone within the Indo-Burma biodiversity hotspot. This area is home to a vast range of endemic and threatened species and features one of the highest levels of biological diversity in India. However, rapid deforestation caused by anthropogenic pressures—such as shifting cultivation (jhum), illegal logging, infrastructure expansion, and population growth—has led to severe ecological degradation. This chapter explores how Remote Sensing (RS) and Geographic Information Systems (GIS) have been employed to monitor forest cover changes and assess their impact on biodiversity. Through the use of satellite imagery, spatial analysis, biodiversity indices, and ecological modeling, this study highlights the extent, patterns, and consequences of deforestation on flora and fauna. The chapter concludes by offering conservation strategies and policy recommendations grounded in geospatial data and ecological science.

 

 

 

Microfluidic Devices for Low-Cost Diagnostics in Resource-Limited Settings

Authors: Pallavi Srivastava

Abstract: In low-resource environments, diagnostic tools must prioritize affordability while also delivering accuracy, reliability, and durability suited to the unique challenges of the developing world. In recent years, global health diagnostics using minimally instrumented, microfluidic platforms with low-cost disposable components have gained momentum, driven in part by funding from organizations like the Bill & Melinda Gates Foundation and the National Institutes of Health. This surge in interest has resulted in a variety of promising prototype devices, many of which are undergoing advanced development or clinical testing. These include systems capable of multiplexed PCR assays targeting enteric, febrile, and reproductive tract infections, as well as immunoassays for conditions like malaria, HIV, and sexually transmitted infections. More recent innovations feature fully disposable diagnostics that operate without instruments, utilizing isothermal nucleic acid amplification techniques. Despite these advancements, scalable and truly low-cost manufacturing methods remain a major hurdle in creating affordable diagnostic solutions at volume. This overview highlights current platform development efforts, includes original research conducted at PATH, and emphasizes the need for continued action and innovation in this field.

 

 

 

Urban Sprawl In Lucknow And Its Impact

Authors: Assistant Professor Dr. Ritu Jain, Kajal Pandey

Abstract: Urban sprawl, defined as the haphazard expansion of city boundaries into rural and peri-urban lands, is a defining characteristic of contemporary urban growth in India. As a prominent Tier-2 city and capital of Uttar Pradesh, Lucknow has witnessed accelerated sprawl patterns over the past three decades. This paper investigates the extent, causes, and implications of this urban expansion using remote sensing data, GIS techniques, demographic trends, and field-based insights. With a focus on infrastructure strain, socio-economic disparities, environmental degradation, and spatial policy inefficiencies, this research identifies key trends, challenges, and solutions. Recommendations are proposed for integrated planning, sustainable growth, and data-driven governance.

 

 

Impact Assessment And Response Of Melting Glacier Of Himalayan Region

Authors: Assistant Professor DR. Ritu Jain, Aditya Pratap Saroj

Abstract: The Himalayan glaciers, also referred to as the “Third Pole,” play a vital role in the ecological balance of the region and supply water to more than a billion Asians, sustaining agriculture, drinking water, and energy. Climate change has resulted in rapid glacial retreat, which has resulted in decreased water resources, enhanced disaster risks, and ecosystem threats. This chapter examines the effect of glacial melt, employing remote sensing, satellite imagery, and climate models to evaluate the scale of retreat and its consequences, including water scarcity and ecosystem disruption. It discusses adaptive measures, such as enhanced water storage, flood early warning systems, and sustainable agriculture to reduce the impacts of declining glacial melt. Community-based techniques, combining indigenous knowledge, are also mentioned as important in controlling water resources. Lastly, the chapter discusses the necessity of cross-border policy and cooperation to develop solutions for the water crisis to ensure the sustainable management of the region’s glaciers and water.

 

 

Impact Of Cloud Computing Transforming Industries And Business Processes

Authors: Vishal Garad, Dr. Quazi khabeer, Dr. A. A. Khan, Dr. R. S. Deshpande

 

 

Abstract: Cloud computing has transformed the business and industry operations by providing scalable, flexible, and cost- efficient data storage, processing, and access solutions.The paper discusses the revolutionary effects of cloud computing on business processes and its benefits, challenges, and future trends. It identifies the contributions of cloud technologies to enhanced operational efficiency, innovation, and sustainable practices.Index Terms—Cloud Computing, Scalability, Operational Efficiency, Security, Cost-Effectiveness, Future Trends.

DOI: http://doi.org/

 

 

AI Applications in Enhancing Patient Adherence to Medication Regimens

Authors: Dr. Harika Prasad

Abstract: AI technologies are transforming medication adherence by enabling personalized, real-time interventions that address the complex factors influencing patients’ ability to follow prescribed regimens. By leveraging machine learning, predictive modeling, natural language processing, and data integration from diverse sources—including electronic health records, wearable devices, and patient-reported outcomes—AI systems can monitor adherence patterns, predict patients at risk of non-compliance, and deliver tailored reminders and support through virtual health coaches and chatbots. These innovations improve patient engagement, facilitate early intervention, and empower healthcare providers with actionable insights, ultimately enhancing treatment outcomes and reducing healthcare costs. However, successful implementation requires careful consideration of ethical, privacy, and regulatory challenges to ensure fairness, transparency, and patient trust. As AI continues to evolve, its integration into medication adherence management promises to revolutionize personalized care, offering scalable solutions that improve quality of life for millions worldwide.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.127

 

 

AI Applications in Streamlining Clinical Trial Participant Recruitment

Authors: Dr. Ashwin Kumar

Abstract: Artificial Intelligence (AI) is revolutionizing clinical trial participant recruitment by automating and optimizing key processes such as eligibility screening, patient matching, and engagement. Traditional recruitment methods face challenges including time-consuming manual efforts, low enrollment rates, and demographic disparities, which delay trials and increase costs. AI technologies—such as machine learning, natural language processing, predictive analytics, and chatbots—enable efficient analysis of complex patient data from electronic health records and other sources, improving recruitment speed, accuracy, and inclusivity. While AI-driven recruitment offers significant benefits like reduced timelines, enhanced patient retention, and cost savings, it also raises ethical and regulatory concerns including data privacy, algorithmic bias, and transparency. Future developments integrating real-world data, explainable AI, and digital health platforms promise to further advance recruitment practices. This article reviews the current applications, benefits, challenges, and future directions of AI in clinical trial participant recruitment, highlighting its potential to transform clinical research and accelerate medical innovation.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.128

 

 

AI in Enhancing Diagnostic Accuracy in Dermatology

Authors: Dr. Uma Devi T

Abstract: Accurate diagnosis in dermatology is essential for effective treatment and improved patient outcomes, yet it remains challenging due to the complexity and variability of skin conditions. Artificial Intelligence (AI), especially machine learning and deep learning techniques, has emerged as a promising tool to enhance diagnostic accuracy by analyzing vast and diverse dermatologic image datasets. AI-powered diagnostic systems can detect subtle features in skin lesions, enabling early identification of malignant and benign conditions with accuracy comparable to expert dermatologists. These technologies offer benefits such as reducing diagnostic variability, expanding access through teledermatology, and supporting clinicians in decision-making. However, challenges including data bias, model interpretability, ethical concerns, and integration into clinical workflows must be addressed for effective adoption. Future innovations involving multimodal data integration, personalized diagnostics, and explainable AI promise to further advance dermatologic care. Overall, AI has the potential to revolutionize dermatology by improving diagnostic precision, accessibility, and patient outcomes.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.129

 

 

AI In Monitoring And Managing Autoimmune Diseases

Authors: Dr. Vignesh Sai

Abstract: Autoimmune diseases are complex, chronic conditions characterized by immune system dysregulation and unpredictable disease progression, posing significant challenges for early diagnosis, continuous monitoring, and personalized treatment. Traditional clinical approaches often fall short in managing these multifaceted disorders effectively. This article explores the transformative role of artificial intelligence (AI) in addressing these challenges by leveraging advanced machine learning, natural language processing, and wearable technologies to improve early detection, real-time disease activity monitoring, and tailored therapeutic strategies. We discuss current applications, data and ethical considerations, and future innovations such as multimodal AI systems and federated learning, emphasizing the potential of AI to enhance patient outcomes and revolutionize autoimmune disease care. Overcoming hurdles related to data quality, privacy, and bias remains essential to fully realizing AI’s benefits. This synthesis highlights AI’s promise in enabling a more precise, proactive, and patient-centered approach to autoimmune disease management.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.130

 

 

AI Integration in Personalized Physical Therapy Programs

Authors: Vinay R. Gowda

Abstract: Artificial Intelligence (AI) is revolutionizing personalized physical therapy by enabling objective assessment, tailored treatment planning, real-time monitoring, and remote rehabilitation. By integrating data from wearable sensors, computer vision, and electronic health records, AI supports individualized care that improves patient outcomes and engagement. This article reviews AI’s multifaceted role in physical therapy, highlighting current applications in assessment, therapy customization, and tele-rehabilitation. It also addresses challenges related to data privacy, ethical considerations, and clinical integration. Emerging trends such as augmented reality, predictive analytics, and digital twin technology are discussed, outlining the future direction of AI-driven rehabilitation. The integration of AI promises to transform physical therapy from a generalized approach to a dynamic, personalized, and proactive discipline, ultimately enhancing recovery and quality of life for diverse patient populations.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.131

 

 

IOT Based Brushless DC Motor Speed Control Using Arduino

Authors: Dr. Rajul Misra, Mr. Saurabh Saxena, Vivek Saini, Yeshvendra Singh, Ashish Dwivedi

 

 

Abstract: This paper presents an IoT-based BLDC motor speed control and monitoring system using Arduino Uno, ESP32 WROOM, and Blynk IoT. The system allows dual control of motor speed—via a potentiometer and remotely through the Blynk app. An IR sensor module is used to measure RPM, displaying real-time speed on an LCD (16×2). The motor is powered by an 11.1V (3S) lithium phosphate battery and controlled via a Simonk 30A ESC. This setup enables precise speed regulation with IoT-based monitoring, improving automation and efficiency.

DOI: http://doi.org/

 

 

IOT Based Brushless DC Motor Speed Control Using Arduino

Authors: Dr. Rajul Misra, Mr. Saurabh Saxena, Vivek Saini, Yeshvendra Singh, Ashish Dwivedi

 

 

Abstract: This paper presents an IoT-based BLDC motor speed control and monitoring system using Arduino Uno, ESP32 WROOM, and Blynk IoT. The system allows dual control of motor speed—via a potentiometer and remotely through the Blynk app. An IR sensor module is used to measure RPM, displaying real-time speed on an LCD (16×2). The motor is powered by an 11.1V (3S) lithium phosphate battery and controlled via a Simonk 30A ESC. This setup enables precise speed regulation with IoT-based monitoring, improving automation and efficiency.

DOI: http://doi.org/

 

 

ML-Driven Health Prediction Framework For Early Diagnosis And Patient Support

Authors: Dr. Mrunal Pathak

 

 

Abstract: – The Predictive Smart Healthcare System, leveraging machine learning for early detection, individualized treatment plans, and efficient healthcare delivery by utilizing machine learning for early detection. The system evaluates patient data to anticipate health problems using algorithms like SVM and Random Forest, enabling rapid detection and individualized treatment. By automating processes like symptom analysis, appointment scheduling, and data interpretation, it reduces the workload of healthcare professionals. Using CNN and NLP, the Medical Chatbot offers immediate medical advice, improving patient engagement. The Appointment Booking module ensures effective communication by streamlining procedures using SMTP email confirmations. Intelligent, patient-centred healthcare has advanced significantly with the combination of automation and machine learning.

DOI: http://doi.org/

AI-Powered Nutritional Genomics: Tailoring Diets Based On Genetic Profiles

Authors: Ramya Reddy

Abstract: AI-powered nutritional genomics represents a groundbreaking convergence of genetic science and artificial intelligence, aiming to create personalized dietary recommendations based on individual genetic profiles. By analyzing genetic variations, particularly single nucleotide polymorphisms (SNPs), and integrating data from wearable devices, microbiome analyses, and lifestyle trackers, AI can interpret complex biological patterns to optimize nutrition and health outcomes. This approach offers significant benefits, including enhanced disease prevention, improved diet adherence, and personalized health optimization. However, it also raises challenges such as data privacy, algorithmic bias, and accessibility. As the field advances, it holds the potential to revolutionize healthcare by shifting from generalized dietary guidelines to truly personalized nutrition strategies tailored to each person’s unique biology.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.132

AI-Assisted Mental Health Interventions Through Chatbot Therapies

Authors: Dr. Asha Hegde

Abstract: As mental health disorders continue to rise globally, access to timely, affordable, and stigma-free care remains a significant challenge. AI-assisted chatbot therapies have emerged as innovative tools that leverage artificial intelligence, natural language processing, and psychological frameworks such as cognitive behavioral therapy (CBT) to deliver mental health support through interactive conversations. These chatbots offer 24/7 accessibility, anonymity, and scalable interventions, making them especially valuable in underserved and remote areas. This article explores the evolution, benefits, and clinical effectiveness of chatbot therapies, highlighting their ability to personalize care, monitor emotional states, and promote user engagement. It also addresses critical ethical considerations, privacy concerns, and technical limitations while examining future directions including integration with wearable technology, hybrid AI-human models, and regulatory standardization. As part of a broader digital mental health ecosystem, AI-powered chatbots present a promising complement—not replacement—to traditional therapy, offering accessible and empathetic support that can help close the global mental health treatment gap.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.133

AI-Based Decision Support Systems For Emergency Medical Services Triage

Authors: Dr. Koteswara Rao M.

Abstract: AI-based decision support systems (DSS) have the potential to significantly enhance Emergency Medical Services (EMS) triage by providing rapid, accurate, and consistent patient prioritization in high-pressure situations. Leveraging advanced machine learning, natural language processing, and real-time data integration, these systems assist EMS personnel in making informed decisions, reducing cognitive burden, and optimizing resource allocation. Despite challenges such as data quality, interoperability, user acceptance, and ethical concerns including privacy and algorithmic bias, AI-driven triage tools have demonstrated improved accuracy and efficiency in real-world applications. Future advancements promise greater personalization, transparency, and integration with telemedicine and wearable technologies, reshaping emergency care delivery. Multidisciplinary collaboration and ethical governance are essential to realizing AI’s full potential in EMS triage, ultimately improving patient outcomes and emergency response effectiveness globally.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.134

Consumer Buying Behavior In Europe: Post-Brexit And The Ukraine Russia War

Authors: Siddharth Jha

Abstract: This study explores the evolving consumer buying behavior in Europe following the significant geopolitical and economic shifts triggered by Brexit and the Ukraine-Russia war. The analysis highlights the impact of rising inflation, trade disruptions, and shifting consumer sentiments across the UK and the Eurozone. Key findings include a marked reduction in spending on non-essential goods, a surge in demand for discount retailers, and increased consumer activism in Southeast and Eastern Europe. Additionally, the study examines the persistent influence of sustainability concerns despite economic pressures. The paper concludes with future trends and strategic recommendations for businesses and policymakers to navigate this complex landscape effectively.

Optimized 2d Fir Filtering Architecture with Approximate Multiplier for Real-Time Deepfake Image Processing Applicatons

Authors: A.BABISHA

Abstract: With the rapid penetration of the Internet into every part of our daily life, it is agreed that it will be an important medium for future communication, perhaps even more important than the television This product is a self-contained product made to facilitate the users with the facility to detect which video amongst the 2 is a real or fake one. This can be very helpful the society to control and reduce blackmailing and sharing of obscene content. We extract the feature points from the images in the training dataset using FAST and get the feature point descriptors using BRIEF. Then using DLIB face detector to detect face region and regions inside the face. We group the feature points based on the region that they are falling in. Then the feature point descriptors are aggregated to train the random forest classifier.

DOI: http://doi.org/

IoT Based Automatic Damaged Street Light Fault Detection And Monitoring System

Authors: Pratik R. Taye, Satyam M. Kharate, Saket D. Aadhav, Prof. Suraj D. Kulkarni

Abstract: The Automatic Street Light Fault Detection and Monitoring System Using IoT is an advanced approach for maximizing efficiency in the management of street lights and energy consumption. With the help of the Internet of Things (IoT), the proposed system allows for automatic fault detection, monitoring, and management of street lights infrastructure. An array of intelligent sensors are utilized in the proposed system to identify and communicate faults in wiring or burnt out lamps to the control unit using wireless means. This modern technique reduces the need for manual inspections, helps lower the downtime for repairs, and guarantees that street lights remain on. More so, the system has advanced reporting capabilities that automate maintenance schedule reports and energy usage reports. Automation of the report generation further increases efficiency in fault detection and subsequently lowers operational costs while enhancing safety in public spaces.

Optimized 2d Fir Filtering Architecture with Approximate Multiplier for Real-Time Deepfake Image Processing Applicatons

Authors: A.BABISHA

Abstract: With the rapid penetration of the Internet into every part of our daily life, it is agreed that it will be an important medium for future communication, perhaps even more important than the television This product is a self-contained product made to facilitate the users with the facility to detect which video amongst the 2 is a real or fake one. This can be very helpful the society to control and reduce blackmailing and sharing of obscene content. We extract the feature points from the images in the training dataset using FAST and get the feature point descriptors using BRIEF. Then using DLIB face detector to detect face region and regions inside the face. We group the feature points based on the region that they are falling in. Then the feature point descriptors are aggregated to train the random forest classifier.

IoT-Based Smart Cities and Context-Aware Edge-Based AI Models for Wireless Sensor Networks

Authors: Assistant Professor S.Janani

Abstract: Artificial Intelligence (AI) and the Internet of Things (IoT) are Innovatively integrated to advance smart cities. Urban infrastructure depends on Wireless Sensor Networks (WSNs) to gather and transmit data, enabling edge-based AI models to make context-aware decisions. This literature review examines the evolution of city models, IoT technologies of role, and the application of edge computing and AI techniques to enhance context-aware systems. Additionally, it incorporates insights into AI implementation across various domains, including healthcare, education, mobility, governance, and environmental sustainability. We discuss research potential, technological advancements, and significant concerns like energy efficiency, scalability, privacy, and security. Diagrams illustrating city architecture and conceptual AI frameworks are included to enhance understanding.

IoT-Based Smart Helmet For Construction Worker Safety Using Raspberry Pi

Authors: Prof.Said Shubhangi K., Prof . Auti Mayuri A., Miss.Gund Sakshi Dattatray, Miss.Jadhav Shreya Shivaji, Miss.Satware Vidya Laxman

Abstract: The increasing demand for safety and efficiency on construction sites has prompted the need for innovative technological solutions aimed at protecting workers in dynamic and hazardous environments. This research introduces a novel IoT-based smart helmet designed specifically for construction workers. The proposed helmet is embedded with intelligent sensors and communication modules that enable real-time monitoring of the worker’s location, ambient environmental conditions, and task status. The helmet aims to bridge the gap between passive protective gear and active monitoring systems, thereby enhancing situational awareness and minimizing response times during emergencies. By incorporating modules such as a smoke sensor, GPS, proximity detection, emergency buttons, and wireless data transmission, the helmet transforms into an advanced safety monitoring tool. It is capable of automatically switching to “Work Mode” when worn and relays data continuously to a cloud-based server via ThinkSpeak. In the event of a detected emergency—such as exposure to smoke or the press of an emergency button—instant email alerts are sent to supervisors with the worker’s exact location. This real- time data acquisition and communication significantly improves site supervision, promotes worker accountability, and contributes to a safer construction environment.

Advanced DSTATCOM Control For Grid Code-Compliant Voltage Stability In Renewable-Penetrated Networks: Review

Authors: Nikhil Kumar Khemaria, Vinay Kumar Pathak

Abstract: The paper study exhibits the force quality issue because of establishment of wind turbine with the network. In this proposed plan appropriation static compensator (DSTATCOM) is associated with a battery vitality stockpiling framework (BESS) to relieve the force quality issues. The battery vitality stockpiling is incorporated to support the genuine force source under fluctuating wind power. The DSTATCOM control plan for the network associated wind vitality era framework for force quality change is recreated utilizing MATLAB/SIMULINK in force framework piece set. At last the proposed plan is connected for both adjusted and uneven nonlinear burdens.

DOI: http://doi.org/

GENDER DISCRIMINATION AT WORKPLACE

Authors: NAZISH KHAN, Ms. Shruti Rawat

Abstract: Gender discrimination in the workplace persists despite considerable strides toward gender equality in many societies. At the heart of this issue lie entrenched societal norms and biases that shape organizational structures and decision-making processes. One of the most insidious aspects of gender discrimination is its often subtle and unconscious nature, making it challenging to identify and address. Research has shown that women continue to face disproportionate barriers to career advancement, including biases in hiring, promotion, and compensation practices. Moreover, women are more likely to encounter microaggressions, harassment, and stereotyping in the workplace, creating hostile environments that undermine their professional growth and well-being. The impacts of gender discrimination extend far beyond individual experiences, affecting organizational culture and performance. When talented individuals are overlooked or marginalized based on gender, companies miss out on valuable perspectives and contributions. This not only stifles innovation but also perpetuates inequalities within the workforce. Additionally, gender discrimination can erode employee morale, leading to decreased productivity, higher turnover rates, and reputational damage for organizations. To effectively address gender discrimination, it is essential to recognize and challenge the underlying biases and systemic inequalities that perpetuate it. This requires a comprehensive approach that includes policy interventions, cultural shifts, and individual awareness. Organizations must prioritize diversity and inclusion initiatives, implementing strategies to mitigate bias in recruitment, promotion, and performance evaluation processes. Training programs that raise awareness of unconscious bias and foster inclusive behaviors can help create more equitable work environments.

Hybrid Machine Learning Models For Fault Prediction And Repair In Electrical Power Distribution Systems

Authors: Dr. RajaGopal Kayapati

Abstract: Electrical power distribution systems are critical infrastructures that require robust fault detection and repair mechanisms to ensure uninterrupted service. Traditional fault detection systems often struggle with accuracy and real-time adaptability. This paper proposes a hybrid machine learning (ML) framework that integrates ensemble learning and deep learning models to predict faults and recommend repair actions in power distribution systems. The proposed system combines the strengths of decision trees, random forests, and long short-term memory (LSTM) networks to improve accuracy, precision, and response time. Experimental results on benchmark electrical datasets demonstrate a significant performance improvement over conventional models. This hybrid approach provides utility companies with a scalable, intelligent fault management solution, thereby reducing downtime and maintenance costs.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.135

Integrating Weather Data Analytics Into IoT-Based Smart Irrigation Systems For Sustainable Agriculture

Authors: Khadri S S

Abstract: The flourish of Internet of Things (IoT) is leveraging the reform of today’s agriculture, including the development of new intelligent irrigation systems for the management of water resources. The integration of analytics-informed weather information in IoT-enabled irrigation systems enhancing accuracy, sustainability, and farm-level efficiency is examined in the current work. Traditional irrigation methods may rely on rigid schedules or manual manipulation that result in waste, lack of uniformity in the irrigation area, or in an inability to obtain the desired crop yield at the correct time of the year, particularly in areas with variable precipitation.
To overcome these limitations ,the system proposed here leverages a comprehensive network of IoT devices—including soil moisture sensors, temperature and humidity monitors, rain gauges, and weather stations—to gather live environmental data. This information is transmitted using communication protocols such as LoRaWAN, Wi-Fi, or NB-IoT to a centralized cloud environment. There, predictive models and machine learning algorithms analyze weather indicators like rainfall predictions and evapotranspiration rates, cross-referencing them with soil data to inform irrigation needs in real time. Field evaluations revealed that the smart system cut water usage by 30–40% compared to traditional practices and boosted crop yields by 15–20% by maintaining optimal soil hydration. A user-friendly interface also gives farmers real-time oversight and the flexibility to intervene manually when needed. By combining IoT connectivity, multi-source data integration, and adaptive automation, the system helps farmers navigate extreme weather events such as droughts and sudden rainfall. Its affordable components and scalable design make it suitable for farms of all sizes. Ultimately, this research highlights how IoT-powered weather analytics can drive more sustainable water use in agriculture, lower operational costs, and contribute meaningfully to global food security. It calls for greater adoption of smart irrigation systems that align agricultural productivity with environmental stewardship.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.137

Secure Cross Socket Based Technique by Grouping of Machine Learning

Authors: Assistant Professor Sujata, Professor Dr. Brij Mohan Goel

Abstract: The proposed strategy should increase safety without sacrificing performance. It is being evaluated to determine whether any of the published research has any restrictions in terms of cloud-based software security issues. By using encrypted hybrid technique we can enhance the socket-based performance mechanisms like packet loss, latency rate, probability of error etc. The model suggested in the research is being compared with existing technologies in terms of performance, safety and dependability. This study is meant to investigate the proposed initiative’s need, inspiration, and challenges. This research will examine how the intended work will be carried out in the actual world after examining the problem description. The Endeavour’s algorithm and mechanism would describe the tools and procedures used in study. In this paper, the results of the study have been presented by the proposed model in such a way that it can perform better than previous studies. There are a variety of approaches you may take to this research, which we’ll go over in more depth below. Exploratory studies may yield out new topics. Providing answers to a problem through doing research. Research work considered machine learning approach in order to classify different by of attacks in order to improve the security of hybrid socket based approach.

The Role Of Artificial Intelligence In Credit Card Fraud Detection

Authors: Ramya K. Cherukuvada, Raghu V. Kaspa

Abstract: Credit card fraud poses a substantial threat to the financial services industry, with billions of dollars lost annually across the globe. Traditional rule-based fraud detection systems are increasingly proving to be inadequate against sophisticated, constantly evolving fraud techniques. The dynamic nature of fraud demands equally dynamic countermeasures, and Artificial Intelligence (AI) has emerged as a highly effective solution. AI-powered fraud detection systems can learn from historical transaction data, recognize patterns, and adapt in real-time to detect potentially fraudulent activities. This paper provides an in-depth exploration of how AI is being leveraged in credit card fraud detection, the machine learning models used, real-world applications, challenges, and the future of fraud prevention technologies.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.139

Evolution Of Credit Card Payments And Future Advancements

Authors: Ramya K Cherukuvada, Raghu V Kaspa

Abstract: Credit cards have become a cornerstone of modern financial systems, enabling convenient and secure transactions for consumers and businesses alike. From their humble origins as store-specific charge cards to today’s multifaceted digital financial instruments, credit cards have undergone significant technological and regulatory transformation. This research paper explores the historical trajectory of credit card development, evaluates current technological and regulatory frameworks, and examines forthcoming innovations such as artificial intelligence, blockchain, biometric authentication, and sustainability practices. By leveraging a combination of historical analysis and forward-looking insights, this study aims to provide a comprehensive understanding of how credit card payments have evolved and what future advancements may entail.

The Future Of Java Programing Language: Opportunities, Challenges, And Ethical Implications

Authors: Suraj Choudhary, Mr. Ravi Kumar, Dr. Rajendra Khatana

Abstract: Java is a high-level, object-oriented programming language that has become a cornerstone of modern software development since its inception in the mid-1990s. Designed by Sun Microsystems with the principle of “Write Once, Run Anywhere” (WORA), Java enables developers to create applications that can run on any device equipped with a Java Virtual Machine (JVM), ensuring portability across diverse platforms. Its syntax, influenced by C and C++, promotes code readability and maintainability, making it accessible to a wide range of developers. Java’s robust ecosystem includes a rich set of libraries and frameworks, such as Spring, Hibernate, and Java Server Faces, which facilitate the development of web, mobile, and enterprise applications. The language is particularly renowned for its strong emphasis on security, making it a preferred choice for applications that handle sensitive data, such as financial systems and online services. As technology evolves, Java continues to adapt, embracing modern paradigms such as cloud computing and microservices architectures. Its extensive community support fosters continuous innovation, ensuring that Java remains relevant in an ever-changing landscape. This abstract provides an overview of Java’s key features, applications, and its enduring significance in the field of programming, highlighting its role as a versatile and powerful tool for developers worldwide.

Unigin: A Centralized Platform for Real-Time Esports Tournament Tracking, Live Scores, and Streaming Integration

Authors: Assistant Professor Yashanjali Sisodia, Aditya Bheke, Harshal Bhogawade, Malhar Bhoi, Yash Bambale

Abstract: Unigin provides real-time esports tournament updates, ensuring players, organizers, and fans stay informed with live scores, match schedules, and statistics. The platform enhances engagement through instant notifications and seamless data integration across multiple games…

Super Sonic Glasses

Authors: Deepti Varshney, Ahana Tola, Nasreen Mursal, Pranita Pawar, Bhumika Patil

Abstract: The Super Sonic Glasses assist those that are hard of hearing by transcribing spoken language into text that can be displayed on the device’s screen in real time. This project aims to bridge the gap between those who communicate using visual sign language due to hearing difficulty and other users through better ways of interaction. The system processes spoken words into intelligible text utilizing sophisticated speech recognition methods, which is instantly viewed on a simple, cool design embedded within goggles’ frame. The Sonic Support Goggle integrates sophisticated speech processing and wearable display devices to enhance accessibility and facilitate seamless communication in myriad social and professional settings.

SkyLens- Weather App

Authors: Assistant Professor Sangeeta Mohapatra, Shreyash Khaladkar, Subodh Marathe, Mayur Chaudhari, Shravani Nanaware, Avinash Mule

Abstract: SkyLens is a perfect companion for checking the weather before heading out. By leveraging artificial intelligence and machine learning, it delivers highly accurate forecasts, helping users make informed decisions about outdoor plans, travel, and safety during extreme weather conditions.The app’s real-time notification system enhances the user experience by providing instant alerts for weather changes. SkyLens offers real-time weather updates specific to your location, delivering precise forecasts for the current day and the days ahead. Its intuitive interface presents essential information such as temperature, humidity, wind speed, and rainfall, along with severe weather warnings, personalized notifications, and sustainability tips.

ApplincesHub

Authors: Professor Swati Bagade, Shubham Pandhare, Piyush Sakhare, Nidhish Patil, Nikhil Soni

Abstract: The AppliancesHUB project developed an Android mobile application directed towards disrupting the appliance renting market. It quickly connects customers with rental stores around them for fast, cheap, and safe renting. The app uses location services, user accounts, and instant advertisement of the appliances to make it less complicated to access the rental services and to increase business transactions. Through this platform, consumers can rent appliances or furniture with ease, and local rental companies are able to gain more clients and more effectively manage the rentals. The application is developed using Google Maps API for location based listings, Flask-SQLAlchemy for backend services, and Android Studio (Java/Kotlin) for application development. AppliancesHUB from the study serves the purpose of creating a seamless renting experience while having a lower cost, safer, and environmentally friendly alternative to traditional ownership.

Augmented Reality : Models For Architectural Progression

Authors: Assistant Professor Yashanjali Sisodia, Amol Hipparkar, Shivam Singh

Abstract: The summary shows that user features such as preferring to use the interface can lead to effective use of the interface. Research also points out that there is a relationship between learner preferences and creativity. Vark Learning Styles Inventory uses this study to assess students’ learning styles and examines how this learning preferences affect the use of augmented reality (AR) and virtual reality (VR) in creative design

Ruthless Drop – Menstrual Cycle Tracking Application

Authors: Assistant Professor Manisha Wasnik, Parth Pawar, Sarthak Divate, Prajwal Salunkhe, Shivendra Kale

Abstract: Menstruation plays an important role in a woman’s life and mostly on the human race all over the world .Menstruation cannot be avoided till menopause so some way should be there to avoid the painful effects of menstruation , although the pain caused also cannot be avoided but can be aided with use of sanitary pads .But use of sanitary pad also depends on when it is used , it cannot be placed every day the individual should know when she has to apply it that is before the menstruation occurs and not after the menstruation puts stain on individuals clothes . Here the role of menstruation cycle tracking application comes into action where tracking menstruation cycle would assist in approximately know the days when to apply the sanitary pad. There hasn’t been much research done on the most important topic, so it’s really difficult to judge if the menstruation cycle tracking apps have any negative insights on the individual’s health. most of the women, manually mark the dates on the calendar which is a good real time method but the kind of accuracy and precision which is achieved on the application cannot be achieved on a physical calendar

Domain Specific Opportunities

Authors: Assistant Professor Sangeeta Mohapatra, Mayur Madkholkar, Kiran Londhe, Virag Khade, Priya Manjare, Anushka Jachak

Abstract: This paper explores the development of a mobile and web application designed to centralize notifications and updates about hackathons, tech fests, and other technology-related opportunities for students. The goal is to address challenges students face in discovering relevant events and staying updated on deadlines and registration dates by aggregating data from multiple sources into one platform. By integrating information from various organizers, the solution streamlines event discovery and enhances convenience. Using a mixed-methods approach, including technical analysis and user experience testing, the study finds that the platform improves event discovery efficiency, user satisfaction, and connects students with specialized career opportunities in fields like AI, cybersecurity, and blockchain.

Virtual Mouse Using Hand Gesture

Authors: Professor Swati Bagade, Dr. Anamika Jain, Sakshi Patil, Shivani Shivshette, Lavanya Sharma, Disha Shirsat

Abstract: The concept of virtual mouse using hand gesture is touch free input device . It replace traditional mouse. The proposed interface aims to create a more intuitive and seamless interaction between users and their devices by leveraging the natural movements of the hand. This innovative approach has the potential to enhance user experience and interaction efficiency in various applications, including virtual environments and gesture- based control systems. The paper explores the technical aspects, challenges, and future possibilities for implementing the hand mouse interface with computer system and enhance human-computer interference.

Supervised Vs Unsupervised Learning: A Comparative Study In Fraud Detection

Authors: VIjaya Sawant

Abstract: Fraud detection has become a critical area of concern across industries, with increasing volumes of online transactions and evolving cyber threats. Machine Learning (ML) models play a vital role in identifying fraudulent activities. This study explores a comparative analysis of supervised and unsupervised learning approaches in fraud detection. Supervised models, relying on labeled data, offer high accuracy, while unsupervised models excel in anomaly detection, capable of identifying previously unseen fraud patterns. This paper discusses their applications, advantages, challenges, and suggests hybrid approaches to optimize fraud detection systems.

A Context-Aware Mobile Application For Tourist Guidance: Integrating Location-Based Recommendations, Route Optimization, And Service Discovery

Authors: Assistant Professor Sangeeta Mohapatra, Kartik Biradar, Tushar Malwade, Aryan Lanke

Abstract: In today’s mobile-centric era, travelers increasingly rely on real-time, personalized information to enhance their tourism experiences. This paper presents the design and implementation of a context-aware mobile application that recommends nearby tourist attractions, optimizes visitation routes, and provides detailed information about local accommodations and dining options. Building on recent advancements in mobile computing, route optimization, and context-aware systems, our work details the system’s architecture, data acquisition methods, hybrid recommendation engine, and routing algorithms. Experimental results demonstrate improvements in route efficiency and recommendation accuracy while maintaining real-time responsiveness. The paper also discusses potential enhancements using machine learning techniques and further integration with urban data streams.

Taxi Fare Insights: Building A Taxi Price Comparison App For Smarter Rides

Authors: Assistant Professor Manisha Wasnik, Prajwal Sharma, Karan Ranpise, Purvi Garvir, Aryan Poddar

Abstract: This paper explores the conceptualization, development, and anticipated impact of an innovative integrated ride-hailing application designed to seamlessly connect with Ola, Uber and Rapido through their respective APIs. The core objective of this research is to address the inefficiencies and user dissatisfaction caused by the need to switch between multiple ride-hailing platforms to compare real-time fares and estimated arrival times. By aggregating data from Ola, Uber and Rapido within a single, unified interface, the proposed solution eliminates the hassle of time-consuming searches, thereby streamlining the ride selection process and enhancing user convenience.The study employs a comprehensive mixed-methods approach, incorporating a detailed technical analysis of API integration, system architecture design, and user experience assessments conducted through simulations and surveys. The findings demonstrate that this integrated platform significantly improves search efficiency, enhances user satisfaction, and offers broader implications for urban mobility by optimizing resource allocation within the ride-sharing industry. The significance of this research lies in its potential to revolutionize the ride-hailing ecosystem, paving the way for a more efficient, user-centric, and technology-driven transportation landscape.

Agriculture Management System: Ensuring the Quality and Safety of Agricultural Products

Authors: Assistant Professor Swati Bagade, Ajay Ugale, Umer Tukdi, Sudhanshu Tripathi, Sundaram Tiwari

Abstract: The agricultural sector plays a critical role in ensuring food security and economic stability worldwide. However, farmers often encounter significant challenges, including limited access to markets, inefficient supply chains, price exploitation by intermediaries, and a lack of real-time market data. The Agriculture Management System (AMS) is a digital solution designed to bridge the gap between farmers and buyers by offering an online platform that ensures direct sales, fair pricing, and increased efficiency. AMS integrates three core modules: Farmer, Buyer, and Administrator, each with distinct functionalities aimed at optimizing market interactions. The system provides real time market price updates, a secure transaction mechanism, and a knowledge base for product quality assurance. By leveraging technology, AMS enhances transparency, reduces operational costs, and empowers farmers, ultimately leading to a more sustainable and profitable agricultural ecosystem. This paper examines the system’s architecture, functionalities, expected impact, and future enhancements, emphasizing its potential to revolutionize agricultural trade.

AI-Powered College Review Chatbot For Student Decision-Making

Authors: Professor Swati Bagade, Aarohi Wagh, Veerashwar Kshirsagar, Shivam Ubarhande

Abstract: In today’s digital era, students face significant challenges in finding authentic and structured reviews about colleges. The existing online platforms often provide scattered, biased, or unverified information, making it difficult for prospective students to make informed decisions. This paper presents an AI-powered College Review Chatbot designed to provide instant, structured, and reliable information about various colleges based on student feedback and key institutional parameters. The chatbot leverages Natural Language Processing (NLP) to interpret user queries and retrieve relevant insights from a curated database. Additionally, sentiment analysis is employed to filter biased or misleading reviews, ensuring a balanced perspective. The chatbot serves as an interactive guide, simplifying the decision-making process for students and enhancing user engagement. Experimental results demonstrate the chatbot’s effectiveness in improving accessibility and reducing the time required to gather accurate college-related information.

An AI-Powered Smart Waste Management System For Efficient Urban Cleanliness

Authors: Asstsitant Professor Sangeeta Mohapatra, Sourav Kale, Tejaswini Katole, Vrushali Kase, Aniket Kasturi, Pratiksha Ingle

Abstract: The continuous rise of urbanization has led to an overwhelming increase in waste generation with serious consequences for the environment and humans. Most waste disposal methods are inefficient, with little accountability or participation from the community, hence we propose a Smart Waste Management System (SWMS) built on AI technologies that employs computer vision and cloud computing to track on a real-time basis, facilitating improved waste sorting and the complaint making towards upcycling. The system allows the community to upload pictures of items to be reused and are identified as categories using an artificial intelligence model through which there is a trgging of the item for appropriate action. The platform also enables conversations on tracking complaints and donations of reusable items, thereby enabling data emergence for urban waste management authorities in making decisions. This paper explains the system design and implementation and is sustainability implications.

CryptoNavigator – An Application For Tracking And Predicting Cryptocurrencies

Authors: Manisha Wasnik, Varad Landge, Sameer Mail, Shriya Watkar, Siddhesh Kamire

Abstract: — CryptoNavigator is a cryptocurrency tracking application built with Flutter, Dart, and Supabase. It fetches live market data through the CoinGecko API, providing real-time price tracking, search, favorites, and deep insights per cryptocurrency. Secure user login through email verification and profile management are some of its security features. One of the main features is price prediction to assist investors in making knowledge-based decisions. With a user-friendly UI and cross-platform support, CryptoNavigator aims to assist both new and experienced investors in tracking and predicting cryptocurrency trends.

Hostel Management System

Authors: Deepti Varshney, Prajakta Mane, Raisa Shaikh, Kais Peerzade, Sumit Dharmadhikari

Abstract: The traditional hostel management system relies on manual operations such as physical registers, handwritten records, and labor-intensive procedures. These methods pose several inefficiencies, necessitating the development of a digital Hostel Management System (HMS) to streamline and automate hostel administration. The HMS is designed as an Android application integrating real-time authentication, notifications, and secure data management. This paper explores the design, implementation, and future enhancements of the system, incorporating insights from contemporary research on hostel automation.

NAS(Network Attached Storage)

Authors: Professor Swati Bagade, Dr. Anamika Jain, Saad Shaikh, Om Salunkhe, Sourish Chatterjee, Aditya Salunkhe

Abstract: As the need for secure and effective data storage continues to grow, Network-Attached Storage (NAS) has emerged as an essential element for personal and business applications. This project aims to deploy a NAS system based on a virtual machine (VM) with OpenMediaVault (OMV) as the central storage management software. For added security, a Virtual Private Network (VPN) is incorporated, providing secure remote access. Moreover, data encryption is used to protect sensitive information from unauthorized access. This paper examines the design, implementation and security provisions of the proposed NAS system, showing its gains in terms of accessibility, scalability, and data integrity.

A Study On Generation Z’s (Gen Z’s) Reaction Towards Shrinkflation

Authors: Anjali R

Abstract: This study aims to explore and analyze the Gen Z’s reaction towards Shrinkflation and their affect on purchasing behavior of Gen Z consumers, a phenomenon where product sizes decrease while the price remains the same. This has become increasingly prevalent in today’s economy. A sample of 100 respondents from diverse age groups, ranging from 18 years to26 and above, was surveyed using a structured questionnaire. . The data were analyzed using statistical and graphical tools to identify key trends and insights. The results indicated that about 61% of respondents belonged to the age group of 18-20 years, where half of the respondents (50%) were not even aware of the term Shrinkflation. About majority (68%) of respondents felt that brands or companies are not being transparent about Shrinkflation due to which consumers have started shifted to buying the product less often and also looking for various discounts to tackle this long term trend. Based on the data received it implies that Gen Z consumers have started exploring alternative brands and they want more transparency regarding the product to improve their experience on Shrinkflation.

A Study On Generation Z’s (Gen Z’s) Reaction Towards Shrinkflation

Authors: Anjali R

Abstract: This study aims to explore and analyze the Gen Z’s reaction towards Shrinkflation and their affect on purchasing behavior of Gen Z consumers, a phenomenon where product sizes decrease while the price remains the same. This has become increasingly prevalent in today’s economy. A sample of 100 respondents from diverse age groups, ranging from 18 years to26 and above, was surveyed using a structured questionnaire. . The data were analyzed using statistical and graphical tools to identify key trends and insights. The results indicated that about 61% of respondents belonged to the age group of 18-20 years, where half of the respondents (50%) were not even aware of the term Shrinkflation. About majority (68%) of respondents felt that brands or companies are not being transparent about Shrinkflation due to which consumers have started shifted to buying the product less often and also looking for various discounts to tackle this long term trend. Based on the data received it implies that Gen Z consumers have started exploring alternative brands and they want more transparency regarding the product to improve their experience on Shrinkflation.

Empowering Healthcare With AI: The Impact Of Large-Scale Pretrained Models

Authors: Professor Swati Bagade, Pallavi Patil, Vaishnvi Patil, Riya Sankpa, Harshwardhan Thorat

Abstract: Artificial Intelligence (AI) models, also known as foundation models, are advanced computer systems that can process huge amounts of data and have billions of settings to fine-tune their performance. Once trained, these models can handle a wide range of tasks with impressive accuracy. A well-known example is GPT, which has amazed people with its abilities and potential to impact different areas of life. In healthcare, AI models are changing the way medical research and diagnosis work. With the rise of deep learning, the amount of medical and biological data has grown significantly, providing new opportunities to develop AI systems that can improve healthcare.This paper explores the role of large AI models in medicine, discussing their background and how they are used. We focus on four key areas where AI can make a big difference:1)Bioinformatics 2)Medical Diagnosis 3)Medical informatics 4)Public Health.

Short News App MinuteMatter

Authors: Assistant Professor Sangeeta Mohapatra, Piyush Padole, Sahil Mulla, Naynesh Patil, Mukund Patil

Abstract: The Short News App is an app for mobile devices that provides brief, current news in a fast, easy-to-read format. With the increasing need for effective news consumption in the fast-paced world of today, this app provides consumers with the option to be informed without spending much time. It collects news from different credible sources and condenses articles into brief, informative summaries that can be read within seconds. Features of the app include customizable news categories, live updates, push alerts, and an easy-to-use interface to provide an overall improved user experience. Through its emphasis on conciseness and pertinence, the Short News App enables users to remain updated with the latest news while conserving precious time.

Deepfake Recognition System

Authors: Professor Swati Bagade, Dr. Anamika Jain, Aditya Sonune, Vedang Solaskar, Sanath Singh, Rishikesh Nate

Abstract: The widespread availability of altered images undermines confidence in digital media across multiple sectors. This work introduces an innovative web-based platform that harnesses deep learning to instantly distinguish genuine visuals from fabricated ones. Developed using Flask and a custom TensorFlow model with specialized components, the system allows users to upload images and receive rapid classifications through an intuitive interface. Experimental outcomes confirm its effectiveness in separating authentic from falsified content, supported by a design tailored for practical deployment. Unique activation functions and dropout techniques enhance the model’s durability, establishing it as a potent tool to counter visual misinformation.

Innovative Approaches In Fake Driving Licence Detection

Authors: Professor Swati Bagade, Vaishnavi Patra, Supriya Unde, Pooja Upadhyay, Sakshi Taru

Abstract: Counterfeit licenses pose significant security risks, leading to identity fraud and unauthorized access. Traditional verification methods are often slow, inefficient, and prone to human errors. This paper introduces an AI-based solution that combines image processing, Optical Character Recognition (OCR), and deep learning techniques for accurate fake license detection. A Convolutional Neural Network (CNN) is used to analyze both visual and textual elements, while blockchain technology ensures secure and tamper-proof verification. The proposed system enhances fraud prevention, enables real-time authentication, and improves regulatory enforcement. Experimental results show that this approach outperforms conventional detection methods in accuracy and efficiency.

Beyond Brands: Unveiling The Power Of Generic Medicines

Authors: Yashanjali Sisodia, Aniket Raut, Sarica Choudhari, Vidya Deshmukh, Grishma Fuke

Abstract: Access to affordable healthcare is a growing global concern, and the high cost of branded medicines often puts essential treatments out of reach for many. Generic medicines offer a practical and cost-effective solution, providing the same therapeutic benefits as their branded counterparts. However, misconceptions about their quality and effectiveness have slowed their acceptance. This research explores the role of generic medicines in modern healthcare, breaking down common myths and shedding light on the rigorous regulations that ensure their safety and efficacy. It also examines the economic impact of generics, their potential to reduce healthcare expenses, and the challenges manufacturers face, such as patent restrictions and consumer trust issues. By addressing these barriers and highlighting the benefits of generics, this study emphasizes the need for greater awareness, policy support, and public confidence. The findings suggest that improved education and stronger regulatory transparency can help shift perceptions, ultimately making healthcare more accessible and affordable for all.

ARTSETU : A World Of Handmade Treasure At Your Fingertips

Authors: Assistant Professor Yashanjali Sisodia, Ankita Choudhary, Srushti Gore, Sanika Bhokare

Abstract: The emergence of e-commerce has revolutionized how artisans and craftsmen reach their audiences. This research explores the development of a digital marketplace tailored for handmade art and crafts, focusing on secure payment solutions, personalized storefronts, and interactive engagement between artists and buyers. By analyzing existing platforms, user needs, and technological advancements, this study proposes an optimal framework for an inclusive, secure, and artist-friendly marketplace.

Rain Sensor: An Automated Protection System For Clothes

Authors: Assistant Professor Manisha Wasnik, Jay Burde, Shreya Tapkir, Apurva Solanke, Yash Burde, Siddesh Tapkir

Abstract: Drying clothes outdoors is a standard household practice, but unexpected weather changes, particularly rain, can cause inconvenience. Traditional drying methods rely on constant human supervision, making them inefficient. This project presents an Automatic Rain Sensor for Clothes, which autonomously detects rainfall and activates a protective covering to prevent clothes from getting wet. The system is designed with a rain detection sensor, a microcontroller, and an automated covering mechanism. When rain is detected, the microcontroller signals the system to deploy the protective covering. Once the rain stops, the cover retracts, allowing clothes to resume drying. This project emphasizes affordability, energy efficiency, and quick responsiveness to changing weather conditions.

Disaster Management System

Authors: Swati Bagade, Lavanya Vinaykumar Pashine, Mrunalini Kamble, Pranav Jadhav, Abhinash Roy

Abstract: Disasters, both natural and man-made, pose significant threats to human lives and infrastructure. Effective disaster management requires timely response, coordination between government agencies, s, and affected individuals, and real-time data collection. This project proposes a Disaster Management System, which serves as a platform where people in distress can request help and where volunteers, NGOs, and government agencies can respond efficiently.The system will include real-time reporting, resource allocation, and volunteer management features. The platform will support multiple users, including citizens, volunteers, and administrators, with role-based access to ensure efficient operations. The proposed system aims to improve disaster response efficiency and enhance communication during emergencies.

SAFARIMATE-A Centralized Platform For Streamlining Jungle Exploration

Authors: Professor Yashanjali Sisodia, Om Dongare, Pranav Gaikwad, Risheekesh Gavate, Atharva Dumbre

Abstract: Traveling through jungles and wildlife reserves is an exciting adventure, but it comes with its fair share of challenges—getting lost, struggling to find transport, securing safe lodging, and connecting with trustworthy tour guides. This paper introduces a website designed to solve these problems by offering real-time navigation help, transport details, accommodation options, and immersive cultural experiences. By using technology, the platform ensures a smoother, safer, and more enjoyable journey for travelers. Here, we discuss how the website works, its key features, and its potential to transform jungle tourism.

Keyloggers Application

Authors: Professor Swati Bagade, Dr. Anamika Jain, Sujata Patil, Anusha Rolla, Vaishanavi Sarangdhar

Abstract: This project presents a security system that helps protect laptops from unauthorized access. If someone enters the wrong password once, the owner receives a notification. After three incorrect attempts, the laptop shuts down automatically to prevent further access. If an intruder manages to log in using the correct password, they will be asked three security questions set by the owner. If they fail to answer correctly, the laptop shuts down again. This system improves security by sending real-time alerts, adding extra verification steps, and preventing unauthorized use while keeping user data private.

Face Mask Detection Using Convolutional Neural Network

Authors: Professor Swati Bagade, Khushi Dilip Wable, Siddhi Virendra Galande, Shreya Vinod Galande, Chanchal Suresh Khandarkar

Abstract: Wearing face masks is a recommended preventive measure to curb the spread of infectious diseases, particularly SARS-CoV-2. Consequently, automated detection of mask usage, including proper placement and mask type, remains a key area of research. Coronaviruses, a vast family of viruses, have significantly impacted public health due to their high transmissibility. To safeguard public health, individuals are encouraged to practice social distancing, maintain hand hygiene, and most importantly, wear face masks. Mask usage has become widespread globally, with densely populated regions, such as India, facing heightened challenges in ensuring compliance. The developed model has undergone through training and validation using a real-world dataset and has been additionally tested on live video streams to assess its effectiveness. The system’s accuracy has been evaluated under various conditions, including different distances, positions, and multiple individuals within a single frame, ensuring reliable and consistent performance.

Legal Information And Act Repository Software

Authors: Professor Swati Bagade, Dr.Anamika Jain, Vedashri Satle, Samruddhi Raskar, Viniya Sanap, Sneha Salunke

Abstract: This research targets an automated system developed in the form of a mobile application which provides relevant legal acts and sections based on user queries. It aims both at legal practitioners and the layman. Users need to explain a legal issue in a normal language and the software seeks the relevant laws, sections, and regulations. It enhances legal transparency, supports research, and aids compliance by tailoring content to different jurisdictions. The system uses structured databases and sophisticated search techniques to provide guaranties for precise and quick retrieval of legal information. With a user-friendly interface and offline accessibility, this application bridges the gap between legal complexities and public understanding, making legal knowledge more accessible, actionable, and efficient for various users, including legal professionals, businesses, and individuals seeking legal guidance.

Helping Hands Android Application

Authors: Deepti Varshney, Prerna Jadhav, Anam Shaikh, Anisha Dhumal, Tejal Pawar

Abstract: The “Helping Hands” app is designed to link donors with those in need, streamlining the process of distributing essentials like food and clothing. This mobile platform enables users to donate items effortlessly, monitor their contributions, and ensure that deliveries reach the intended recipients efficiently. By incorporating NGOs, hospitals, and animal shelters, the app enhances transparency and optimizes resource management. It tackles urgent issues such as hunger and homelessness, providing a straightforward yet powerful means to foster social responsibility and philanthropy within the community.

PDF2MindMap: AI-Based Interactive Mind Map Generation

Authors: Assistant Professor Sangeeta Mohapatra, Assistant Professor Pooja Mohbansi, Omkar Bhalekar, Avinash Nayakawadi, Sumit Patil, Md Mahbub Reza

Abstract: This paper presents an innovative application that converts PDF documents into interactive mind maps using advanced AI technologies. By leveraging Google’s Gemini AI model and Streamlit, PDF2MindMap extracts text from uploaded PDFs, processes it to identify key concepts, and generates a hierarchical markdown mind map. The mind map is visualized through an enhanced Markmap interface, providing an intuitive and dynamic way to explore document structures. This tool aims to streamline knowledge extraction and visualization, offering significant value in educational, research, and professional contexts where understanding complex documents quickly is essential.

Development Of Advanced Neural Network Architectures For Automated Autism Spectrum Disorder Diagnosis

Authors: Lokesh, Saurav Ingale, Ayush Kapse, Om Solanke, Milind Ankleshwa, Professor Kirti Randhe

Abstract: This survey paper investigates advancements in applying neural networks to Autism Spectrum Disorder (ASD) diagnosis, a condition characterized by challenges in communication, social interaction, and behavioral patterns. With early intervention critical for positive outcomes, traditional diagnostic methods are often time-consuming, subjective, and prone to limitations in accuracy. Emerging technologies like neural networks offer promising solutions for automating and improving ASD diagnostics. Our study systematically reviews current applications of neural networks, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), in analyzing behavioral patterns and facial image data. Key findings underscore the strengths of these models in capturing distinct ASD traits while also addressing challenges such as overfitting, data scarcity, and model generalizability. The integration of multi-modal data—such as combining behavioral cues with facial analysis—is explored as a pathway for enhancing diagnostic precision. While demonstrating the potential of these techniques, this paper highlights ethical considerations, including data privacy and the interpretability of neural network-based decisions in clinical settings. Future directions focus on developing self-updating datasets, promoting explainable AI, and fostering global collaborations to ensure diverse and representative data pools. This comprehensive review aims to guide the development of innovative, scalable, and ethically compliant diagnostic tools that make early ASD diagnosis more accessible and reliable.

MindSync : Bridging Emotional Support

Authors: Assistant Professor Sangeeta Mohapatra, Mr. Samarth Vitthal Pandit, Mrs. Ankita Jagdish Naik, Mrs. Sakshi Govind Nagargoje, Mr. Nandani Surendra Gaikwad, Mrs. Pranjal Santosh Pardeshi

Abstract: Mental health often takes a backseat in the fast-paced life of India, leading to rising cases of stress, anxiety, and lifestyle-related diseases. Many individuals struggle to find accessible and effective support systems. Our mental health tracker app aims to address this gap by offering an interactive chatbot for emotional support, expert-written blogs on wellness, a mood and habit tracker, and a smart health band to monitor vitals. This paper delves into the system design, key features, and its impact, drawing insights from recent research in digital mental health, peer influence, and intervention strategies.

MethodologyCrew – A Social Meetup and Movie Booking Platform

Authors: Assistant Professor Yashanjali Sisodia, Suraj Doke, Kaustubh Chaure, Shivam More, Sanskar Dhayade

Abstract: The increasing demand for social interaction and entertainment has led to the development of intelligent platforms that facilitate spontaneous connections in public spaces. Our Social Meetup and Movie Booking Platform integrates location-based services, AI-driven recommendations, and secure communication to provide users with seamless social experiences. By leveraging artificial intelligence and real-time data, the platform ensures personalized meetups, enhancing social engagement while prioritizing security and privacy. Additionally, the system is designed to be user-friendly, making it accessible to individuals with varying levels of technical expertise. This paper outlines the system architecture, methodology, implementation, and ease of use of our platform.

Hospital OPD Website

Authors: Assistant Professor Yashanjali Sisodia, Aryan Chaudhari, Ashish Bhanuse, Aman Kumar Arya, Aryan Rajpoot

Abstract: The purpose of this research paper is to create a website that will help with OPD and healthcare service management. Additional features on the website include video consultation, appointment scheduling, patient medical records, billing, and follow-up. The study assesses how well a website improves patient satisfaction, cuts down on waiting times, and eliminates needless crowding.

Readify: Evaluating the Virtual World Digital Library

Authors: Assistant Professor Manisha Wasnik, Jayraj khule, Mayur Mahajan, Tejas Gangrude, Nupur Gambhire, Riya Uchale

Abstract: The offline sale of books has been met with more and more challenges concerning market visibility, accessibility, and consumer engagement in this digitalizing world. This research proposes a mobile application to facilitate transactions between traditional book vendors and the online market, thereby raising their reach and streamlining their sales processes. The application thus provides an easy platform for the buying and selling of books, thereby creating a sustaining ecosystem for book reuse and affordability. It now bestows the vendors with utmost power in terms of modern tools and amenities to com In the ever-evolving retail space against the backdrop of storefronts, secured financial gateways, and inventory monitoring. The digital migration study thus addresses the vendors from a local perspective, operating within a paradigm of enhanced interplay within market corridors, economic engagement, and enhanced consumer experience.

Corner Connection :Neighbourhood Networking Hub Application

Authors: Assistant Professor Sangeeta Mohapatra, Sujay Pardeshi, Abhishek Nimbalkar, Santoshi Nelwade, Suhani Muke Divisha Patel

Abstract: Neighbourhood Connect is an innovative networking application designed to faster stronger community relationships and enhance local engagement. The application provides a digital platform for residents within a neighbourhood to connect, communicate, and collaborate on common interests and initiatives. Key features include a community bulletin board for announcements, chat functionalities for private and group discussions, an events calendar to highlight local activities, and showing availability of rooms. calendar to showcase local events, and a room availability display are some of the key features.

Smart Parking System

Authors: Dr. Deepti Varshney, Aditya Humbe, Rohan Vanjari, Nidhi Goyal, Om Hole

Abstract: The smart parking system is an advanced problem solution made to improve parking efficiency and user benefit by using sensor technology and mobile web application. The system uses components such as infrared sensors, ID UNO SMD, LCD display, 3.7 V battery, ESP 32, etc to monitor the status of parking spaces in real time. Identifying whether each slot is occupied or vacant. This data is transmitted via sensors on a user-friendly mobile web application. The data will be based on no. of parking slots available in the parking. The application provides on time updates on parking slots availability, allowing users to easily find and navigate to empty parking slot. By reducing time spent for finding parking, the system lowers fuel required and minimizes environmental impact.

Use Of Aloe Vera As A Natural Coagulant For Treatment Of Potable Water

Authors: Vishwajeet Kadlag, Rohit Chavan, Atharva Fulware, Tejas Khirad

Abstract: Access to clean and safe drinking water remains a pressing challenge, especially in rural and developing regions. Traditional chemical coagulants like alum are effective in water treatment but can pose health risks and environmental concerns. To provide a safer and eco-friendly alternative, we explored the use of Aloe Vera as a natural coagulant for the treatment of potable water. Aloe Vera contains bioactive compounds such as polysaccharides and glycoproteins, which facilitate the coagulation process by destabilizing suspended particles. In this project, raw water samples were treated with Aloe Vera extract, and key parameters such as turbidity, pH, and microbial load were monitored. The results demonstrated significant improvement in water clarity and quality, proving that Aloe Vera is a promising natural substitute for chemical coagulants. This method offers a sustainable, non-toxic, and cost- effective solution suitable for rural communities and emergency water purification needs. By promoting the use of plant-based coagulants, the system enhances public health and environmental safety. It represents a step forward in natural water treatment technologies and supports the global move toward green chemistry.

A Comprehensive Survey On Applications Of Artificial Intelligence In Cyber Security

Authors: Prof. Kirti Randhe, Atharva Kendale, Siddhesh Bhargude, Shantanu Thorat

Abstract: – With the proliferation of digital technologies, cyber threats have become increasingly complex, dynamic, and difficult to mitigate using traditional defense mechanisms. Artificial Intelligence (AI), encompassing machine learning (ML), deep learning (DL), and Natural Language Processing (NLP), has emerged as a transformative force in modern cyber security systems. This survey presents an in-depth exploration of how AI is revolutionizing the landscape of cyber defense. We analyze key AI techniques, their applications in intrusion detection systems (IDS), malware analysis, phishing detection, threat hunting, and anomaly detection. Additionally, the paper explores real-world deployments, benefits, challenges, and the future trajectory of AI-driven cyber security solutions. The study integrates insights from over ten recent peer-reviewed sources and proposes future research directions in explainable AI, adversarial robustness, and real-time edge-AI models.

Population Density And Sanitation Challenges In Lucknow

Authors: Assistant Professor DR. Ritu Jain, Anamika Rawat

Abstract: health, especially in rapidly growing cities of developing countries. Lucknow, the capital of Uttar Pradesh, India, has experienced tremendous demographic expansion over the last few decades, intensifying pressure on its sanitation systems. This paper examines the interlinked issues of population density and sanitation in Lucknow by analyzing demographic trends, urban planning limitations, infrastructure deficits, socio-economic factors, and policy responses. The study emphasizes the need for holistic urban governance, community engagement, and sustainable technological interventions to address sanitation challenges and improve urban health outcare are the keywords based on your abstract.

Optimum Base Isolation Method To Resist Seismic Effect On Mid-Rise Structure

Authors: Atharv Nale, Niraj Gadewar, Piyush Sahu, Gaurav Varade, Prof. Sangita Mishra

Abstract: The main objective of project is to compare conventional Seismic analysis and lead rubber bearing system. While no structure can be entirely immune to damage from earthquakes, the goal of earthquake resistant construction is to erect structures that fare better during Seismic activity than their conventional counterparts. The installation of isolators at the base increases the flexibility of the building structures. In present study Modeling and analysis of G+10 storey RC building is done in ETBS software for two cases. The first one is fixed base and the second one is base isolated; one vertical irregular model is considered and analysis is done by equivalent static and response spectrum method. The Lead rubber bearing (LRB) is designed as per IS and UBC 97 code and the same was used for analysis of base isolation system. The results obtained from analysis were Storey displacement. Damper systems are designed and manufactured to protect integrities and structural damages and to prevent injuries. There are many techniques to make seismic resistant structure. The base isolation technique is used in this project to resist against earthquake. Lead Rubber Bearing is a new type earthquake resistance rubber bearing, formed by inserting lead core into ordinary laminated rubber bearing, vertical supporting, and horizontal displacement and hysteric damping are combined in single unit together.

Metal And Non-Metal Sorting By Using PLC

Authors: Professor M.D.Patil, Mr. Kumbhar Sani Anil, Mr. Dadas Swapnil Uttam

Abstract: The increasing need for automation in industries has led to the development of systems that can improve efficiency, accuracy, and reduce human involvement in repetitive tasks. This project, titled “Sorting of Metal and Non-Metal using PLC,” focuses on designing an automated system that can differentiate and sort materials based on their metallic or non-metallic properties. Using a conveyor belt mechanism integrated with an inductive proximity sensor and controlled by a Delta DVP14SS2 PLC, the system detects the material type of objects and sorts them accordingly. The automation process ensures high- speed operation, consistent accuracy, and minimized errors compared to manual sorting. This project demonstrates the practical application of PLCs in industrial automation and material handling, offering a cost-effective and scalable solution suitable for small and medium-scale industries. The system is designed to be modular, allowing future expansion such as adding more sensors or integrating a vision system. It also promotes safety by reducing the need for manual intervention in hazardous working environments. The success of this project highlights the potential of automation to transform traditional material handling processes into more intelligent, reliable, and efficient systems. The implementation of such automated sorting systems can greatly benefit industries like recycling plants, manufacturing units, and quality control departments by streamlining their operations and ensuring greater precision. The integration of PLC technology not only makes the system more flexible and adaptive but also simplifies troubleshooting and future upgrades. Overall, this project sets a strong foundation for the future development of more advanced material classification and handling systems using automation and smart technologies.

Research Paper in Data Analysis ,And Tools

Authors: Rahul Yadav, Dr. R.S Khatana

Abstract: Data analysis plays a crucial role in today’s data-driven world. It is the science of examining raw data to make conclusions, identify patterns, and support decision-making. This paper explores the definition, techniques, tools, and real-world applications of data analysis, especially in sectors like business, healthcare, education, and government. With the rising importance of big data, this study also discusses ethical considerations and challenges faced in data analysis.Data analysis is indispensable in the digital age. From simplifying operations to transforming entire industries, its potential is vast. However, with power comes responsibility. Ethical handling of data, maintaining quality, and using insights judiciously are key to unlocking the true potential of data analysis.

Machine Learning-Driven Malware Detection For Malicious Domains And Unsafe Software Sources

Authors: Tarush Katiyar,, Khushi Pant, Sumit Yadav, Aman Anand, Dr. Vivek Kumar,, Dr. Hitesh Singh,

Abstract: The rapid growth of cyber threats, especially malicious domain (phishing) attacks, calls for advanced detection methods beyond traditional signatures. We propose a machine learning framework that analyzes URL characteristics and other features to classify domains as safe or malicious. The system uses Python-based tools (Pandas, scikit-learn, XGBoost) to train and evaluate multiple classifiers – including Random Forests, Decision Trees, Gradient Boosting, XGBoost, and Logistic Regression. Features are extracted directly from URL strings (such as domain entropy, URL length, and special character counts) along with blacklist/whitelist checks. On a large URL dataset (≈700k samples), ensemble methods achieved high accuracy: for example, Random Forest reached 95% accuracy on the test set, and XGBoost reached 94%. In contrast, a simple logistic regression achieved only 78% accuracy, showing the advantage of tree-based models on this task. Our results demonstrate that ML-driven analysis of URL -based features can effectively detect malicious domains, significantly improving over naive baselines. The framework is implemented as a Python pipeline and can be integrated into real-time security tools. Future work will extend this approach with additional data sources and advanced learning techniques to further improve detection rates.

Substation Surveillance Using Camera Based Vehicle

Authors: Professor Dr. A. A. Kalage, Megha Dagadu Gade, Vaishnavi Digambhar Mundhe, Shraddha Sandip Ambekar, Asmita Amarsingh Jagdale

Abstract: Transmissao Paulista actually operates 105 substations geographically distributed across Sao Paulo State. These substations are remotely operated by two Operating Centers – Transmission Operating Center (COT Centro de Operacao da Transmissao), Bom Jardim SP, and Back-end Operating Center (COR – Centro de Operacao Retaguarda), Cabreiiva SP. Through the years, CTEEP has been deploying its high reliability and throughput WAN/LAN to connect all of its key facilities. Based on such corporate network infrastructure, it was possible to provide remote operations with a visual, real time monitoring system. Its structure comprises cameras installed in substation strategic spots, local digital image recorder and devices to convert and regulate video streams and control cameras, and Ethernet network interfaces. The system allows visual checking of operating handling, physical status of substation yard, and perimeter integrity thus addressing many corporative areas’ needs. Since there is a high reliability, high throughput corporative network infrastructure available to connect main facilities, it enable us to provide remote substation operations with support of a visual, real time monitoring system, which comprises camera movement control, tamper-proof recording, image transmission and viewing, both locally and remotely. SIM – Sistema Integrado de Monitoramento (Integrated Monitoring System) is a joint project among CTEEP’s Enterprise Security, Information Technology, and Maintenance and Operations organizations. It aims to deploy a visual monitoring system for electrical substations providing camera movement control, tamper-proof recording, image transmission and viewing, both locally and remotely using existent corporative network (“browser-based”). It allows electrical system operations and enterprise security organizations to monitor substations and other CTEEP facilities through images transmitted via data channels (corporative network), which are enabled by heterogeneous technologies and throughput, from frame relay (64Kbs to 512Kbps) to fiber optic/digital radio links (2Mbps). By promoting integration of video, audio, and text information, and by associating it to company existing databases, SIM also meets CTEEP’s strategic goals related to information system integration (technological convergence). In addition to align strategic information integration goals, SIM deployment will provide CTEEP Electrical Transmission System operators with environmental viewing of facilities in a real-time, strategic way, enabling an improvement of operating processes. SIM usage means lower costs related to staff displacement to remotely assisted substations, either for equipment handling checking, equipment current status checking or substation areas physical integrity checking. All of these intended to optimize access to substations risk areas. Also, note that such solution means lower operating and maintenance costs for entire company due to its standardization.

Research Paper in Data Analysis ,And Tools

Authors: Rahul Yadav, Dr. R.S Khatana

Abstract: Data analysis plays a crucial role in today’s data-driven world. It is the science of examining raw data to make conclusions, identify patterns, and support decision-making. This paper explores the definition, techniques, tools, and real-world applications of data analysis, especially in sectors like business, healthcare, education, and government. With the rising importance of big data, this study also discusses ethical considerations and challenges faced in data analysis.Data analysis is indispensable in the digital age. From simplifying operations to transforming entire industries, its potential is vast. However, with power comes responsibility. Ethical handling of data, maintaining quality, and using insights judiciously are key to unlocking the true potential of data analysis.

A Deep Learning Approach To Mental State Analysis Of EEG

Authors: Siddharth Mahankal, Suyesh Shinde, Akash Unhale, Dr. Jagannath Nalavde Arun, Hirmukhe

Abstract: Mental health issues are becoming increasingly common among individuals over the age of 16, with academic, social, and career-related stress being the main reasons. Traditional mental health assessment methods, such as surveys or counseling, are often affected by personal biases or insufficient information. With this in mind, our project presents a system that collects and analyzes EEG (electroencephalogram) brain wave graphs across different mental states — such as awake, drowsy, and deep sleep. Users upload a multi-page PDF report containing the EEG graph to the system. This PDF is then separated into pages, analyzed with the help of a trained machine learning model, and the percentage probability of the user’s mental state being normal or abnormal is displayed. The system is trained on a dataset of EEG graphs classified by experts. Importantly, this project is not intended to be a substitute for medical diagnosis or professional mental health services. Instead, the project seeks to raise awareness and act as a link between individuals and mental health professionals, especially for those who may not recognize the need for help. The ultimate goal is to make early mental health screening in educational institutions more accessible, data-based, and stigma-free.</p

Comparative Study And Performance Assessment Of Stone Matrix Asphalt Incorporating Different Fibers

Authors: Assistant Professor Mohammad Zayan, Akhi S Ragh

Abstract: Bituminous mixtures serve as wearing and base layers in pavements, with performance judged by resistance to deformation, cracking, moisture damage, and stiffness. Stone Matrix Asphalt (SMA), using PMB 40-grade bitumen, offers better rut resistance than conventional mixes. This study tested SMA mixes with glass and jute fibers, examining tensile strength, drain down, and rutting resistance. Glass fiber improved stability, stiffness, and reduced bitumen drain down, while jute fiber showed higher drain down due to its elasticity. Overall, glass fiber outperformed jute in enhancing rutting resistance and long-term performance. The findings emphasize the importance of fiber selection for optimizing SMA mix designs and improving pavement durability.

Investigating Bias Detection and Mitigation in AI-Powered Recruitment Systems

Authors: Payal Anil Barhate, Associate Professor Dr. Ayesha Siddiqui, Dr.Nagsen Bansod, Dr.Rajkumar Deshpande

Abstract: Artificial Intelligence (AI) is changing the way companies hire people by making it possible to automatically screen resumes, predict who will get the job, and assess behaviour. These new technologies make things much more efficient and scalable, but they also raise important ethical issues, especially the possibility of algorithmic bias. Unfair discrimination against candidates based on their gender, race, or socioeconomic background can happen when training data is biassed, decision-making models are unclear, and there is no accountability. This study looks into where bias comes from and how it shows up in AI-powered hiring systems. It also looks at a range of ways to reduce bias, which are divided into three groups: pre-processing, in-processing, and post-processing. It looks at how well tools like fairness-aware learning, adversarial debiasing, and equalised odds post-processing work to promote fairness.

Crash Analysis Using Regression Model In Kollam District

Authors: Assistant Professor Niranjini Shibu, Assistant Professor Sameena A

Abstract: Rapid population expansion and rising economic activity have led to an enormous increase in motor vehicles, which is one of the main causes of an increase in road accidents in many major cities. In this paper, four factors are taken into account while evaluating the degree of road safety in Karunagapally, Kollam District. The factors considered are accident severity index, accident fatality rate, accident risk and accident risk. The data set for six years (2017 to 2022) is brought from “Police Department”. And also, Regression-based data analysis carried out to foresee the likelihood of accidents in a given environment. As a result, there is or should be a close relationship between crash investigation, data collection and analysis, and the creation and evaluation of viable countermeasures. Finally, it is critical that the study results are shared to those who are involved in implementing countermeasures and preventive programs.

The Future Of Artificial Intelligence: Opportunities, Challenges, And Ethical Implications

Authors: Nitin Yadav, Assistant Professor Dr. Rajendra Khatana, Neeharika Sengar

Abstract: Artificial Intelligence (AI) is changing our world very quickly. It affects how we work, learn, communicate, and get medical help. This paper talks about where AI is heading in the future. It looks at the good things AI can bring, the problems it might cause, and the ethical questions we need to think about. As AI becomes smarter and more powerful, we need to be careful about how we use it. This paper discusses trends, new technologies, and why it’s important to develop AI in a responsible and fair way. AI is no longer a futuristic concept—it is deeply embedded in many areas of our lives. From personalized recommendations on streaming platforms to advanced medical diagnostics, AI systems are assisting humans in making better decisions and improving efficiency. With rapid advancements in machine learning, deep learning, and natural language processing, AI continues to break new ground, offering innovative solutions to problems once thought to be unsolvable. The potential benefits of AI are vast. In healthcare, AI can assist doctors by analyzing medical images and patient data to detect diseases earlier and with higher accuracy. In education, AI-powered tutors can adapt to individual students’ learning styles. In transportation, autonomous vehicles promise to reduce accidents and traffic congestion. AI also holds the promise of transforming industries like agriculture, where smart sensors and predictive analytics can increase crop yields while reducing environmental impact. This paper aims to provide a comprehensive overview of these issues by examining the current state of AI, future trends, and possible applications. It also addresses the ethical and societal implications of widespread AI adoption. The goal is not only to inform but also to encourage responsible innovation—AI must be developed with fairness, transparency, accountability, and inclusiveness in mind.

Human Pose Estimation & Correction During Exercise Using ML

Authors: Miss.Kithe Priya Suresh, Miss.Khatal Sneha Pradip, Dr.Khatri.A.A

Abstract: The fields of magnetism and resonance are crucial to the operation of Electric Vehicle Wireless Communication (EVWC) devices. A magnetic field is produced when electricity flows through a coil of wire, just as it is in a transformer. For Wireless Power Transfer (WPT) to work, it’s necessary to position two coils in such a way that one’s magnetic field induces a current in the other. Unless the coils are very close to one another and aligned in a straight line, inductive power transfer is inefficient. In this paper work related to wireless charging system proposed by various researchers is explored. Concept of Static and dynamic charging, Inductive power transmission, wireless power transmission techniques including inductive and capacitive coupling, far field techniques like Radio, microwave and laser techniques are also presented.

Numerical Investigation Of Gurney Flap In Martian Atmospheric Condition

Authors: L. Parinita Goud , Panneeru Nandini, M. Hrithika Marie, B. Aslesha

Abstract:-Exploration of Martian atmospheric conditions present numerous challenges, particularly regarding the aerodynamic performance of aerial vehicles. This study investigates the impact of Gurney flaps on airfoil behavior under static stall conditions in a Martian environment. Computational analyses are conducted to evaluate how the presence of a Gurney flap influences stall characteristics. Various Gurney flap sizes, expressed as percentages of the airfoil chord length, are examined. Simulations are performed at angles of attack (AoA) of 5°, 10°, 15°, and 20° for both clean airfoil configurations and airfoils equipped with Gurney flaps. The corresponding lift (Cl) and drag (Cd) coefficients are recorded and analyzed through graphical representation. Results indicate that, for angles of attack between -10° and approximately 10°, both the clean airfoil and the airfoil with a Gurney flap exhibit a similar trend, with the lift coefficient increasing as the angle of attack increases. However, the 1% chord Gurney flap configuration consistently yields slightly higher Cl values compared to the clean airfoil. As the angle of attack approaches 15° to 20°, both configurations demonstrate a peak in Cl, highlighting the Gurney flap’s influence on stall delay and overall lift
enhancement.

A Sustainable Approach To Compressed Earth Brick Stabilization Using Iron Dust, Metakaolin And Oxalic Acid

Authors: Saravanan.G, Assistant Professor Kalaimathi.D

Abstract: The project aimed to explore the possibility of fully or partially replacing cement as a stabilizer in Compressed Stabilized Earth Blocks (CSEBs). Cement is commonly used as a stabilizer in CSEBs, but it has a high carbon footprint. The bricks were tested for compressive strength along with water absorption and efflorescence. A comparison of strength gain between them was also conducted. Two proposed mixes, referred to as P-cement 1 and P-cement 2, were selected based on literature review for better comparison and to identify the optimum mix. To evaluate the strength characteristics of these mixes, mortar cubes were cast using both P- cement variants and Ordinary Portland Cement (OPC), and then tested for compressive strength.

Smart Tongue Diagnosis For Gastrointestinal Diseases Using ResNet50

Authors: Anjali Kadam, Aishwarya Bhosale, Vaishnavi Jadhav, Swara Chavan, Dnyaneshwari Mohotkar

Abstract: Tongue diagnosis has traditionally been a non-invasive method for detecting gastrointestinal (GI) disorders, widely practiced in Eastern medicine. This research explores the use of a fine-tuned ResNet50 model for tongue image classification to aid in the diagnosis of gastrointestinal (GI) disorders. The model was trained on labeled images focused on three conditions: fissure, constipation, and hyperacidity. The dataset was manually collected from patients with assistance from an Ayurvedic practitioner, including hospital visits and shared tongue images. Preprocessing and augmentation techniques were applied to enhance generalization. The model achieved 80–97% accuracy on known images but dropped to 50–60% on unseen data, highlighting the need for a larger dataset. This project is intended as a foundation for future research, with the expectation that the accuracy and number of diagnosable conditions will improve as the dataset expands.

Building Scalable, Regulatory Compliant Clinical Trials Platforms For Nih-Sponsored Research

Authors: Venkata Krishna, Bharadwaj Parasaram

Abstract: Clinical research faces critical challenges in scalability, data integrity, and regulatory compliance, particularly for large-scale NIH-sponsored trials (National Institutes of Health [NIH], 2023). This paper presents a cloud-based architecture leveraging Amazon Web Services (AWS) to address these challenges through three key innovations: (1) a HIPAA-compliant infrastructure with real- time data capture, (2) automated monitoring for FDA 21 CFR Part 11 compliance, and (3) nationally scalable deployment models.Our proposed architecture utilizes AWS Aurora PostgreSQL for electronic health record storage (Amazon Web Services [AWS], 2025) and Kinesis Data Streams for real-time ingestion of wearable device data (Smith et al., 2024). The system implements granular access controls through AWS Identity and Access Management (IAM), addressing NIH’s emphasis on data security in multi-center trials (Collins & Tabak, 2024). Compliance features include automated audit trails via CloudTrail (U.S. Food and Drug Administration [FDA], 2022) and PHI detection using Macie (Johnson & Patel, 2024).Real-time dashboards built with QuickSight enable trial monitoring across 120+ sites, reducing protocol deviation detection time from 14 days to 48 hours in pilot testing (Légaré et al., 2023). The platform’s national scalability is demonstrated through AWS Local Zones deployment, decreasing latency for rural sites by 72% compared to traditional models (Roberts et al., 2023). We evaluate this architecture against NIH’s Strategic Plan for Data Science (NIH, 2023), highlighting its alignment with FAIR data principles while addressing persistent challenges in trial diversity enrollment (Bierer et al., 2022). The paper concludes with implementation guidelines for academic medical centers and cost-benefit analysis comparing cloud versus on-premises solutions (Mandel et al., 2024).

Human Pose Estimation & Correction During Exercise Using ML

Authors: Miss.Kithe Priya Suresh, Miss.Khatal Sneha Pradip, Dr.Khatri.A.A

Abstract: The fields of magnetism and resonance are crucial to the operation of Electric Vehicle Wireless Communication (EVWC) devices. A magnetic field is produced when electricity flows through a coil of wire, just as it is in a transformer. For Wireless Power Transfer (WPT) to work, it’s necessary to position two coils in such a way that one’s magnetic field induces a current in the other. Unless the coils are very close to one another and aligned in a straight line, inductive power transfer is inefficient. In this paper work related to wireless charging system proposed by various researchers is explored. Concept of Static and dynamic charging, Inductive power transmission, wireless power transmission techniques including inductive and capacitive coupling, far field techniques like Radio, microwave and laser techniques are also presented.

The Role Of Mathematics In Machine Learning: A Comprehensive Study

Authors: Rohit Kamleshwar Singh, Sangram Kakade, Dr. Nagsen Bansod, Dr. R. S. Deshpande

Abstract: Mathematics is the backbone of machine learning, providing the theoretical framework required to develop algorithms, optimize models, and interpret data patterns. The integration of mathematical disciplines such as linear algebra, probability theory, statistics, calculus, and optimization enables the construction of robust machine learning systems. This paper justify the essential mathematical concepts that underpin machine learning, covering major topics such as matrix operations, statistical inference, statistical inference, optimization techniques, and differential equations. Additionally, it impart how these mathematical tools contribute to several machine learning paradigms, such as deep learning, reinforce ment learning, supervised learning, and unsupervised learning. By understanding the function of mathematics in machine learning, researchers and practitioners can enhance model performance and develop innovative AI-driven solutions.

Impact Of Online Learning Education

Authors: Vivek Ghogare,, Dr. Quazi Khabeer

Abstract: The fast advancement of innovation has tremendously affected the instruction scene, particularly with the Affect Of Online Learning Instruction. This term paper examines how online learning influences learning results, understudy inspiration, openness, and instructing proficiency. Based on different quantitative and subjective information, the think about examines both the benefits and issues of online instruction. The foremost noticeable recognized benefits are more noteworthy adaptability, individualized learning directions, and more extensive get to to learning materials. In any case, the think about too focuses to critical issues like computerized difference, less social interaction, and varying degrees of learner selfmotivation and teach. The comes about infer that indeed in spite of the fact that online learning holds colossal potential for progressing instruction, it is intensely unexpected on advanced substance plan, educator preparation, and back structures for understudies.</p

Final Fake Paper Abcd Se Lena

Authors: Shanmukha Priya Kurre, Bapanapalli Naga Bhargavi, Guntur Pushpa, Dabbugottu Thirupathi Vani, Chinthabttina Meghamala, Dhulipudi Chinmayi Sai Sri.

Abstract: The Red Chilli Defect Detection and Removal System is a robust and automated solution designed to identify and remove defective red chillies on a conveyor belt. Utilizing a Raspberry Pi 3 B V1.2 and a Pi Camera module, the system captures real-time images of chillies as they move along the belt. Advanced image processing algorithms analyze these images to detect defects based on predefined parameters such as color, shape, and texture. Upon detection of a defective chilli, a control signal is sent to a DC motor-controlled ejection mechanism powered by an L293D motor driver to remove the defective chilli from the conveyor. This automated approach enhances the efficiency and precision of the quality control process in industries handling red chilli sorting, ensuring higher throughput and consistent product quality.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.275

Text Mining Using Sentiment Analysis

Authors: Sanjana Bhandare, Ajinkya Pokharkar, Prerna Bhandare, Dnyaneshwar Chaudhari, Dr. Manisha Wasnik

Abstract: In this era of the most popular social networking, Twitter has many users who express their thoughts in the form of tweets. This paper presents an idea to extract sentiments from tweets and a method to classify tweets as good, bad or neutral. This approach is beneficial in many ways for all organizations mentioned or tagged in a tweet. Generally speaking, tweets are in unstructured format and tweets need to be converted into structure first. In this paper, tweets are analyzed using predefined steps and accessed by the library using Twitter API. The data needs to be learned using algorithms that allow it to test tweets and extract the desired information from given tweets.

Educational And Vocational Interests In Relation To Academic Achievements Of Secondary School Students In Delhi

Authors: Sonali Bahuguna, Professor Indu Sharma

Abstract: This research examines the connection between educational and vocational interests and the academic performance of secondary school students in Delhi. Considering the recent inclusion of vocational courses in more than 800 government schools as part of the samagra shiksha scheme, this study examines the correlation between students’ interests and their academic achievements. The study employs a stratified random sample of 500 students from various socio-economic and institutional backgrounds, utilizing standardized interest inventories and academic data analysis. The findings indicate a strong positive relationship between educational and vocational interests and academic performance, with vocational interests having a greater predictive power. This supports the belief that incorporating student interests into educational content can enhance academic engagement and achievement.

Characteristics Of High Performing Organizations: A Case Study Of Tesla, Inc.

Authors: Raghu V Kaspa

Abstract: High Performing Organizations (HPOs) consistently outperform their peers in metrics such as innovation, agility, financial results, and employee engagement. This paper explores the critical attributes that characterize HPOs and applies these attributes to Tesla, Inc., as a case study. Through an analytical lens grounded in organizational theory, performance frameworks, and empirical evidence, Tesla’s rise as a global automotive and energy leader is examined to identify the drivers of its high performance.

Smart Society Solution– Transforming Community Management With Digital Approach For Efficient Society Administration

Authors: Anjali Gupta, Assistant Professor Pooja, Dr. Rajendra Singh

Abstract: In the modern era of rapid urbanization, gated communities and residential societies require an integrated, scalable, and secure management solution to handle day-to-day operations efficiently. This paper presents the design and development of Smart Society Solution (SSS)—a web-based platform engineered using React.js for the frontend, Strapi for headless backend services, and Tailwind CSS/Bootstrap for responsive UI/UX. The system provides a modular architecture, supporting essential community management functions like dashboard analytics, service request handling, resident and visitor management, billing, and reporting. RESTful APIs tested via Swagger ensure seamless client-server communication. The solution offers robust extensibility and has potential implications for smart city planning and digital governance

Drug Discovery Using Generative Adversial Network

Authors: Professor Anita Mahajan, Ajaz Shaikh, Shubham Ghume, Neeraj Lonkar, Saif Shaikh

Abstract: Drug development research is traditionally a lengthy, resource-intensive, and expensive process, often relying on experimental approaches and iterative laboratory trials. the emergence of generative adversarial networks (gans) hasintroduced a novel and efficient approach to this field by facilitating the generation of new molecular structures. This research explores the application of molgan, a specialized gan framework tailored for generating molecular graphs in drug discovery. traditional methods struggle with inefficiencies and the vastness of the chemical space, making it challenging to identify molecules with specific pharmacological properties. molgan addresses these limitations by automating molecular generation while incorporating desired chemical characteristics. by leveraging reinforcement learning techniques, molgan fine- tunes the generation process to produce drug-like molecules, enhancing both the speed and effectiveness of drug discovery efforts.

Votechian:A Biometric Blockchain – Based Voting System

Authors: Manisha Wasnik, Shreya Sharma, Aamir Shaikh, Abhishek Shinde, Harsh Tagde

Abstract: CryptoNavigator is a cryptocurrency tracking application built with Flutter, Dart, and Supabase. It fetches live market data through the CoinGecko API, providing real-time price tracking, search, favorites, and deep insights per cryptocurrency. Secure user login through email verification and profile management are some of its security features. One of the main features is price prediction to assist investors in making knowledge-based decisions. With a user-friendly UI and cross-platform support, CryptoNavigator aims to assist both new and experienced investors in tracking and predicting cryptocurrency trends.

DOI: http://doi.org/

A Study Paper On Power System Safety

Authors: Assistant professor Satya Pavan Kumar Voleti, Madhu Babu Thadee, Sirisha Adari, Pala Vijayab, Satya Praksh

Abstract: Power system safety is a one of the major focused areas in recent days due to mismatch between power generation and power demand. Successful operation of a power system depends largely on the engineer’s ability to provide reliable and uninterrupted service to the loads. Safety includes both the operation and planning of power system networks i.e both voltage and frequency at allloads must be held within acceptable tolerances so that the patron equipment will operate efficiently.Inordertoachieve safety the system generators should run synchronously andwith adequate capacity to meet the load power demand. Secondly, the integrity of the power network should ‘be maintained to ensure continuity of service. Power systems occasionally suffer perturbations. These perturbations may be small originating from random changes in loads or they may be severe arising out of a fault on the network.This paper presents brief overview of differenttypesofinstabilities inpower systemandthe techniques used to overcome it. The paper also compares the applicabilityof different techniques on the basis of performance.

Machine Unlearning: A Review Of Techniques, Applications And Challenges

Authors: Kusum Kumari, Goutam Shaw, Debosmita Sukul, Anurima Majumdar, Antara Ghosal, Koushik Pal

Abstract: This paper discusses the advancement, challenges, and future of machine unlearning with emphasis on its significance in enhancing data privacy, security, and compliance with regulatory requirements. The review process began in 2015 and is ongoing to the current year. As privacy has become the focal point within the machine learning community, along with regulations like the General Data Protection Regulation (GDPR), machine unlearning—removing specific data from machine learning models—has attracted significant attention. The process of deleting such data is naturally timeconsuming, considering that it requires a complete retraining of the entire model; hence, traditional models have a dilemma because the process of erasing data is technically challenging and usually impractical considering the associated costs of computation. Machine unlearning enhances data privacy by facilitating selective erasure of specific data points without the need for total model retraining. It also improves model responsiveness and compliance with regulations like GDPR, hence encouraging the ethical application of artificial intelligence. The advantages of machine unlearning are enhanced data privacy, enhanced model performance, efficient utilization of resources, reduction of bias, quicker updates, and ensured compliance with ethics and laws. Through out the extensive literature survey a significant gap is observed to be that there are no reproducible, standardized procedures confirming the complete and effective elimination of data without compromising model efficiency and scalability. Areas of latent application in sectors like healthcare, finance, personalized services, and federated learning are identified, particularly in situations where unlearning is required to ensure privacy and compliance with regulations.

DOI: DOI: http://doi.org/10.5281/zenodo.15783199

Soft Computing Techniques In Neuroimaging

Authors: Ms. Monalisa Baral, Ms. Komal Bhamble, Dr. Jasbir Kaur, Ms. Ifrah Kampoo

Abstract: A variety of real-world problems are being addressed today by soft computing, but limited research has been found in the area of neuroimaging. Given the vast area of neuroimaging that can be explored through soft computing, researchers can work on and improve their work. The results of this research should advance soft-computing approaches to address neuroimaging problems. However, the human brain contains a large portion of the dataset, and the dataset is not homogeneous, so it is not easy to deal with the problem. A heuristic approach to soft computing can play an important role in addressing problems within limited time constraints. Furthermore, fuzzy logic is also an effective neural networks, fuzzy logic, statistics, and probabilistic inference. In addition, parts of machine learning and optimization are also included in this domain. However, Neuro imaging is primarily focused on brain data and the impact on behavioral and cognitive data by analyzing solution for identifying neurodivergent diseases. To combine all the fruitful solutions, this research topic aims to summarize all the solutions by covering a wide range of soft computing and neuroimaging methods

DOI: 10.61137/ijsret.vol.11.issue3.153

WECAN:AI-Driven Personalized Cancer Treatment App

Authors: Kashish Srivastava, Prerana Kumari, Jatin Sharma, Nikhil Sharma, Dr. Hitesh Singh, Dr. Vivek Kumar

Abstract: The AI-Powered Personalized Cancer Treatment App “WeCan” is an innovative initiative that incorporates the latest technologies such as React.js, Vite, and Gemini AI to bring back personalized cancer treatment recommendations to patients. Our revolutionary approach leverages machine learning algorithms along with deep medical expertise to review individual patient profiles such as genetic data, medical history, and lifestyle factors to develop customized treatment plans optimized for efficacy and reduced side effects. WeCan’s user-friendly interface allows patients to enter their medical details and gain personalized advice, while healthcare providers can view detailed reports and track patient progress in real-time. This enables data-driven decision-making and maximizes patient outcomes throughout the cancer care continuum. The core of WeCan’s architecture revolves around an ultrasecure data management system that protects sensitive patient data through compliant storage and secure processing techniques. Sophisticated encryption technologies safeguard data in transit and at rest. The back end is engineered to integrate with existing healthcare infrastructure seamlessly, supporting effective data exchange with minimal administrative burden for providers, so they can spend more time on patient care and less on paperwork. With the fusion of AI-driven insights and predictive analytics, WeCan enables healthcare providers to detect high-risk patients and create customized treatment plans based on the individual characteristics, background, and genetic profile of each patient. Through this personalized strategy, decision-making is more informed, resources are optimized, and patient outcomes are maximized. The tool integrates patient data, such as treatment plans, prognosis factors, and probable outcomes, into a single, user-friendly interface. This simplifies the handling of cancer care and facilitates improved coordination among healthcare professionals, patients, and caregivers along the journey. Ultimately, this patientfocused and cooperative strategy revolutionizes the way healthcare providers interact with cancer patients by facilitating more efficacious and personalized treatments.

Data Analysis

Authors: Dr.R.S Khatana, Rahul Yadav

 

 

Abstract: Abstract- Data analysis plays a crucial role in today’s data-driven world. It is the science of examining raw data to make conclusions, identify patterns, and support decision-making. This paper explores the definition, techniques, tools, and real-world applications of data analysis, especially in sectors like business, healthcare, education, and government. With the rising importance of big data, this study also discusses ethical considerations and challenges faced in data analysis.Data analysis is indispensable in the digital age. From simplifying operations to transforming entire industries, its potential is vast. However, with power comes responsibility. Ethical handling of data, maintaining quality, and using insights judiciously are key to unlocking the true potential of data analysis. Keywords-Data Analysis,Big Data,Decision-Making,Data-Driven,Analytical Techniques.

DOI: http://doi.org/

Personal Finance Management System Using Java Swing And MySQL

Authors: Darshita Singh, Shreya Saini, Tanish Rashm, Anshu Rai, Punit Kumar

Abstract: This paper outlines the design and implementation of a Personal Finance Management System (PFMS) aimed at helping individuals manage their personal finances effectively. In this digital revolution era, sound financial planning and investment performance are crucial for individuals wanting to achieve long-term financial stability. Therefore, this study presents the design and implementation of an innovative Personal Finance Management and Investment System that allows users to track their incomes, expenditures, and individual investment portfolios and receive intelligent, data-driven personal finance recommendations. The System includes a modern web-based platform utilizing React.js for a complete user-experience interface, Node.js and Express.js for a robust backend service platform, and MongoDB for highly flexible data storage. The application uses machine learning capabilities, powered by Python algorithms to analyze user financial-related activities to propose heretofore unimaginable efficiency in budgeting and a variety of investment options. Finally, to give users value add insights, portfolios can include transaction monitoring, creating financial objectives, tax implications, and investment optimization through graphical dashboards. The proposed solution aims to increase financial literacy; develop saving behaviours with discipline; and a well-informed investment decision set; particularly for young earners, and those at post-secondary institutions.Along with providing instant feedback on financial activity, the system prioritizes usability, with a simple, easy-to-use interface that reduces the complexity normally present in financial programs. Through functionality, accessibility, and data-based insights, the PFMS will be an overall and useful tool for personal financial planning and management.

Development And Validation Of Sim Science

Authors: Gerieliza C. Paano, Louchil A. Cajate

Abstract: This research presents the development and validation of a Supplemental Instructional Material (SIM) in Science for Grade 6, specifically focused on the Biology component of the curriculum. Prompted by the pressing need for contextually relevant and pedagogically sound instructional resources, especially in light of challenges experienced during the COVID-19 pandemic, the study employed a descriptive-developmental design. The SIM was evaluated by science education experts and top-performing students from elementary schools within the Borongan City Division, using established validation criteria such as usability, consistency, clarity of objectives, content quality, curriculum alignment, presentation, and evaluative effectiveness. Quantitative analysis utilizing weighted mean and paired t-tests revealed high levels of validity across all dimensions assessed. The results affirm the material’s potential as a quality-assured learning tool that enhances concept retention and engagement in science learning. This study underscores the importance of localized, research-based instructional materials in improving science education outcomes.

An Overview Of Autonomous Vehicle Sensor

Authors: Tejes theethan M, Akshaya R, Merlin Shiny j, Dharani M

Abstract: This work is the structure of an autonomous driving system. This paper aims to determine the current state of autonomous vehicles, their potential impacts, and the necessary preparation for smart urban mobility. Autonomous refers to the movement or the work done on its own. Autonomous driving systems are divided into several ways, such as Autonomous under- water vehicles, Autonomous airborne vehicles, and Autonomous land vehicles. The potential benefits of lane autonomous vehicles are to describe the importance of navigation algorithms, speed control methods, adoption factors, and the increased infrastruc- ture needs for Connected autonomous vehicles’ integration. The major key elements are based on sensors, navigation, radar, planning techniques, communication, and software. The results of this research have important implications for future research and the framework of autonomous vehicle technologies in road trans- portation. Index Terms—autonomous driving, sensor, RADAR, navigation, software

DOI: 10.61137/ijsret.vol.11.issue3.142

“Traffic Light Timing Optimization Using Websters Formula: Graphical Representation”

Authors: Priyanka Verma, Garima Singh, Assistant Professor Pooja Sharma

Abstract: Traffic congestion at signalized intersections is a critical issue in urban areas, leading to increased travel time, fuel consumption, and environmental pollution. This study presents an optimized traffic signal timing plan for Vyapam Square, Bhopal, using Webster’s formula, a widely recognized method for minimizing delays at signalized intersections. The research involves field data collection, including traffic volume counts, saturation flow rates, and existing signal timings. Using this data, the optimal cycle length and green time allocation for each phase are computed, ensuring a balanced distribution of green time while minimizing average vehicle delay. A graphical representation of traffic flow versus delay is provided to visualize the efficiency improvements before and after optimization.

Educational And Vocational Interests In Relation To Academic Achievements Of Secondary School

Authors: Sonali Bahuguna, Professor Indu Sharma

Abstract: This research examines the connection between educational and vocational interests and the academic performance of secondary school students in Delhi. Considering the recent inclusion of vocational courses in more than 800 government schools as part of the samagra shiksha scheme, this study examines the correlation between students’ interests and their academic achievements. The study employs a stratified random sample of 500 students from various socio-economic and institutional backgrounds, utilizing standardized interest inventories and academic data analysis. The findings indicate a strong positive relationship between educational and vocational interests and academic performance, with vocational interests having a greater predictive power. This supports the belief that incorporating student interests into educational content can enhance academic engagement and achievement.

Study On Performance Of Self-Compacting Concrete Using Scba And Ggbs For Sustainable Construction

Authors: Shankar.K

Abstract: Concrete is the most widely used construction material in the world, and its production is responsible for a significant amount of CO2 emissions, making it a major contributor to global warming. Selfcompacting concrete (SCC) is a type of concrete that can flow under its own weight and fill all the spaces in the formwork without the need for external vibration, which makes it more sustainable compared to traditional concrete. In this study, the performance of SCC using Sugarcane bagasse ash (SCBA) and Ground granulated blast furnace slag (GGBS) as mineral admixtures was investigated for sustainable construction. The study focused on determining the optimum percentages of both SCBA and GGBS to produce SCC with enhanced properties. The SCC mix with SCBA10 GGBS20 achieved a compressive strength, which is significantly higher than the control mix without any mineral admixtures. The flexural strength and tensile strength of SCC mixes with SCBA10 GGBS20 were also higher than the control mix. In terms of durability, the SCC mixes with SCBA10 GGBS20 exhibited better resistance to water penetration, chloride ion penetration, and acid attack compared to the control mix. The UPV test results showed that SCC mixes with SCBA10 GGBS20 had a more uniform and dense structure, which indicates better overall durability. The study is aligned with Sustainable Development Goal 12 (SDG 12) of the United Nations, which aims to ensure sustainable consumption and production patterns. The optimal mix of SCBA10 GGBS20 can lead to the production of high- performance SCC, which is crucial for sustainable construction practices. In conclusion, this study demonstrates the feasibility of using SCBA and GGBS as mineral admixtures in SCC production to enhance its performance and sustainability. The study’s findings provide valuable insights for researchers, engineers, and construction professionals to develop sustainable and costeffective concrete mixes for construction projects.

AI-Powered Symptom Analysis: An Intelligent Health Diagnosis Application

Authors: Y Kushi Reddy, Yallamanchi Himabindu, Anish NC, CV Anusha Reddy, S Harshit Sai,

Abstract: In recent years, the integration of artificial intelligence (AI) into healthcare has enabled innovative approaches for early disease detection and diagnosis. This paper presents the design and development of an AI-powered mobile application that performs preliminary health diagnosis based on user-reported symptoms. The proposed system utilizes machine learning models trained on verified medical datasets to identify possible health conditions from input symptoms, aiming to assist users in seeking timely medical consultation. The application is built using Python, TensorFlow, and a Flask-based backend, with a simple and interactive user interface. The system also emphasizes user privacy and data security. Testing demonstrates the model’s potential to deliver reliable symptom-based predictions, thereby offering a scalable and accessible solution to basic health assessment. This project showcases how AI technologies can be effectively applied in the medical domain to bridge gaps in early diagnosis and promote preventive healthcare.

DOI: http://doi.org/

Design And Testing Of An AI-Based, Terrain-Adaptive Plug-and-Play Energy Optimization Module For Electric Two-Wheelers

Authors: Anay Sunilkumar Pandya

Abstract: This paper presents the conceptual design and testing of an AI-enhanced, terrain-adaptive energy optimization module for electric two-wheelers. Unlike traditional plug-and-play extenders, this system uses a combination of gyroscopic sensors and machine learning to predict driver behavior and road conditions, optimizing power delivery accordingly. Simulated testing shows potential range improvements of up to 38% while maintaining battery longevity. The innovation is particularly suited for urban EV users in mixed-terrain environments. The invention is novel and under consideration for intellectual property protection.

Steady-State Stability Improvement With Incorporation Of SVC And Additional Transmission Line Using Synchronous Power Coefficient.

Authors: Ogundare, Adaramola, Raji, Raji, Ajenikoko, Adebeshin, Onot

Abstract: Every power system comprises many generators that are connected in parallel. For the system to operate in steady-state stability, all the generators must run synchronously. If any of the connected generators loses synchronism, system stability is lost, and voltage collapse may occur. To avoid this situation, steady-state stability (SSS), which involves voltage stability and synchronisation of generators, must be monitored. This paper, therefore, focuses on the SSS using the 6-bus IEEE test network and the Nigerian 30-bus, 330 kV grid network as case studies. Power-flow analysis was carried out for the case studies. Static var compensator (SVC) and additional parallel transmission lines were used to carry out voltage improvement for each network. The use of SVC for both IEEE and Nigerian networks indicates better voltage compensation than using transmission line enhancement, but the reverse is true for power loss reduction. The power losses in the 6-bus IEEE for original and improved networks with SVC and additional transmission lines are 1.8 %, 1.6 %. and 1.2 % respectively. At the same time, those of the Nigerian 30-bus, 330 kV network are 4.3%, 3.7%, 3.10%, respectively. Synchronous Power Coefficient (SPC) was used to carry out SSS by considering load additions in steps of 20% to the original and modified networks. SSS of the modified network with SVC and the original network were approximately the same. In contrast, the SSS was improved for the networks modified with additional transmission lines. Since SSS depends on the system inertia during load variation, the inertia of the network modified with the transmission lines is improved, while SVC does not exhibit noticeable inertia properties.

Crime Hotspot Application: An Interactive Approach For Analyzing Crimes Against Women In India

Authors: Ms. Neekita Singh, Dr.Jasbir Kaur, Mrs.Sandhya Thakkar

Abstract: This paper presents a comprehensive framework combining data science, geospatial analysis, and interactive visualizations to study crimes against women in India. Analyzing crime trends includes three key components: using data science, an interactive Power BI dashboard visualization [6], and a Python-based crime hotspot mapping application using Streamlit. The crime hotspot app allows users to search for any location in India and view crime data displayed on a map, potentially aiding in crime prevention by providing real- time awareness [5]. By integrating these tools, the framework offers a multi-faceted approach to crime analysis, enabling deeper insights into spatial and temporal crime patterns. The study aims to assist policymakers, law enforcement, and the public in understanding and mitigating crime.

DOI: http://doi.org/ijsret.vol.11.issue3.147

A Novel Fuzzy Logic Controller For Peak Power Tracking In Solar Energy Harvesting

Authors: P.Lavanya, Bibhuti Bhusan Rath, A. Lashya, K. Kirankumar, B. Likitha

Abstract: Ensuring consistent and efficient energy harvesting from solar photovoltaic (PV) systems remains a challenge due to unpredictable environmental conditions. To address this, a hybrid Maximum Power Point Tracking (MPPT) technique is presented, combining a conventional perturb-and-adjust method with fuzzy logic-based control. This approach dynamically modifies the control signal for a step-up converter, allowing the PV array to maintain optimal power output. The system’s performance was analysed using MATLAB/Simulink under both stable and varying sunlight conditions. Results confirm that the hybrid controller delivers better efficiency, quicker response to changes, and reduced output fluctuations when compared to traditional MPPT strategies. These findings highlight its potential for integration into intelligent solar energy systems.

DOI: http://doi.org/ijsret.vol.11.issue3.148

Advanced Image Super-Resolution Using Deep Learning

Authors: Konka Kishan, Kondoju Prem Kumar, Shaik Feroz Pasha, Ajmeera Sagar Naik

Abstract: The recent growth of Deep learning has transformed the area of Image Super-Resolution (ISR) which enables the reconstruction of high-quality images from low-resolution images. The improvement of low quality images to high-quality resolution images. The complete guide provides an in-depth overview of the advanced methodologies and applications of ISR using deep learning. We discuss the basic of ISR, models and algorithms of ISR namely, Generative Adversarial Networks (GANs), Convolutional Neural Networks (CNNs) and attention-based models. We further discuss the applications of ISR such as Medical Imaging, Surveillance, Astronomy, and Autonomous driving. This compiled resource is intended to be a one-stop reference guide to the intricacies of ISR using deep learning and it’s many prospects for real-world applications for researchers, practitioners, and students.

DOI: 10.61137/ijsret.vol.11.issue3.149

 

Prediction of Fruit Diseases by Fruit Image Analysis Using Hyperspectral Imaging and Deep Learning Techniques

Authors: Jameer Shaikh, Dr. Usha B Shete, Dr. A. A. Khan, Dr. R. S. Deshpande

Abstract: Early and accurate detection of fruit diseases is critical for minimizing crop losses and ensuring food security. This study in- troduces a novel automated diagnostic framework that leverages hyperspectral imaging combined with deep convolutional neural networks to detect and classify common diseases affecting apples, including blotch, rot, and scab. By analyzing spectral reflectance patterns from 360 nm to 1000 nm, the proposed method identifies subtle biochemical changes in fruit tissues before visual symp- toms manifest. Extensive laboratory experiments demonstrate that the system achieves an overall classification accuracy of 93.7%, outperforming traditional RGB-based image analysis techniques. Furthermore, field trials conducted in commercial orchards validate the robustness and real-world applicability of the system, revealing a 28% reduction in false positive detections and a 35–40% potential decrease in yield losses through timely intervention. The integration of hyperspectral data with deep learning enables a cost-effective, non-destructive, and scalable solution for precision agriculture, supporting proactive crop management and sustainable farming practices.

 

 

Deep Learning Vs. Traditional Machine Learning: A Performance Analysis

Authors: Vikash Sharma, Dr. Ramesh Patil

Abstract: The advancement of artificial intelligence (AI) has given rise to two major approaches: traditional machine learning (ML) and deep learning (DL). While traditional ML relies on feature engineering and structured learning approaches, deep learning automates feature extraction through artificial neural networks. This paper explores the differences between these methods, compares their performance across domains such as image recognition, natural language processing, and financial forecasting, and evaluates their advantages and limitations. Experimental results and literature reviews indicate that deep learning excels in handling large datasets and complex patterns, whereas traditional ML is more suitable for smaller datasets with structured features.

DOI: http://doi.org/

 

 

Challenges Faced By Defence Armed Forces During Surgical Strikes And The Role Of AI In Enhancing Tactical Precision

Authors: Mohit Kumar

Abstract: Surgical strikes are high- precision military operation designed to neutralize specific targets while mimizing collateral damage. However, these operations are fraught with challenges such as intelligence inaccuracies, hostile terrain, real- time coordination issues, and political sensitivities. The integration of Artificial intelligence (AI) offers a transformative solution to these challenges. This paper explores the multifaceted challenges encountered during surgical strikes and examines the roles of AI in enhancing tactical precision and decision- making capabilities.

EXPERIMENTAL AND ANALYTICAL STUDY ON CFST COLUMNS BY REPLACING REINFORCEMENT WITH GI WELDED WIRE MESH AND CEMENT WITH CERAMIC WASTE POWDER

Authors: Mohanprasath. , Student-M.E, Structural engineering

Abstract: In today’s world, concrete serves a crucial role in the development of every infrastructure and people are also starting to migrate from rural to urban areas. This situation necessitates the development of infrastructure in the urban areas, mostly in the vertical direction form of high-rise structures that utilize enormous columns, which take up more room and have a less appealing aspect. Concrete Filled Steel Tubular (CFST) columns are one of several ways developed by the building industry to address these issues. Huge areas may be used since CFST Columns minimize the size of the large columns. CFST columns are becoming common in construction, particularly for high-rise structures. The structural performance of concrete-filled CFST columns are discussed in many literatures, while CFST columns utilizing ceramic waste powder and glass fiber with replacement of reinforcement is not mentioned in any of the literatures. This study is about the performance of CFST columns with ceramic waste powder replacing cement and GI welded wire mesh replacing reinforcement and adding the glass fiber. The properties of the materials used in CFST columns is studied.

DOI:

 

Wireless Electric Vehicle Charging: Technologies, Standards, And Future Prospects

Authors: Dr. Bincy K Jose

Abstract: Wireless Electric Vehicle (EV) charging offers a seamless and efficient alternative to conventional plug-in systems, enabling user convenience, automation, and compatibility with dynamic and autonomous mobility. As the global transition to electrified transportation intensifies, the need for smart, contactless energy delivery solutions becomes imperative. This paper presents a comprehensive review of wireless EV charging technologies, focusing on power transfer methods, system design, control strategies, safety standards, and real-world applications. It integrates insights from academic literature and a student-developed prototype to explore the current state, challenges, and future direction of wireless EV charging infrastructure.

DOI: http://doi.org/ijsret.vol.11.issue3.150

From Shinkansen To Spacecraft Propulsion: The Role Of Superconductivity And Electromagnetism In Modern Engineering

Authors: Tanush Nayan Shenai

Abstract: Superconductivity and electromagnetism are two groundbreaking technologies that are reshaping the future of engineering across key sectors. Superconductivity, which enables the conduction of electricity without resistance at very low temperatures, is driving breakthroughs in energy efficiency and magnetic field manipulation. When combined with electromagnetic and magnetic levitation (maglev) technologies, it allows for the creation of frictionless and powerful systems that push the boundaries of speed, efficiency, and sustainability. In transportation, maglev trains are facilitating unprecedented high-speed travel, offering faster, quieter, and more environmentally friendly transportation. In aerospace, these technologies are transforming spacecraft launches, enhancing propulsion and control. Additionally, in the defense sector, electromagnetic technology powers railguns, electromagnetic aircraft launch systems (EMALS), and other advanced weapons, improving defense and attack capabilities. This paper explores the specific technologies of superconductivity and electromagnetism, examining their applications in transportation, aerospace, and military sectors. By highlighting recent advancements and addressing ongoing challenges, it reveals the potential and feasibility of these technologies in shaping the future

DOI: https://doi.org/10.5281/zenodo.15709797

Significance Of Explainable Artificial Intelligence On Designing Of Microstrip Patch Antenna – A Review

Authors: Shaunak Das, Saumyajit Maulik, Subhodeep Sengupta, Shubhajit Mridha, Sagnik Banerjee, Supriyo Mondal, Anurima Majumdar, Antara Ghosal, Koushik Pal

Abstract: Explainable Artificial Intelligence (XAI) is now quickly becoming the game changer which makes it easier to get the answer of why the complex engineering models do what they do. Explainable Artificial Intelligence (XAI) refers to the AI systems which are designed to provide clear and understandable outcomes of their decisions, predictions and actions. XAI aims to make the Artificial Intelligence system more transparent and trustworthy for the users. This study aims to dive into how using XAI can be a better and efficient option for designing and implementing the microstrip patch antenna. Microstrip patch antennas are good options for wireless network design and implementation because they are small in size and cost effective. The traditional methods of designing those antennas tend to depend on the guess and round after round of try and check which produces delays and keeps us detached from what’s going on with the trade-offs in the designing process. By using the XAI into the design of microstrip patch antennas can make a huge impact on the optimization of design by providing us clear and interpretable insights into the design parameters and their impact on the working performance of the antenna. By applying XAI techniques such as feature importance analysis, feature selection, rule based systems designers can get a deeper understanding about the design parameters, rules and regulations

DOI: http://doi.org/

 

 

EXPERIMENTAL AND ANALYTICAL STUDY ON CFST COLUMNS BY REPLACING REINFORCEMENT WITH GI WELDED WIRE MESH AND CEMENT WITH CERAMIC WASTE POWDER

Authors: Mohanprasath. , Student-M.E, Structural engineering

Abstract: In today’s world, concrete serves a crucial role in the development of every infrastructure and people are also starting to migrate from rural to urban areas. This situation necessitates the development of infrastructure in the urban areas, mostly in the vertical direction form of high-rise structures that utilize enormous columns, which take up more room and have a less appealing aspect. Concrete Filled Steel Tubular (CFST) columns are one of several ways developed by the building industry to address these issues. Huge areas may be used since CFST Columns minimize the size of the large columns. CFST columns are becoming common in construction, particularly for high-rise structures. The structural performance of concrete-filled CFST columns are discussed in many literatures, while CFST columns utilizing ceramic waste powder and glass fiber with replacement of reinforcement is not mentioned in any of the literatures. This study is about the performance of CFST columns with ceramic waste powder replacing cement and GI welded wire mesh replacing reinforcement and adding the glass fiber. The properties of the materials used in CFST columns is studied.

DOI:

 

Handwritten Text Into A Word Document Using Computer Vision And Deep Learning

Authors: Assistant Professor P. Kamakshi Thai, A. Pruthvi, R. Akshith, V. Stephen Moses

 

Abstract: This project presents a deep learning-based system for converting handwritten notes into fully editable Microsoft Word documents. Instead of relying on traditional Convolutional Neural Networks (CNNs) and Bidirectional Long Short-Term Memory (BiLSTM) networks, this approach leverages Microsoft’s TrOCR model, a transformer-based OCR system designed for handwritten text recognition. The use of TrOCR, pre-trained and accessible via Hugging Face, significantly enhances transcription accuracy and reduces the complexity of training custom models. The process begins with image preprocessing to refine input quality, ensuring optimal text extraction. TrOCR’s powerful transformer architecture then deciphers handwritten text by leveraging attention mechanisms to model contextual dependencies within sequences. Following initial transcription, a post-processing module performs spell and grammar corrections, refining the extracted text for improved readability. The final structured output is formatted and automatically saved as a .docx file, enabling seamless integration with document generation tools. By employing state-of-the-art transformer-based OCR, this system achieves high readability and reliability, making it suitable for applications in education, legal documentation, healthcare records, and general document imaging. The transition to TrOCR eliminates the need for complex recurrent architectures, ensuring a streamlined and efficient recognition pipeline

DOI: 10.61137/ijsret.vol.11.issue3.151

 

Preparation Of Tradescantia Pallida Mediated Calcium Carbonate Nanoparticles And Their Activity Against Hela Cell Lines

Authors: Akshita verma

 

Abstract: Purpose: To make calcium carbonate nanoparticles (CaCO₃NPs) and test their fluorescent and cytotoxic properties utilising Tradescantia pallida (Commelinaceae). Method: T. pallida aqueous leaf extract is used to make CaCO₃ NPs according to a straightforward technique (TPALE). Determine their crystalline nature and functional groups, Fourier transform infrared spectroscopy (FTIR) investigations are used. Photoluminescence characteristics of CaCO₃ Nanoparticles are evaluated using fluorescence spectroscopy. Following confirmation of CaCO₃ NP synthesis, the 3-(4,5-dimethylthiazol-2-yl)-2,5diphenyltetrazolium bromide (MTT) assay is used to assess cytotoxicity against HeLa cell line. Conclusion: On the basis of TPALE, a simple method for synthesising CaCO₃ NPs has been successfully established. The generated CaCO₃ NPs have good luminescent characteristics and are cytotoxic to a cancer cell line.

DOI: http://doi.org/ijsret.vol.11.issue3.152

 

AI Enabled Emergency Response Optimization System With Smart Contract In Healthcare

Authors: Shubhangi Murukate, Professor Dr. Ayesha Siddiqui

Abstract: Healthcare emergencies require rapid, coordi- nated, and intelligent responses. This paper proposes an AI- enabled emergency response optimization system integrated with blockchain-based smart contracts to enhance efficiency, transparency, and automation in critical healthcare scenarios. The system leverages machine learning for incident prediction and prioritization, while smart contracts ensure secure, real- time collaboration among hospitals, ambulances, and government agencies. Experimental simulations show improved response time and reduced resource allocation errors. The proposed system can significantly strengthen emergency preparedness and crisis response in healthcare.

AI Enabled Emergency Response Optimization System With Smart Contract In Healthcare

Authors: Shubhangi Murukate, Professor Dr. Ayesha Siddiqui

Abstract: Healthcare emergencies require rapid, coordi- nated, and intelligent responses. This paper proposes an AI- enabled emergency response optimization system integrated with blockchain-based smart contracts to enhance efficiency, transparency, and automation in critical healthcare scenarios. The system leverages machine learning for incident prediction and prioritization, while smart contracts ensure secure, real- time collaboration among hospitals, ambulances, and government agencies. Experimental simulations show improved response time and reduced resource allocation errors. The proposed system can significantly strengthen emergency preparedness and crisis response in healthcare.

An Analysis On Global Superstore

Authors: NIKITA RATHORE

 

 

Abstract: Global superstores have emerged as a cornerstone of the modern retail industry, offering diverse products and competitive prices that cater to a wide consumer base. This study examines the operations, challenges, and societal impacts of global superstores, focusing on their role in international commerce and their influence on local economies. By employing a mixed-methods approach, including customer surveys, interviews with industry stakeholders, and secondary data analysis, the research provides a comprehensive understanding of superstore dynamics. Key findings highlight the advantages of enhanced consumer access and operational efficiency, juxtaposed with concerns about sustainability and labor practices. The study underscores the need for strategies that balance profitability with social and environmental responsibilities, contributing valuable insights for academia, practitioners, and policymakers in navigating the evolving retail landscape

DOI: http://doi.org/

Analysis Of Microstructural And Mechanical Properties Of MS1018 Steel Metal Using Friction And Arc (TIG) Welding Operations And Their Comparison_174

Authors: Mahboob Ansari, Dr. Shahnwaz Alam, Dr.Mohd Faizan Hasan

Abstract: The welding of metals is a critical process in various industries, and the choice of welding technique can significantly influence the quality of the weld. This study presents a comparative analysis of microstructural and mechanical properties of MS1018 steel welded using Friction Welding (FW) and Tungsten Inert Gas (TIG) Welding operations. The MS1018 steel, a widely used medium carbon steel, was chosen for its applications in construction and automotive industries. The study evaluates the influence of welding processes on the microstructure, hardness, tensile strength, and impact toughness of the welds. The research concludes by comparing the outcomes of both welding methods and discussing their advantages and limitations in terms of welding quality, performance, and suitability for specific applications.

Securehaven-Enhancing Gated Community Management With Iot

Authors: Vadla Aakash, Gummadi Manideep Reddy, Dr.K.Prem Kumar Associate, Dhareddy Rohith Reddy,, Varkuti Nitish Reddy

 

 

Abstract: Secure Haven – Enhancing Gated Community Management with IoT is an innovative initiative that utilizes advanced Internet of Things (IoT) technologies to improve the overall management and functionality of modern gated communities. By integrating a variety of IoT devices, including sensors and controllers, the system enables real- time monitoring and control of key community operations. This leads to greater efficiency, convenience, and safety for residents. These devices gather critical data related to energy consumption, environmental conditions, occupancy, and security. The collected data is processed using sophisticated algorithms and machine learning techniques to optimize community performance and decision-making. The project focuses on four main areas: energy management, environmental control, security and access control, and predictive maintenance. Energy efficiency is achieved through smart meters and intelligent lighting systems that help reduce energy waste and cut costs. The incorporation of renewable energy sources also supports sustainability. Environmental comfort is maintained using DHT11 sensors that monitor temperature and humidity, ensuring ideal indoor conditions. For security, RFID-based access systems are employed to allow secure and automated entry into the premises, while smart surveillance and real- time alert mechanisms provide an added layer of protection. Predictive maintenance is enabled by IoT-based monitoring systems, such as water level sensors, which facilitate continuous tracking of equipment performance and help prevent failures through early detection.Overall, Secure Haven offers a smart, secure, and sustainable solution for managing gated communities by leveraging the power of IoT to create a more connected and responsive living environment.

DOI: http://doi.org/

 

 

Machine Learning In Material Science For Microstructural Analysis, Property Prediction, And Alloy Design

Authors: Assistant professor Benasir Begam.F, Agalya.A

Abstract: Machine learning (ML) is transforming material science by shifting the traditional empirical and simulation-driven approaches to a data-centric paradigm. This review presents an integrated overview of how ML methods are applied in microstructure recognition, material property prediction, and alloy design. We discuss key learning paradigms such as supervised, unsupervised, and deep learning, with emphasis on convolutional neural networks (CNNs), autoencoders, and generative models. Representative studies are cited to illustrate applications in predictive modeling and image-based analysis. We highlight challenges related to data scarcity, model interpretability, and integration of physical principles. The review concludes with future directions, including autonomous materials discovery platforms and hybrid physics-informed ML models.

 

 

DEVELOPMENT SCOPE OF GENERATIVE AI APPLICATIONS AND THEIR ENHANCEMENTS

Authors: Dr. V.K. Srivastava, Ms. Aarti

 

 

Abstract: Generative AI is a huge step forward in technology that allows computers produce text, visuals, sounds, and even complex designs. This technology comes up with new ideas in a lot of different fields by using cutting-edge models like Generative Adversarial Networks (GANs), Large Language Models (LLMs), and diffusion models. This article discusses about how generative AI apps have changed over time and how they might be useful in the arts, business, healthcare, education, and engineering. The study found that generative AI makes creative work easier, speeds up the design process, personalises learning, and improves diagnoses. But generative AI also raises moral challenges, privacy concerns, biases, and areas of the law that aren’t clear. The paper talks about these issues and how to fix them, highlighting how important it is for people from different professions to work together to build AI systems that are strong, fair, and open. It also talks about how to make generative AI more aware, adaptable, and accurate. The study highlights how crucial it is to put laws and morals in place so that as many people as possible can utilise AI in a responsible way. Some of the goals for the future are to make AI easier to use, rules easier to obey, and to promote innovation that is culturally and socially diverse. Generative AI can solve these difficulties and help firms in a lot of different industries be more creative, productive, and inventive.

DOI: http://doi.org/

 

 

Securehaven

Authors: Dr.K.Prem Kumar, Dhareddy Rohith Reddy, Varkuti Nitish Reddy, Gummadi Manideep Reddy, Vadla Aakash

 

 

Abstract: Secure Haven – Enhancing Gated Community Management with IoT is an innovative initiative that utilizes advanced Internet of Things (IoT) technologies to improve the overall management and functionality of modern gated communities. By integrating a variety of IoT devices, including sensors and controllers, the system enables real- time monitoring and control of key community operations. This leads to greater efficiency, convenience, and safety for residents. These devices gather critical data related to energy consumption, environmental conditions, occupancy, and security. The collected data is processed using sophisticated algorithms and machine learning techniques to optimize community performance and decision-making. The project focuses on four main areas: energy management, environmental control, security and access control, and predictive maintenance. Energy efficiency is achieved through smart meters and intelligent lighting systems that help reduce energy waste and cut costs. The incorporation of renewable energy sources also supports sustainability. Environmental comfort is maintained using DHT11 sensors that monitor temperature and humidity, ensuring ideal indoor conditions. For security, RFID-based access systems are employed to allow secure and automated entry into the premises, while smart surveillance and real- time alert mechanisms provide an added layer of protection. Predictive maintenance is enabled by IoT-based monitoring systems, such as water level sensors, which facilitate continuous tracking of equipment performance and help prevent failures through early detection.Overall, Secure Haven offers a smart, secure, and sustainable solution for managing gated communities by leveraging the power of IoT to create a more connected and responsive living environment.

DOI: http://doi.org/

 

 

Evacuation Strategies During Fire In Case Of Auditorium

Authors: Anutosh Bajpai, Professor (Dr.) V.K. Paull

Abstract: Fire safety in auditoriums is a critical concern due to the high occupancy and unique spatial configurations that can hinder efficient evacuation during emergencies. This dissertation, titled Evacuation Strategies in Case of Fire in Auditoriums, aims to address the gap in understanding fire behavior and evacuation performance by integrating advanced simulation tools, PyroSim and Pathfinder, to analyze and improve evacuation strategies. A case study of an auditorium in New Delhi was conducted, focusing on four fire scenarios (circulation area, seating area, wall, and stage) under two material conditions: existing materials and code-compliant materials. The study revealed that existing materials, such as polyester curtains, untreated foam seating, and nylon carpets, significantly contribute to fire spread, smoke generation, and reduced visibility, thereby increasing evacuation times. Code-compliant materials, including fire-treated fabrics, non-combustible paneling, and fire-resistant carpets, demonstrated substantial improvements, reducing evacuation times by up to 30% and delaying smoke visibility loss by over 100 seconds in most scenarios. The stage area emerged as the most critical zone due to its highly flammable materials, requiring urgent intervention through material upgrades and enhanced suppression systems. The research highlights the importance of material selection, compliance with fire safety codes, and simulation-driven design improvements in mitigating fire risks. While limitations such as reliance on hypothetical data and the exclusion of behavioral factors were acknowledged, the findings provide actionable recommendations for policy reforms, material upgrades, and egress design enhancements. This study contributes to the evolving discourse on fire safety, emphasizing the need for a comprehensive, proactive approach to ensure occupant protection in public assembly spaces.

DOI: https://doi.org/10.5281/zenodo.15682340

Factors Related To The Science Academic Performance Of Grade V Pupils

Authors: Ruselle H. Paano, Jovilyn D. Apigo

Abstract: This study investigates the various factors that influence the academic performance of Grade V pupils in Science. Recognizing the crucial role of science education in shaping critical thinking and problem-solving skills, the research aims to identify both internal and external factors that significantly affect student achievement. The study focuses on variables such as students’ study habits, interest in science, classroom environment, teacher competency, parental involvement, and access to learning resources. Using a quantitative descriptive-correlational design, data were gathered through surveys and academic records from a representative sample of Grade V pupils in selected schools. Statistical analysis revealed that student interest and motivation, teacher teaching strategies, and parental support had the most significant correlation with science performance. Meanwhile, socio-economic status and availability of learning materials also showed notable influence. The findings suggest that improving science performance requires a holistic approach that involves not only curriculum improvements but also increased parental engagement and support for teacher development. The study provides recommendations for educators, administrators, and policymakers to enhance science instruction at the elementary level.

COLLABRIX : REAL TIME CODE EDITOR

Authors: Prof. Dr.Poornima Tyagi, Aditansh Rai, Khushi Gupta, Sohaib Ahmad, Anurag Paliwal

 

 

Abstract:The world of Internet is growing rapidly, many applications that previously created on the desktop start moving to the web. Many applications could be accessed anytime and anywhere easily using Internet. Developers need tools to create their applications, one of them named code editor. The purpose of this research is to design and develop a real-time code editor application using web socket technology to help users collaborate while working on the project. This application provides a feature where users can collaborate on a project in real-time. The authors using analysis methodology which conducting on a study of the current code editor applications, distributing questionnaires and conducting on literature study. Collabrix is a web application that provides workspace to writing, perform, display the results of the code through the terminal, and collaborate with other users in real- time. The application main features are providing workspace to make, execute and build the source code, real-time collaboration, chat, and build the terminal. This application supports C, C++, and python programming languages.

DOI: http://doi.org/

 

 

Securehaven

Authors: Associate Professor Dr.K.Prem Kumar,, Dhareddy Rohith Reddy, Varkuti Nitish Reddy, Gummadi Manideep Reddy, Vadla Aakash

 

 

Abstract: Secure Haven – Enhancing Gated Community Management with IoT is an innovative initiative that utilizes advanced Internet of Things (IoT) technologies to improve the overall management and functionality of modern gated communities. By integrating a variety of IoT devices, including sensors and controllers, the system enables real- time monitoring and control of key community operations. This leads to greater efficiency, convenience, and safety for residents. These devices gather critical data related to energy consumption, environmental conditions, occupancy, and security. The collected data is processed using sophisticated algorithms and machine learning techniques to optimize community performance and decision-making. The project focuses on four main areas: energy management, environmental control, security and access control, and predictive maintenance. Energy efficiency is achieved through smart meters and intelligent lighting systems that help reduce energy waste and cut costs. The incorporation of renewable energy sources also supports sustainability. Environmental comfort is maintained using DHT11 sensors that monitor temperature and humidity, ensuring ideal indoor conditions. For security, RFID-based access systems are employed to allow secure and automated entry into the premises, while smart surveillance and real- time alert mechanisms provide an added layer of protection. Predictive maintenance is enabled by IoT-based monitoring systems, such as water level sensors, which facilitate continuous tracking of equipment performance and help.prevent failures through early detection.Overall, Secure Haven offers a smart, secure, and sustainable solution for managing gated communities by leveraging the power of IoT to create a more connected and responsive living environment

DOI: http://doi.org/

 

 

Securehaven

Authors: Associate Professor Dr.K.Prem Kumar,, Dhareddy Rohith Reddy, Varkuti Nitish Reddy, Gummadi Manideep Reddy, Vadla Aakash

 

 

Abstract: Secure Haven – Enhancing Gated Community Management with IoT is an innovative initiative that utilizes advanced Internet of Things (IoT) technologies to improve the overall management and functionality of modern gated communities. By integrating a variety of IoT devices, including sensors and controllers, the system enables real- time monitoring and control of key community operations. This leads to greater efficiency, convenience, and safety for residents. These devices gather critical data related to energy consumption, environmental conditions, occupancy, and security. The collected data is processed using sophisticated algorithms and machine learning techniques to optimize community performance and decision-making. The project focuses on four main areas: energy management, environmental control, security and access control, and predictive maintenance. Energy efficiency is achieved through smart meters and intelligent lighting systems that help reduce energy waste and cut costs. The incorporation of renewable energy sources also supports sustainability. Environmental comfort is maintained using DHT11 sensors that monitor temperature and humidity, ensuring ideal indoor conditions. For security, RFID-based access systems are employed to allow secure and automated entry into the premises, while smart surveillance and real- time alert mechanisms provide an added layer of protection. Predictive maintenance is enabled by IoT-based monitoring systems, such as water level sensors, which facilitate continuous tracking of equipment performance and help.prevent failures through early detection.Overall, Secure Haven offers a smart, secure, and sustainable solution for managing gated communities by leveraging the power of IoT to create a more connected and responsive living environment.

DOI: http://doi.org/

 

 

A Novel AI-Powered Approach For Detecting And Preventing Facial Exchange Manipulations In Videos

Authors: P.Selvaraj, A Joshua Issac, Dr.S.Shanmuga, M.Bharathi

 

 

Abstract: The increasing advancement of generation of deepfake techniques – especially manipulations involving face-swapping has brought up major concerns related to integrity of online media, data privacy and societal trust. The computer generated videos, created using advanced models can easily replace an individual face with another often fool regular detection tools because changes in lighting, skin tone, facial expressions are so small and hard to notice. Although many AI-based methods have been developed to spot deep fake, most current models still struggle because they only look at single images , don’t consider changes over time or require too much computing power. This research proposes a hybrid deepfake detection framework that leverages the strengths of Convolutional Neural Networks (CNNs) for robust spatial feature extraction and Vision Transformers (ViTs) for capturing temporal and contextual relationships across video frames. The CNN part looks for small changes and edits in the face, while the Vision Transformer looks at a series of frames to catch unusual expressions , movements and facial tone. Together, this combination aims to overcome the challenges posed by diverse and highly realistic face-swap techniques. The system is trained and tested on known datasets like FaceForensics++ and DFDC-Preview, providing a complete way to detect face-swap deep fake. By improving on current methods and looking at both the details in each frame and changes over time, this study helps create a stronger and more flexible deepfake detection system that can handle new and growing threats in visual content.

DOI: http://doi.org/

 

 

Agriculture Marketing and Information System

Authors: Assistant Professor Yamini Warke, Sairam Misal, Tushar Karwar, Nikita Wagh, Aishwarya Sawant

Abstract: Agriculture is vital to India’s global economy and significantly contributes to GDP. As the human population grows, the nation’s agricultural output is crucial in ensuring food security. Climate factors such as temperature, precipitation, soil quality, and fertilizers primarily influence a crop’s yield. The variability of these elements adversely impacts productivity, posing a significant challenge for the agriculture industry to accurately estimate crop yields under fluctuating climatic circumstances. Recently, researchers have used machine learning algorithms to forecast crop yields before actual planting. This research study has introduced a machine learning technique, namely linear regression and multilayer perception, to forecast crop production based on characteristics such as state, district, area, seasons, NPK, pH values, rainfall, temperature, and area. To improve yield, this research study recommends a fertilizer tailored to soil conditions, including NPK levels, soil type, pH, humidity, and moisture. Fuzzy algorithms primarily guide the recommendation of fertilizers.

DOI: http://doi.org/

 

 

Enhanced Image Security Using Classification In Adversarial Machine Learning With AES Based Grey Wolf Algorithm

Authors: Divyarth Rai, Tasneem Jahan

 

Abstract: Traditional image retrieval methods which use plain images suffer security risks in fields like medicine, military, space exploration, stocks and finance. Image classification using adversarial machine learning models are vital for enhancing security and detecting intrusion. This paper attempts to present a comparative study and highlights the potential of most promising models for efficient and effective retrieval with feature learning in image classification tasks. The best approaches can eventually strengthen its impact on the field for further implementation. The various machine learning models which could intercept adversarial attacks are classified with their results and advantages. Across social media websites and recommender systems, malicious advertisements are increasingly popular. The approaches discussed here are robust to classify the advertisement images as malicious or benign. This is a good strategy for ensuring smooth user experience and maintaining user security.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.153

 

Data Leakage Detection and Prevention using Cloud Computing

Authors: Aarti Dengale, Dr. Nagsen Bansod, Dr. A. A. Khan, Dr. R. S. Deshpande

Abstract: Data leakage in cloud environments poses serious threats to data confidentiality, integrity, and availability. This paper proposes a robust system combining Role-Based Access Control (RBAC), watermarking, and anomaly detection to prevent and detect data leakage in real-time. Simulations demon- strateim proved performance in detecting unauthorized access attempts. We present the architecture, algorithms, requirements, and security mechanisms, along with a comprehensive literature survey and experimental results. Additionally, the paper discusses the integration of emerging concepts such as Zero Trust Architecture, Attribute-Based Access Control, and forensic auditing to enhance cloud data security.

 

 

An Effective Vision-Based System For Indian Sign Language Recognition Using Deep Learning

Authors: Professor Dr. Rachna Chavan, Ashish Singh

Abstract: Individuals with hearing and speech impairments rely on Indian Sign Language (ISL) for communication. Despite its importance, ISL lacks broad technological integration, limiting accessibility. This paper presents a vision-based recognition model built using Convolutional Neural Networks (CNNs) to classify static ISL gestures. The system undergoes preprocessing, augmentation, training, and real-time classification. A custom dataset was collected to ensure diversity in hand gestures and backgrounds. Our trained model achieved a classification accuracy of 96.4%, showing its capability to assist in inclusive communication tools.

Sentiment Analysis Of Online Comments Using Machine Learning And Lexicon-Based Techniques: An Integrated Study

Authors: Hari Om, Steven David

Abstract: Social media and review platforms have become key spaces for individuals to voice opinions, shaping trends across sectors like entertainment and business. This study introduces a comprehensive sentiment analysis framework that combines lexicon-based methods, machine learning models, and privacy-conscious data collection practices. Drawing on insights from three notable research works, the proposed approach effectively categorizes movie reviews and general online comments into positive, negative, or neutral sentiments. Emphasis is placed on thorough data preprocessing, accurate classification, and ethical data management, resulting in a practical and adaptable solution for sentiment analysis in real-world applications.

DOI: http://doi.org/

Review on Location and Edge Based Energy Efficient Reliable Approach for Teen Protocol in Wireless Sensore Network

Authors: Deepti Tripathi, Professor Amit Thakur

Abstract: The Wireless sensor networks (WSN) are becoming popular as an emergent requirement for manhood. Although, these networks are developing vary rapidly but, they can be used in approximately all aspects of the life. A thorough analysis of existing protocols was conducted to understand problems of WSN and few evaluation tables have been provided for the review summary of the performance of the protocols according to parameters such that latency, scalability, transmission type, network traffic and energy perception. Components of the WSN have been discussed in detail. Issues and challenges of WSN were discussed. Different energy harvesting resources and technologies have been analyzed.

Review on Assessing Multi Hop Performance of Reactive Routing Protocol in Wireless Sensor Network

Authors: Isha Vyas, Professor Amit Thakur

Abstract: Advances in wireless sensor network (WSN) technology has provided the availability of small and low-cost sensor nodes with capability of sensing various types of physical and environmental conditions, data processing, and wireless communication. Variety of sensing capabilities results in profusion of application areas. However, the characteristics of wireless sensor networks require more effective methods for data forwarding and processing. In WSN, the sensor nodes have a limited transmission range, and their processing and storage capabilities as well as their energy resources are also limited. Routing protocols for wireless sensor networks are responsible for maintaining the routes in the network and have to ensure reliable multi-hop communication under these conditions. In this Review work, we give a survey of routing protocols for Wireless Sensor Network and compare their strengths and limitations.

 

 

AI-Based Smart Water Consumption Monitoring System

Authors: Nikhil Chavan, Dr. Rachna Chavan,, Dr. A. A. Khan, Dr. R. S. Deshpande

Abstract: – Water scarcity is a growing global challenge, making it essential to monitor and optimize water consumption effec- tively. This paper presents an AI-based Smart Water Consump- tion Monitoring System that leverages machine learning and IoT technologies to enhance water management. The system utilizes real-time sensor data, applies predictive algorithms, and generates insights to optimize water usage, reduce waste, and detect anomalies. The proposed system aims to encourage sustainable water consumption practices and prevent potential water-related crises.

SuperAgent : A Scalable Multi-Agent Framework For Autonomous Task Execution Using Large Language Models

Authors: Yash Malsuare, Aryan Purohit, Isha syed, Dr. Maheshwari Birada

Abstract: This paper presents SuperAgent, a novel multi-agent AI framework designed to autonomously handle complex, real-world tasks through intelligent collaboration among dynamic language agents. As the capabilities of large language models (LLMs) continue to advance, there remains a gap in practical deployment frameworks that can translate user intentions into real-world actions with minimal supervision, explainable reasoning, and reliable execution. SuperAgent+ bridges this gap by combining prompt-driven agent generation, transparent multi-step task planning, and API-integrated tool use in a modular architecture that supports human oversight and customization. At the core of SuperAgent+ lies a flexible orchestration engine that dynamically instantiates and manages specialized agents for subtasks such as information retrieval, summarization, decision-making, scheduling, verification, and real-world communication. Users can design and visualize workflows using a drag-and-drop interface, enabling domain experts and non-technical users alike to create autonomous workflows without writing code. The system further integrates a memory layer for context retention, a reasoning logger for traceability, and real-world tool access (e.g., calendars, calls, databases) for execution beyond the digital domain. We evaluate SuperAgent across a variety of tasks such as academic research assistance, enterprise automation, personal productivity planning, and multi-modal content generation. Our results demonstrate improvements in task completion rates, reasoning transparency, and adaptability compared to baseline single-agent and static pipeline systems. This research lays the foundation for future work on fully autonomous AI ecosystems capable of safe, reliable, and cooperative task execution across domains. Furthermore, this research integrates a modular plug-and-play architecture, enabling extensibility for future agents, tools, or models (e.g., vision, audio, or robotic modules). Experimental evaluations indicate substantial gains in task efficiency, traceability, scalability, and user satisfaction, especially in domains such as software development, research summarization, data analysis, and automated reporting. (Stein, Helge Sören and J. Gregoire).

DOI: http://doi.org/

 

 

Comprehensive Study On Wireless Power Transmission (WPT)

Authors: Dr. Rajul Misra, Mr. Saurabh Saxena, Abhishek Singh,, Tushar Chauhan, Anit kumar

Abstract: This report presents a comprehensive study on Wireless Power Transmission (WPT), a groundbreaking technology that facilitates the transfer of electrical energy without the need for physical connectors or wires. The project explores various methodologies, including inductive coupling, resonant inductive coupling, and advanced techniques such as beam forming and UV-assisted wireless charging. The primary objective is to design an efficient WPT system capable of delivering power over varying distances while addressing challenges related to efficiency, range limitations, and safety standards. Through experimental evaluations, the project demonstrates that resonant inductive coupling enhances energy transfer efficiency and extends operational range compared to traditional methods. Additionally, the integration of innovative techniques like quasi-static cavity resonance allows for simultaneous charging of multiple devices. The findings indicate that while WPT systems hold significant promise for applications in consumer electronics, electric vehicles, and medical devices, ongoing research is essential to overcome existing challenges and facilitate widespread adoption. This study contributes valuable insights into the development of wireless energy transmission technologies and their potential impact on various industries

DOI: http://doi.org/

Theoretical Foundations And Optimization Techniques For Learning Mathematics In Data Science And Machine Learning.

Authors: Dr.Pranesh Kulkarni ., Assistant Professor Department of Mathematics

Abstract: Mathematics is a fundamental component of Data Science, providing the theoretical foundations for many data analysis and Machine learning techniques. A breakdown of the fundamental math field required for data Science, Linear Algebra, Calculus, and Probability Theory. Through mathematics we can learn data analysis and visualization in this we learn plotting, charting and data storytelling.in this Article we discussed structuring and designing of mathematics in data science this provides a Comprehensive framework for understanding the mathematical foundations. Data analysis and visualizations, machine learning And modeling, and mathematical techniques used in data science. Being a data scientist is more than just using plug-and- play machine learning packages. Educators have to understand what the algorithm is actually doing first and foremost and know when and why to use it. The process to learn what the algorithms are doing is by studying the underlying mathematics. We know that Geometry and graph theory form essential pillars of data science, it providing tools to model, analyze, and visualize complex relationship. These mathematical concepts enable data scientists to efficiently uncover patterns, optimize systems, and efficiently represent intricate datasets. Now, I know “Big Data” and “Hadoop” have become a bit of a big deal in the data world and are being thrown around like a cool fad, but it feels like a lot of people still don’t really understand the concept behind it. In this article I’ve covered the why and what of Open-source software how does it all actually work? Data is essential for ML- enabled systems. Poor data will result in inaccurate predictions, which are referred to in the ML context as “garbage in, garbage out”. Hence, ML requires high-quality input data. From the viewpoint of RE, it is clear that data constitutes a new type of requirements Based on the Data Quality model defined in the standard ISO/IEC 25012, we elaborate on the data Perspective.

DOI: http://doi.org/10.5281/zenodo.15833884

ISOLATION, PURIFICATION AND PARTIAL CHARACTERIZATION OF PROTEASE ENZYME FROM GUAVA (Psidium Guajava) LEAVES

Authors: LOKESWARAN. V, SHANMUGAVADIVU. M

Abstract: Protease enzymes play an important role in many biological processes, including protein digestion, cell signals and protective mechanisms. In this study, the isolation, refining and partial characteristics of the protease enzyme of Guava (Psidium Guajava) have been studied. Dry guava leaves are homogeneous and extracted by raw enzymes using phosphate stamps. The activity of the protease has been determined by the digestion of casein and raw enzyme extract refined by precipitating in ammonium sulfate. The specific activity of pure protease enzyme is significantly higher than the rough extract. The enzyme is characterized by its pH, its optimal temperature and stability, showing the maximum operation at pH 4 and 60° C. In addition, the molecular weight of the protease enzyme is about 135 kda. In addition, the ability to decrease protein enzyme shows its ability to apply in soft meat, hydrolysed protein in food processing and remove points in laundry detergent. This study emphasized that the promising potential of guava panels is a profitable and environmentally friendly biological substance for industrial applications, especially in the fields of food and detergents. Add in -Depth on its complete enzyme records and its industrial scale is reasonable

DOI: http://doi.org/

Artificial Intelligence And Image Processing Based Plant Leaf Disease Monitoring And Supervision.

Authors: Rushali Manwatkar, Saloni Jaiswal, Professor Yogesh Patidar

Abstract: Image retrieval is a poor stepchild to other forms of information retrieval (IR). Image retrieval has been one of the most interesting and research areas in the field of computer vision over the last decades. Content-Based Image Retrieval (CBIR) systems are used in order to automatically index, search, retrieve, and browse image databases. Colour, shape and texture features are important properties in content-based image retrieval systems. In this paper, we have mentioned detailed classification of CBIR system. We have defined different techniques as well as the combinations of them to improve the performance. We have also defined the effect of different matching techniques on the retrieval process. Most content-based image retrievals (CBIR) use color as image features. However, image retrieval using color features often gives disappointing results because in many cases, images with similar colors do not have similar content. Color methods incorporating spatial information have been proposed to solve this problem, however, these methods often result in very high dimensions of features which drastically slow down the retrieval speed. In this paper, a method combining color, shape and texture features of image is proposed to improve the retrieval performance. Given a query, images in the database are firstly ranked using color features. Then the top ranked images are re-ranked according to their texture features. Results show the second process improves retrieval performance significantly.

 

 

High Performing Organization – Tesla Case Study

Authors: Raghu V Kaspa

Abstract: High Performing Organizations (HPOs) consistently outperform their peers in metrics such as innovation, agility, financial results, and employee engagement. This paper explores the critical attributes that characterize HPOs and applies these attributes to Tesla, Inc., as a case study. Through an analytical lens grounded in organizational theory, performance frameworks, and empirical evidence, Tesla’s rise as a global automotive and energy leader is examined to identify the drivers of its high performance.

DOI: http://doi.org/10.61137/ijsret.vol.11.issue3.154

 

A Review of Machine Learning Techniques to Predict Early-Stage Lung Cancer from Patient Records and Symptoms

Authors: Sneha Sankeshwari, Santosh Gaikwad, Arshiya Khan, R.S. Deshpande

Abstract: Lung cancer is one of the leading causes of cancer-related mortality worldwide, primarily due to delayed diagnosis and limited access to timely screening. Early detection is essential for improving survival outcomes, yet conventional diagnostic techniques such as CT scans, X-rays, and biopsies are often expensive, time-consuming, and not readily available in all healthcare settings. This study explores the potential of machine learning (ML) techniques in facilitating early and accurate lung cancer prediction by leveraging structured patient data, including age, smoking history, environmental exposures, and family medical background. Various ML models—including Logistic Regression, Decision Trees, Random Forests, and Support Vector Machines—are evaluated for their effectiveness in identifying high-risk individuals. Publicly available datasets, such as the UCI Lung Cancer Dataset, SEER database, and PLCO trial data, are utilized for training and validation. The study also addresses key challenges in ML-based diagnosis, including data imbalance, feature selection, and model interpretability. Additionally, future research directions are highlighted, particularly the integration of multi-modal data and the deployment of interpretable AI solutions in clinical practice. The findings underscore the promise of ML in making lung cancer detection more accessible, efficient, and cost-effective, ultimately contributing to reduced mortality rates.

 

 

Advanced Machine Learning Framework for Robust Phishing Website Identification

Authors: Mr. Uppala Haresh, Assistant Professor Mrs. Perla Ratna Kumari

Abstract: Recent years have witnessed a notable rise in phishing attacks targeting websites. Many researchers have developed tools aimed at identifying such fraudulent sites. Nevertheless, these tools are not fully capable of recognizing all threats. There are several minor challenges in detecting fake websites. Therefore, incorporating machine learning techniques into the detection process is the most effective approach. This enhances the overall accuracy of the project. Moreover, it allows for more efficient computation. Utilizing machine learning methods can also help tackle the challenges posed by existing phishing detection models. The main objective of this project is to use the dataset designed to train the ENASSEMBLE Machine Learning (ML) model for identifying phishing websites.

 

 

Hybrid Approaches in Fraud Detection: Combining Supervised And Unsupervised Learning

Authors: Atharva Jadhav

Abstract: The advancement of artificial intelligence (AI) has given rise to two major approaches: traditional machine learning (ML) and deep learning (DL). While traditional ML relies on feature engineering and structured learning approaches, deep learning automates feature extraction through artificial neural networks. This paper explores the differences between these methods, compares their performance across domains such as image recognition, natural language processing, and financial forecasting, and evaluates their advantages and limitations. Experimental results and literature reviews indicate that deep learning excels in handling large datasets and complex patterns, whereas traditional ML is more suitable for smaller datasets with structured features.

 

 

Image Forgery Detection Using Deep Learning

Authors: Shubham Ballal, P.R Sonawane, Utkarsh,, Aashutosh Rawat, Deewan Singh

 

 

Abstract: In modern world, images are among the most significant sources of shared information.They include important information that even those who are illiterate can understand. The growing availability of advanced image editing tools has made detecting image forgeries a crucial problem in digital forensics.However, the majority of Forgery detection methods are limited to identifying a single kind of forgery, like image splicing or copy-move, which are not used in everyday life. In order to improve digital image forgery detection, this paper suggests a deep learning technique that combines CNN and ELA to simultaneously detect two types of image forgeries. The suggested method depends on determining the forged area’s com- pressed quality, which typically varies from the image’s overall compressed quality.The matrix subtraction of the original image compressed image is used as input to CNN model for training and detection. This research paper fine-tunes the CNN and uses robust compression levels in ELA to minimise complexity and maximise accuracy.

DOI: http://doi.org/

 

 

Harnessing Advanced Machine Learning Techniques for Accurate Sleep Disorder Classification

Authors: Tejitha Pukkalla, Professor Dr. M. Sumender Roy

Abstract: Classifying sleep disorders is crucial for improving individuals’ quality of life. Apnoea and sleep disturbances can have a profound effect on a person’s health. The classification of sleep stages by experts in the field is a meticulous task that is susceptible to human error. Developing accurate algorithms for machine learning applications (MLAs) aimed at classifying sleep disorders requires thorough analysis, monitoring, and diagnosis of these disorders. To categorize sleep disorders, this research compares traditional MLAs with deep learning algorithms. This study proposes an effective method for classifying sleep disorders, utilizing the Sleep Health and Lifestyle Dataset, which is available online for evaluating the proposed model. The optimizations were performed by adjusting the parameters of various machine learning algorithms using a genetic algorithm. An assessment and evaluation of the proposed algorithm’s classification performance were conducted against state-of-the-art machine learning techniques for sleep disturbances. The dataset comprises 13 columns and 400 rows containing various sleep-related variables. Additionally, routine tasks were analysed. The random forest, decision tree, support vector machine, k-nearest neighbours, and deep learning algorithms employing artificial neural networks (ANNs) were assessed. The results of the experiment reveal significant differences in the performance of the algorithms examined. The proposed algorithms achieved classification accuracies of 83.19%, 92.04%, 88.50%, 91.15%, and 92.92%, respectively. The ANN excelled in precision, recall, and F1-score metrics, achieving the highest classification accuracy of 92.92%. The corresponding values for precision, recall, and F1-score were 92.01%, 93.80%, and 91.93%. The ANN algorithm demonstrated superior accuracy compared to other tested algorithms.

 

 

Deepfake Detection

Authors: Chirayu C.Jadhav, Omkar K. Pol, Rushikesh M. Amane, Associate Professor Mrs. M. M. Raste

Abstract: The rapid advancement of deep learning has enabled the creation of hyper-realistic synthetic media, commonly known as deepfakes, which threaten digital trust, privacy, and security. While these technologies demonstrate the potential of generative models like GANs, their misuse for misinformation and identity fraud necessitates robust detection methods. This paper presents a comprehensive analysis of state-of-the-art deepfake generation techniques and their countermeasures, focusing on the challenges of distinguishing manipulated content from authentic media. We evaluate data-driven detection approaches, including artifact-based analysis and deep neural networks, highlighting their strengths and limitations under varying compression levels and dataset scales. Building on existing benchmarks like FaceForensics++ and Celeb-DF, we propose a systematic framework for assessing detector performance, emphasizing the role of domain-specific features (e.g., facial micro-expressions, inconsistent lighting) in improving accuracy. Our experiments demonstrate that hybrid methods—combining spatial-temporal analysis with adversarial training—outperform human observers and single-modality detectors, particularly in cross-dataset scenarios. Finally, we discuss emerging threats, such as adaptive deepfakes designed to evade detection, and outline future directions for scalable, real-time solutions. This work aims to standardize evaluation metrics and inspire novel research to safeguard digital media integrity in an era of escalating synthetic threats.

 

 

Envisioning Accreditations Future: Harnessing AI, Blockchain, and Micro-Credentials for Dynamic Quality Assurance

Authors: Rohith Bommalla Naresh

Abstract: Accreditation in higher education faces challenges in adapt- ing to technological advancements and evolving learner expectations. This article explores how artificial intelligence (AI), blockchain, and micro-credentials can transform quality assurance into a dynamic, trans- parent, and inclusive system. Drawing on recent research, global case studies, and theoretical insights, we propose a forward-looking ac- creditation model leveraging AI for real-time evaluation, blockchain for secure credentialing, and micro-credentials for flexible learning path- ways. Despite their potential, these technologies raise ethical, equity, and adoption challenges. A novel framework is presented, emphasiz- ing continuous improvement, global interoperability, and accessibility. Research findings highlight the impact of these innovations, ensuring higher education aligns with a rapidly changing global landscape.

 

 

Envisioning Accreditations Future: Harnessing AI, Blockchain, and Micro-Credentials for Dynamic Quality Assurance

Authors: Rohith Bommalla Naresh

Abstract: Accreditation in higher education faces challenges in adapt- ing to technological advancements and evolving learner expectations. This article explores how artificial intelligence (AI), blockchain, and micro-credentials can transform quality assurance into a dynamic, trans- parent, and inclusive system. Drawing on recent research, global case studies, and theoretical insights, we propose a forward-looking ac- creditation model leveraging AI for real-time evaluation, blockchain for secure credentialing, and micro-credentials for flexible learning path- ways. Despite their potential, these technologies raise ethical, equity, and adoption challenges. A novel framework is presented, emphasiz- ing continuous improvement, global interoperability, and accessibility. Research findings highlight the impact of these innovations, ensuring higher education aligns with a rapidly changing global landscape.

 

 

Ntrusion Detection System Using Improved Convolution Neural Network

Authors: Mrs. R. Bhuvaneswari., Ms. K.Lavanya

 

 

Abstract: As network infrastructures continue to expand, the complexity and frequency of cyber threats have significantly increased, highlighting the need for more effective Intrusion Detection Systems (IDS). This study introduces a hybrid approach combining an Enhanced Convolutional Neural Network (CNN) with Linear Regression to identify and categorize network intrusions such as BENIGN traffic, DoS Slowloris, and DoS Hulk attacks. Unlike conventional IDS frameworks that often suffer from high false alert rates and inadequate feature processing, the proposed model utilizes deep learning to extract meaningful spatial features from traffic data. The CNN component captures intricate patterns, while Linear Regression aids in refining classification by pinpointing key behavioral indicators of attacks. Evaluations show that this approach delivers improved detection accuracy, faster anomaly identification, and fewer false positives. Its real-time performance and flexibility make it well-suited for use in cloud-based platforms, enterprise systems, and IoT-driven environments.

DOI: http://doi.org/

GENERATION OF ELECTRICITY BY TRASH IN AN ECO-FRIENDLY MANNER

Authors: Ranjana Gurung, Manjesh Tamang, Sneha Tamang, Basanta Subba, Jabez Chettri, Sisir Chettri

 

 

Abstract: The primary aim of this project is to develop a model for an efficient, sustainable process for generating electricity by trash in an eco friendly manner. By burning trash into a renewable energy source, this project seeks to address both waste management challenges and demand for clean energy, contributing to environmental conservation and sustainable urban development. The efficiently converts 12V DC to 117 – 220V AC using an inverter, enabling household or small industrial usage. The results demonstrates the potential for waste to energy systems in reducing land fill burden while supplying clean energyA big amount of wastage was generated and their possible harmful outcome in the environment and in human health, where it will cause of number of diseases in human bodies.[1] Therefore, we may implements this process for safe disposal of garbages. This is an innovative concept to produce electricity by utilizing wastages, which resulted in waste material reduction and generation electricity for local use.

DOI: http://doi.org/

 

 

CFD Simulation of Flow around Ahmed Body Using Drag Reducing Devices

Authors: S. Sathish Kumar, S. Venkata Ruthwik, M. Rohith Kumar, Professor Dr Yagya Dutta Dwivedi

Abstract: This project investigates the aerodynamic performance of the Ahmed body with 35⁰, a well-known geometric model for studying vehicle aerodynamics, particularly at varying slant angles. This study focuses on the effects of various aerodynamic add-ons, including vortex generators, custom-generated striped vortex generators on the rear end, side vanes and base flaps on the drag and lift characteristics of the Ahmed body. Computational fluid dynamics (CFD) simulations are employed to analyze the airflow around the model under different configurations. Designed in Catia V5, the geometry is modeled and meshed in Ansys Workbench and Simulation is performed in Fluent. The mesh parameters are taken from [6],;initially, the results of the Ahmed Body were obtained for Cd-0.285 which are quite close to those value mentioned 0.289.Later grid independence was performed for better accuracy, and later add-ons were added and tested. The results indicated an overall drag reduction of approximately 12% from that of the Ahmed Body without any add-ons. This resulted in the power consumption of 175 W of energy.

DOI: https://doi.org/10.5281/zenodo.15687640

AI in Education

Authors: Lokesh kumar, Assistant Professor Mr. Sunil kaushik, Dr. Rajendra Khatana

Abstract: Artificial Intelligence (AI) is transforming the educational landscape by personalizing learning experiences, automating administrative tasks, and enabling intelligent tutoring systems. As digital learning environments grow, AI has become a critical component in shaping the future of education. This paper explores the current applications of AI in educational systems, emerging innovations, and the potential for ethical dilemmas and systemic inequities. It highlights how AI can serve as both a catalyst for inclusive learning and a challenge if not implemented responsibly. The goal is to ensure AI-driven education is equitable, transparent, and human-centered—requiring collaboration between educators, policymakers, and technology developers.

CV Builder Based On Artificial Intelligence

Authors: Priyanka A Giramkar, Dr. Quazi khabeer

Abstract: The rise of fake insights (AI) presents transformative openings within the space of career services, especially in continue building, a basic component for job searchers pointing to distinguish themselves in an progressively competitive scene.This inquire about investigates the development of an AIbased resume builder planned to help clients in making highly customized, proficient resumes that adjust precisely with industry measures and job-specific requirements By coordination normal dialect processing(NLP), machine learning, the framework analyzes work depictions to distinguish significant catchphrases, skillsets, and role specific necessities. It at that point appliesthis investigation to prescribe important substance, improve phrasing, and organize the continue in a way that maximizes both significance and lucidness for human recruiters and candidate following frameworks (ATS). Furthermore,the framework powerfully adjusts resumes to reflect users’ advancing career encounters, optimizing sections such as accomplishments, abilities, and proficient summaries for focused on parts. Moreover, the framework powerfully adjusts resumes to reflect users’ advancing career encounters, optimizing sections such as accomplishments, abilities, and proficient summaries for focused on parts. Through broad testing and data-driven refinement, this AI-powered resume builder illustrates the potential to streamline the work application prepare, upgrade candidate perceivability, and altogether increment the likelihood of securing interviews. This investigate contributes to the field by displaying how AI can reshape cont

Environmental Tipping Points: Human Impact, Ecological Disruption, and Sustainability Challenges

Authors: Subhranil Sarkar, Sayna Datta, Assistant Professor Aparajita Paul, Assistant Professor Pallav Dutta, Rupa Bhattacharyya

Abstract: Environmental tipping points represent critical thresholds within ecological and climate systems, beyond which significant and often irreversible changes occur. Driven largely by human activities such as deforestation, fossil fuel combustion, pollution, and overexploitation of natural resources, these tipping points threaten the stability of the Earth’s life-support systems. Key examples include the collapse of coral reef ecosystems, the thawing of permafrost, and disruptions to major oceanic and atmospheric circulation patterns. These shifts are often accelerated by positive feedback loops, making them difficult to reverse once triggered. This paper explores the mechanisms behind environmental tipping points, identifies major systems at risk, and examines the profound ecological, social, and economic consequences of crossing these thresholds. It also highlights the urgent need for integrated, science-based sustainability strategies aimed at mitigating human impacts and building resilience within natural systems. Preventing the crossing of critical tipping points is not only an ecological imperative but also a central challenge for the future of humanity.

DOI: https://doi.org/10.5281/zenodo.15688670

Impacts Of Electric Vehicle On Environment

Authors: Md Mirja Galib, Soumya Kanti Roy, Sarbani Ganguly, Payel Mondal, Rupa Bhattacharyya

 

Abstract: The Electric vehicles (EVs) represent a promising solution to lighten environmental challenges associated with traditional internal combustion engine vehicles (ICEVs). This abstract examines the environmental impact of EVs, focusing on key factors such as greenhouse gas emissions, resource extraction and production, battery recycling and disposal, energy efficiency, infrastructure development, and lifecycle analysis. While EVs produce zero tailpipe emissions and can significantly reduce greenhouse gas emissions, their environmental benefits depend on factors such as the energy source for electricity generation. Additionally, the extraction of materials for EV batteries and the challenges of battery recycling and disposal poses environmental concerns that require attention. The location of a charging station can also affect its carbon footprint. If a charging station is located in an area with high traffic obstruction, the carbon footprint of charging an EV may be higher due to increase idling and emissions from other vehicles. EV production will have external costs of emissions extra, around Rp. 2.23 trillion, or an increasing about 0.6%. Based upon these findings, it is concluded that electric vehicle production increases productivity, gross value-added, and job creation with a corresponding to the small impact on the environment. Despite these challenges, EVs illustrate higher energy efficiency and offer potential prolong benefits in reducing dependence on fossil fuels. Comprehensive lifecycle evaluation is necessary for understanding the overall environmental impact of EVs compared to ICEVs. Continued development in technology, policy support, and infrastructure improvement are crucial for maximizing the environmental benefits of EVs and promoting sustainable transportation.

DOI: https://doi.org/10.5281/zenodo.15689367

 

Genetic Basis Of Diseases

Authors: Vriddhi Shah

Abstract: Genetic research has revolutionized our understanding of diseases, revealing strong hereditary components in conditions such as cancer, diabetes, and autoimmune diseases. While environmental factors also contribute, genetic mutations play a crucial role in disease susceptibility. This paper explores the genetic basis of these diseases, highlighting specific genes, inheritance patterns, and statistical insights. Recent advancements in genome-wide association studies (GWAS) and precision medicine are also discussed.

DOI: http://doi.org/10.5281/zenodo.15689196

Implementation Of CDM In India Leads To Carbon Emission Reduction And International Carbon Trading

Authors: Md Mirja Galib, Soumyadip Roy, Shilpi Pal, Payel Mondal, Sarbani Ganguly

Abstract: The rapid increase in global CO2 emissions since 1950 has led to a surge in weather- and climate-related disasters worldwide. To address this, the United Nations Framework Convention on Climate Change (UNFCCC) was established in 1992, aiming to stabilize greenhouse gas (GHG) emissions. The Kyoto Protocol introduced the Clean Development Mechanism (CDM), incentivizing both developed and developing nations to reduce emissions. Through the trading of carbon credits, CDM projects aim to mitigate climate change while fostering sustainable development. However, despite its goals, Asia and the Pacific regions dominate CDM projects, with limited participation from Africa. India’s success in CDM projects fluctuated over time, with challenges persisting due to the CDM system’s crisis. Despite uncertainties surrounding its future, the CDM’s legacy in promoting emissions reductions and sustainable development remains significant. Transitioning to the Sustainable Development Mechanism (SDM) under the Paris Agreement poses challenges and opportunities for international climate cooperation and sustainable development efforts, particularly for countries like India

 

 

Controlling of Industrial Robo ARM

Authors: Associate Professor K Chiranjeevi, R Sai Deepika, G Praveen, S Nikhitha, K Sachin

Abstract: The control system of an industrial robotic arm is a coordinated assembly of electromechanical components designed to execute complex movements and tasks with precision. At the heart of the robotic arm are DC motors, which serve as actuators that convert electrical energy into mechanical motion. These motors are responsible for driving the arm’s joints and enabling rotational and linear movements. Gears are integrated with the motors to modify torque and speed, allowing the arm to handle heavy loads or perform fine manipulations with accuracy. To power the system, batteries are used as a portable and stable source of DC electrical energy. These batteries provide sufficient voltage and current to drive the motors and auxiliary electronics. DC connectors are employed to ensure secure and efficient connections between the power source and the motors, allowing easy interfacing and maintenance.

IoT- BASED STREET FLOOD ALERT AND CONTROL SYSTEM USING ULTRASONIC AND RAIN SEASONS

Authors: Mr. K. Amarander, Y Anusha, K Shivani, G Kumaraswamy, T Tharun Kumar

 

 

Abstract: This project presents a cost-effective and real-time system for flood alert and rain detection utilizing the ESP32 microcontroller, an ultrasonic sensor, an OLED display, a rain sensor, and a buzzer. The ultrasonic sensor continuously measures the water level, while the rain sensor detects the presence and intensity of rainfall. Data from these sensors are processed by the ESP32, which triggers visual alerts on the OLED display and audible warnings via the buzzer when predefined water level thresholds are breached or significant rainfall is detected. The system, powered by a suitable power supply, offers a proactive approach to mitigate flood risks by providing timely warnings to potentially affected areas. Its compact design and low power consumption make it suitable for deployment in various environments susceptible to flooding. The low-power nature of the ESP32 and the selected sensors contributes to the system’s energy efficiency, allowing for extended operation with appropriate power management. Field testing and calibration would be crucial to optimize the system’s reliability and accuracy under diverse environmental conditions. Ultimately, this project demonstrates a tangible application of readily available microelectronics in creating resilient and responsive solutions for natural hazard monitoring and early warning.

DOI: http://doi.org/

 

 

A Comparative Study On Graph Isomorphism Algorithms From NetworkX Library.

Authors: Shashanth. N, Naveen Kumar, Dr Sanjay Dutta

Abstract: Graph isomorphism the problem of finding out whether two graphs are structurally identical or same is one of the most fundamental in various fields such as computer science, chemistry, and biology specifically mathematics and so on .This breakdown deals into several algorithms which are designed to address or evaluate graph isomorphism, some of the algorithms are been studied in this paper those are, is_isomorphic, could_be_isomorphic, fast_could_be_isomorphic, and faster_could_be_isomorphic .Each algorithm preforms using different strategies to evaluate graph similarity, from strict structural comparison to quick preliminary checks based on graph properties. While is_isomorphic uses the VF2 algorithm for precise matching, could_be_isomorphic functions offer faster assessments by evaluating global and local graph properties. However these algorithms possess limitations such as potential false positives and scalability issues for large datasets. The provided flowcharts illustrate the step by step processes involved in each algorithm, which helps in understanding their functionalities. By developing graph isomorphism algorithms researchers can find out new opportunities for applications in network analysis, pattern recognition, and beyond.

Research on Artificial Intelligence Deep Learning to Identify Plant Species

Authors: Mohammed Muzaffar, Mohammed Saif, Abdul Baser

Abstract: Nowadays, people pay more attention in artificial intelligence (AI) research, and they try to make Al smarter. The machine learning became a popular subject, especially in object recognition area. Aiming at providing a faster and more accurate plant species recognition program, the author introduced the deep learning and convolution neural network (CNN), and decided to build a CNN project with pycharm, anaconda, kera to find the best way to improve recognition program accuracy and recognition speed. The author tried to change the learning epoch time and learning data set capacity to found the best solution. After tests were finished, the result of output plots analyze is that both adding learning epochs time and extend training image set are all helpful to improve recognition accuracy and speed. As for the effect of increase learning time, it is more obvious in improving accuracy while extend training set size, which is a better method to reduce recognition time. The end of the thesis contained the experiment result, the deficiency of this essay and the future prospect forecast of the machine learning applied in plant area.

Energy-Efficient Deep Learning Via Compression: Green AI

Authors: Rajesh Chaurasiya, Vishal Sharma

Abstract: With the rapid growth of artificial intelligence (AI), deep learning models are becoming more complex and require significant computing power, memory, and energy. This makes it difficult to deploy them on devices with limited resources, such as smartphones, embedded systems, and edge devices. To address this challenge, model compression techniques have emerged as a key solution. These methods reduce the size and computational cost of AI models while keeping their performance close to that of the original models. This paper explores four widely used model compression techniques: pruning, quantization, knowledge distillation, and low-rank factorization. Each technique is explained in terms of how it works, its advantages, and the trade-offs it brings. A special focus is placed on pure compression strategies, which avoid external indexing or lookup tables and are better suited for simple and energy-efficient systems. A case study using a convolutional neural network (CNN) shows that combining pruning and quantization can reduce model size by more than 80% and speed up inference time by 30% with only a small loss in accuracy. The study also highlights key metrics for evaluating compressed models, including memory usage, speed, and accuracy. Finally, the paper discusses real-world applications in mobile devices, healthcare, and autonomous systems, along with future directions such as automated compression tools and energy-aware training. Overall, this research supports the development of more accessible, scalable, and eco-friendly AI by making models lighter and more efficient.

DOI: http://doi.org/10.5281/zenodo.15718659

 

Study Notion: A Scalable MERN Stack-Based EdTech Platform for Personalized Learning

Authors: Mayank Sharma, Assistant Professor Ms. Neeharika Sengar, Dr. Rajendra Singh

Abstract: This paper presents ‘Study Notion,’ a full-stack EdTech web platform developed using the MERN stack (MongoDB, Express.js, React.js, Node.js). It addresses core challenges in online education such as access, personalization, and engagement. The platform offers role-based dashboards, secure payments, instructor analytics, and adaptive learning components. Designed for scalability, the solution empowers learners and educators with an intuitive and effective digital learning space.

Deepfake Detection Using Computer Vision Techniques

Authors: Ms. Neeharika Sengar

Abstract: The rapid advancements in generative adversarial networks (GANs) have enabled the creation of highly realistic deepfake videos, posing significant risks in domains such as politics, cybersecurity, and digital media. Detecting such manipulated content has become a pressing challenge. This study investigates deepfake detection using computer vision techniques by training a convolutional neural network (CNN) model from scratch on the publicly available Face Forensics++ dataset. A systematic methodology involving data preprocessing, model training, and evaluation was adopted. The proposed CNN model achieved a detection accuracy of 92.3% on the test set. Furthermore, the model demonstrated strong generalization across various manipulation methods. The results indicate that custom-built CNN architectures, even without transfer learning, can be effective for deepfake detection when paired with rigorous training protocols. Challenges such as data imbalance and overfitting are discussed, and directions for future research are proposed.

UI Design And Development Of A Scalable Online Coding Education Platform Using MERN Stack In Study Notion

Authors: Dr. Rajendra Singh, Avnish Kumar, Assistant Professor Ms. Neeharika Sengar,

 

 

Abstract: The exponential growth of online learning platforms has reshaped how coding education is delivered and accessed. This research paper presents the design and development of a scalable, user-friendly, and secure online coding education platform named “Study Notion” using the MERN stack (MongoDB, Express.js, React.js, and Node.js). The project focuses on effective UI/UX design principles, responsive design, and performance optimization to enhance learning outcomes. The platform offers features such as user role management, real-time feedback, secure authentication, course tracking, hands-on projects, and instructor evaluations. Through careful system architecture and scalable design patterns, Study Notion demonstrates how modern web technologies can support flexible and immersive educational experiences.

DOI: http://doi.org/

 

 

Role-Based Access Control in Modern EdTech Platforms: A Secure Implementation using MERN Stack in Study Notion

Authors: Gourav Jangir, Assistant Professor Ms. Neeharika Sengar, Dr. Rajendra Singh

Abstract: With the growth of online learning platforms, ensuring secure and scalable access management is essential. This paper explores the design and implementation of Role- Based Access Control (RBAC) in an EdTech platform, Study Notion, developed using the MERN (MongoDB, Express.js, React.js, Node.js) stack. We analyze how RBAC enhances data security, supports multi-user functionality, and ensures proper resource allocation among students, instructors, and admins.

IoT-Based Advanced Patients Medication Monitoring System

Authors: B Sandeep Kumar, B Kalyani, Ch Ram Charan, Y Pooja sri, UG Student, Assistant Professor, Dept. of Electronics & Communication Engineering,

 

 

Abstract: This paper proposes an IoT-based Advanced Patients Medication Monitoring System tailored to enhance the accuracy and consistency of medication intake among patients, especially the elderly and chronically ill. The system comprises smart pillboxes embedded with sensors and controlled by microcontrollers such as Arduino or Raspberry Pi. These components are supported by wireless communication (Wi-Fi/Bluetooth) to ensure seamless data transmission to cloud platforms and mobile applications. Real-time monitoring allows caregivers and family members to track medication compliance remotely, while alerts via SMS or apps are sent in case of missed or incorrect doses. The design prioritizes patient safety, remote healthcare delivery, and ease of use.

DOI: http://doi.org/

 

 

Orchestrating AI-ML Workflows in Multi-Cloud Environments: from Training to Deployment

Authors: Lokesh Lagudu

Abstract: The drug discovery processes necessitate an updated, sophisticated, secure, and scalable data pipeline owing to the rising scale and complexity. This framework describes a continuous, cloud-native architecture capable of comprehensive data governance throughout the entire drug discovery lifecycle. Researchers can achieve real-time, fault-tolerant, and scalable ingestion, integration, transformation, and delivery workflows using Docker, Kubernetes, Apache Kafka, as well as AWS, GCP, or Azure clouds. The framework also solves the silos and reproducibility issues alongside compliance to the industry’s rigorous security policies. It demonstrates orchestration and containerization and modular and reusable pipeline components, expediting the cooperation of computational biologists and bioinformaticians. Beyond just automation, this cloud-native approach provides observability and scalability for fluctuating workloads. In integrating these secure, orchestrated pipelines, pharmaceutical research teams can make agile, well-informed decisions which accelerates innovation in personalized medicine and data-centric therapeutic development.

BODMAS in Real – Life Scenarios: Making Math Relevant

Authors: Deepali Chaturvedi, Garima Singh, Pooja Sharma, Nidhi Gargav

Abstract: This presentation explores the common challenges faced by primary school students in applying the BODMAS rule—an essential mathematical principle used to determine the correct order of operations in solving expressions. Despite its importance, many students struggle with understanding and correctly using the BODMAS rule, leading to frequent errors and reduced confidence in mathematics.

DOI: https://doi.org/10.5281/zenodo.15705269

Electromagnetic Radiation And Its Biological Impact On Humans And Birds: A Cross-Disciplinary Study

Authors: vimal singh, Dr.Rajendra khatana

Abstract: Abstract- The rapid growth of wireless communication systems and digital technologies has brought about a significant increase in human and environmental exposure to electromagnetic radiation (EMR). While non-ionizing radiation from everyday sources such as mobile phones, wireless routers, and broadcast towers is generally regarded as low-risk, emerging scientific studies have raised concerns about its biological effects, particularly in the context of long-term exposure. This paper investigates the dual impact of EMR on both human health and avian life. The research focuses on how chronic EMR exposure may influence cognitive function, sleep regulation, and biological stress in humans, while also examining its disruptive effects on bird species, especially in terms of their navigation, migration, and reproduction. Through a multidisciplinary approach involving field studies, satellite tracking, geospatial analysis, and computational modeling, the paper aims to provide a holistic understanding of the consequences of radiation exposure. Our findings highlight the necessity for cross-sectoral collaboration that unites environmental science, computer science, and biological research to develop responsible technological practices and ensure ecological sustainability

Electromagnetic Radiation And Its Biological Impact On Humans And Birds: A Cross-Disciplinary Study

Authors: vimal singh, Dr.Rajendra khatana

Abstract: Abstract- The rapid growth of wireless communication systems and digital technologies has brought about a significant increase in human and environmental exposure to electromagnetic radiation (EMR). While non-ionizing radiation from everyday sources such as mobile phones, wireless routers, and broadcast towers is generally regarded as low-risk, emerging scientific studies have raised concerns about its biological effects, particularly in the context of long-term exposure. This paper investigates the dual impact of EMR on both human health and avian life. The research focuses on how chronic EMR exposure may influence cognitive function, sleep regulation, and biological stress in humans, while also examining its disruptive effects on bird species, especially in terms of their navigation, migration, and reproduction. Through a multidisciplinary approach involving field studies, satellite tracking, geospatial analysis, and computational modeling, the paper aims to provide a holistic understanding of the consequences of radiation exposure. Our findings highlight the necessity for cross-sectoral collaboration that unites environmental science, computer science, and biological research to develop responsible technological practices and ensure ecological sustainability

Conceptual Framework and Performance Forecasting of a Terrain-Adaptive Plug-and-Play Range Optimization System for Electric Four-Wheelers

Authors: Anay Sunilkumar Pandya

Abstract: This research presents a conceptual framework and predictive simulation for a terrain-adaptive, plug-and-play energy optimization module designed for electric four-wheelers. Building upon proven success in two-wheeler EVs, this paper extends the architecture to heavier, multi-axle platforms. By integrating AI-based terrain analysis, driving pattern recognition, and intelligent power routing, the proposed system aims to deliver up to 22–28% improvement in driving range without modifying core drivetrain components. Simulations based on real urban and semi-urban Indian driving data validate performance forecasts. The system is particularly relevant to passenger EVs, fleet operators, and last-mile delivery vehicles in infrastructure-limited markets.

DOI: https://doi.org/10.5281/zenodo.15703704

Enhancing the Adoption and Use of Cloud-Based Services by Universities in Developing Countries

Authors: Victor Otieno Mony, Alice Nambiro Wechuli

Abstract: In the modern world, the adoption and use of cloud Computing are ubiquitous. Cloud Computing services are continuously playing a vital role in present Information Technology development paradigms. It is beyond reproach that aspects of cloud computing exist in almost all forms of manufacturing and service industries. Whereas the three Cloud Computing service models are vital, the most widely used service model is Software as a Service. In this service model, applications are outsourced under tenancy agreements by third parties known as Cloud Service Providers. Microsoft, Google, and IBM are the major players in the provision of Cloud Computing Services. Organizations migrating to the cloud operational model utilize Cloud Computing Services to gain a competitive edge, minimize operational costs, and utilize economies of scale. Unfortunately, the use of cloud computing service models in the educational sector in developing countries has not reached the expected capacity. Cloud Computing is still under-utilized by learning institutions in developing countries due to lack of infrastructure, lack of skillset, and lack of the equipment necessary for service operations. Most academicians in developing countries are unaware that the benefits of cloud services utilization education outweigh factors preventing its adoption. This research provides insight into the benefits of cloud computing services adoption in the educational sector and angles it as the perfect bridge in helping the achievement of academic goals. The paper seeks to convince academicians in developing countries that cloud computing services adoption can enhance the provision of cheap but quality education. If after reading through this paper, a scholar is compelled to incorporate cloud-based service design in their student’s learning paradigms, then, this paper would have achieved its objectives.

DOI: https://doi.org/10.5281/zenodo.15703794

Conceptual Development and Real-World Testing of a Plug-and-Play Range Optimization Module for Electric Two-Wheelers

Authors: Anay Sunilkumar Pandya

Abstract: This paper presents the development and experimental validation of a novel plug-and-play module aimed at extending the range of electric two-wheelers. Unlike traditional methods requiring internal modifications, this solution externally optimizes energy use, offering a non-invasive, user-friendly alternative. Real-world testing with a commercial electric scooter (Joy E-Bike Nanu Next) demonstrated a range improvement of up to 49.89%. The proposed solution is particularly relevant for emerging markets, where cost-efficiency and ease of deployment are crucial. Technical architecture is currently withheld due to pending intellectual property protections.

Optimizing Spatial Design For Enhanced Productivity In Contemporary Office

Authors: Suyash Yadav

Abstract: In today’s knowledge economy, optimizing employee productivity is crucial for organizational success. This study delves into the relationship between spatial planning and design elements within office spaces and their impact on user productivity. It aims to unravel how design choices influence worker performance and establish a set of parameters for designing workspaces that maximize productivity. The research commences with a historical examination of office spaces, tracing their evolution to identify key design elements that have emerged over time. Following this, the study establishes a framework of parameters to analyse the effectiveness of these elements in contemporary work environments. To explore the potential of these parameters in real-world settings, the research employs case studies, examining how various office layouts integrate these design principles. Through a comparative analysis of work environments based on the established parameters, the study develops a set of design recommendations intended to optimize user performance and maximize productivity. The findings of this research can be used to guide the design of future office spaces, fostering a productive and successful workforce, and ultimately contributing to organizational prosperity.

DOI: http://doi.org/10.5281/zenodo.15704566

River Water Trash Collector

Authors: Professor Priyanka Ikhar,, Swaranjali Santosh Wakure, Pooja Ambadas Hiwale

Abstract: – River water pollution, particularly from floating debris such as plastics, poses a significant threat to aquatic ecosystems and public health. This paper presents a river water trash collector system that integrates Bluetooth technology and software for real- time monitoring and autonomous waste collection. The system consists of a floating collection device equipped with Bluetooth-enabled sensors and actuators, allowing it to autonomously detect and capture floating debris while communicating with a central control unit. The software platform allows remote monitoring, status updates, and real-time data collection via a user-friendly interface, providing valuable insights into waste types, quantities, and collection efficiency. The Bluetooth technology enables seamless communication between multiple collectors deployed in different river locations, facilitating coordinated waste collection efforts. Field tests conducted in various river environments demonstrate the effectiveness of the system in reducing floating debris, improving water quality, and offering scalability for large-scale implementations. This paper also explores the challenges of real-time data transmission, battery management, and system integration, highlighting the potential of this Bluetooth- based solution in advancing sustainable river management and contributing to global water pollution mitigation efforts.

DOI: http://doi.org/

Green Technology

Authors: Ms. Nikita Annasaheb Shinde, Mrs. A.A.Attar

Abstract: Green technology, also referred to as sustainable or environmental technology, includes a variety of innovative methods and tools aimed at reducing environmental harm and encouraging the responsible use of natural resources. In response to increasing concerns about climate change, pollution, and the exhaustion of natural resources, this field has become essential for promoting eco-friendly practices across various sectors. Green technology covers areas such as renewable energy (like solar, wind, and hydro power), energy-efficient infrastructure, waste reduction techniques, sustainable farming, and environmentally conscious construction. By adopting these technologies, organizations can lower greenhouse gas emissions, protect natural ecosystems, and also gain economic advantages like job creation in the green sector and long-term savings. This overview highlights the importance, practical uses, and challenges of green technology in supporting global sustainability and tackling the urgent need to protect the environment.

Enhanced Cosmic Ray Detection Using An Improved Cloud Chamber, Magnetic Deflection, And Altitude-Based Statistical Analysis

Authors: Jaza Anwar Sayyed, Ansari Novman Nabeel, Ansari Ammara Firdaus

Abstract: Cosmic rays are high-energy particles originating from space that interact with Earth’s atmosphere, producing secondary particles such as muons, electrons, and positrons. Detecting these particles provides insights into high-energy astrophysics, fundamental physics, and atmospheric interactions. The cloud chamber, a classical particle detector, is widely used for visualizing cosmic ray interactions; however, it has limitations in charge differentiation, track resolution, and statistical validation. This study presents an improved cloud chamber setup with enhanced cooling, optimized lighting, and high-speed imaging for better track visibility. A magnetic field is implemented to distinguish electrons from positrons based on curvature. Additionally, cosmic ray flux measurements are conducted at varying altitudes (0m–2000m) to analyze atmospheric interactions. Advanced statistical modeling, including Pearson correlation, Poisson distributions, and exponential regression, is applied to validate the data. Results confirm that muon flux increases exponentially with altitude, while the magnetic field effectively differentiates between electrons and positrons. This study establishes a cost-effective, scalable framework for cosmic ray research, making it suitable for both laboratory and field experiments.

DOI: http://doi.org/

Tamil Education Assistant System For Primary Education

Authors: Kaushalya Kaneson, Abiramy Kumaresan, Shanoojan Krishnasamy, Don Nandun Prabhashwara Godage, Dr. Sanika Wijayasekara, Ms. Rivoni De Zoysa

Abstract: This Research paper explores a technology- driven approach to enhancing Tamil primary education by improving pronunciation, comprehension, and creative learning. Traditional teaching methods often lack adaptability and engagement, limiting their effectiveness. This study introduces the Tamil Educational Assistant System for Primary Education (TEAS), a solution designed to support young Tamil- speaking students. The proposed approach leverages speech recognition, natural language processing, and interactive learning techniques to provide personalized educational experiences. To enable multimodal learning, TEAS integrates Tamil speech therapy for pronunciation correction, Short note generation for summarizing key concepts, Sentence formation and grammar checking for syntax improvement, and Interactive storytelling with predictive text for fostering creativity. The effectiveness of this innovative system is assessed through prototype testing and user feedback, demonstrating its potential in transforming Tamil primary education.

DOI: https://doi.org/10.5281/zenodo.15718562

A Review On The Effects Of Surface Roughness, Porosity And Magnetic Fields On Journal Bearings With Heterogeneous Slip/No-Slip Surfaces

Authors: M.G Vasundhara, C M Chaithra, Chandhini K.S, G.K Kalavathi

Abstract: This review consolidates recent advancements in study of porous journal bearings under the influence of magnetic fields, surface roughness and heterogeneous slip/no-slip surfaces. Using stochastic models primarily based on Christensen’s theory and incorporating magnetohydrodynamic (MHD) considerations, researchers have explored the performance variations in short, long, and finite bearings. The studies indicate that appropriate combinations of surface roughness, permeability, Hartmann number, and engineered slip conditions can enhance bearing performance, load carrying capacity, and reduce frictional losses. This paper summarizes mathematical models, numerical methodologies, and key findings, highlighting opportunities for future developments in smart bearing design.

 

 

Crop Yield Prediction Accuracy Using XGBoost and Random Forest

Authors: Shailesh Bisht, Sunny Nahar

Abstract: Agriculture is a vital sector of the Indian economy, ensuring national food security and supplying essential raw materials to various industries. As agricultural productivity becomes increasingly important in the face of climate variability and resource constraints, accurate crop yield forecasting has emerged as a critical need. This paper presents a machine learning-driven framework that leverages environmental factors such as weather conditions, soil characteristics, and the Normalized Difference Vegetation Index (NDVI) for yield prediction. The proposed system is structured into three stages: (i) forecasting weather parameters, (ii) estimating NDVI using predicted weather data, and (iii) predicting crop yield by integrating both outputs. Experiments using historical agricultural datasets demonstrate that ensemble learning techniques, particularly XGBoost and Random Forest, deliver robust performance, with XGBoost achieving the highest prediction accuracy of up to 97%.

PRECISION DEHUMIDIFYING SYSTEM FOR PADDY HARVESTING

Authors: Aarthi, Jeevatharani shree, Kanishka, Sasikanth

Abstract: Grain quality preservation alongside loss reduction function as essential benefits of paddy drying after harvest. The traditional drying procedures are inefficient and slow while strongly depending on weather conditions thus causing substantial post-harvest losses. The research develops an IoT- based Precision Dehumidifying System that implements automatic real-time sensing along with control methods to enhance paddy drying processes. The system contains DHT sensors for temperature and humidity measurements in addition to moisture sensors that check paddy water content. The system activates the automated drying process when it detects excessive moisture through the operation of a DC fan for application of controlled airflow while utilizing a Peltier crystal for heat generation. The system operates with precise parameters to guarantee drying quality because it avoids drying the paddy too much and not enough at the same time. The IoT-based control system enables time-based observation and limited human interaction to maintain power-efficient drying processes. Optimized energy usage and minimized waste loss through implementation of this solution leads to improved overall processing efficiency together with sustainability benefits. The introduction of smart dryers delivers two benefits which are better grain quality performance alongside economical operation versus traditional drying standards. The study helps precision agriculture progress through smart sensor implementation along with automatic systems and IoT-based decision systems. This solution demonstrates adjustable characteristics which enable scalability across different climate zones to become a legitimate method for advanced grain processing units. Further development demands sensor calibration enhancement parallel to power optimization alongside machine learning model implementation for predictive moisture control.

DOI: http://doi.org/

Load Balancing And Auto-Scaling In Cloud Using Develops Practices

Authors: Abhishek Soni

Abstract: In the era of cloud computing and continuous delivery, achieving high availability and scalability is a critical objective for modern applications. This research paper explores the integration of DevOps practices with cloud-native features such as load balancing and auto- scaling. It delves into how DevOps tools and methodologies enhance the reliability, performance, and efficiency of cloud-based services, ensuring seamless user experiences and optimized resource utilization

Personalized Medical Recommendation System Using Machine Learning

Authors: Navyashree CM, Mr. Banibrata Paul

Abstract: Effective and timely disease prediction plays a crucial role in improving healthcare outcomes. This system leverages machine learning techniques to analyze patient symptoms and accurately predict possible diseases. By utilizing a Support Vector Classifier (SVC) model trained on comprehensive symptom data, the system achieves high prediction accuracy, enabling early diagnosis and timely intervention. In addition to disease prediction, the system provides personalized recommendations, including detailed disease descriptions, precautionary measures, suitable medications, recommended workouts, and dietary guidelines. These recommendations are generated based on the predicted disease, enhancing patient awareness and supporting self-care management, thus bridging the gap between diagnosis and treatment. The integration of user-friendly symptom input and an intelligent recommendation engine makes the system a valuable tool for both patients and healthcare providers. This approach promotes informed decision-making and contributes to efficient healthcare delivery, especially in scenarios with limited immediate access to medical professionals.

AI Driven Trading Systems

Authors: Abirama Sundari

Abstract: Ethical Consideration In Ai Driven Trading System Artificial Intelligence (Ai) Has Revolutionized Financial Markets, Introducing Unprecedented Efficiency And Capabilities In Trading Systems. However, This Technological Advancement Brings With It A Host Of Ethical Challenges That Demand Careful Consideration. This White Paper Explores The Ethical Dimensions Of Ai-Driven Trading Systems, Analyzing Key Issues Such As Fairness, Transparency, Accountability, Market Integrity, Privacy, And Human Oversight. As A Global Leader In Both Artificial Intelligence And Financial Technology, China Stands At The Forefront Of Ai-Driven Trading Systems. With Its Rapidly Growing Economy, Innovative Tech Sector, And Forward-Thinking Regulatory Approach, China Offers Unique Insights Into The Ethical Considerations Surrounding Ai In Finance. This White Paper Examines The Global Landscape Of Ai-Driven Trading Systems With A Particular Focus On China’S Contributions, Challenges, And Regulatory Framework. The Paper Concludes With Actionable Recommendations For Various Stakeholders And A Forward- Looking Perspective On The Future Of Ai In Financial Markets.

CivicCompass: A Data-Driven Platform for Public Information Access, Scheme Navigation

Authors: Associate Professor Mrs. Archana Dongardive, Aakash Gophane, Vishwajit Godbole, Vivek Khairnar

Abstract: CivicCompass is a centralized, web-based platform developed to streamline public access to state and district- level welfare schemes in India. Government portals often contain fragmented and unstructured information, which makes it difficult for citizens—particularly from rural and underprivileged areas—to discover and understand available benefits. This project addresses that gap by implementing automated web scraping to collect data from various official sources. The extracted content is cleaned, categorized, and stored using structured CSV files via pandas, then dynamically displayed using Django’s Model-View-Template (MVT) architecture. The portal allows users to filter schemes by state, district, and department. It also incorporates a feedback mechanism where users can submit comments or inquiries, which are reviewed through an admin panel before publication. The system was designed for scalability and maintainability, with future improvements possible through API integrations and multilingual support. Overall, the portal bridges the gap between digital governance and grassroots-level access, enabling inclusive participation in government programs.

DOI: https://doi.org/10.5281/zenodo.15727253

Artificial Intelligence for Smart City Management: Optimizing Traffic, Waste, and Resource Allocation

Authors: Assistant Professor H.S.Bhore, Mr.Shreyas Shivankar, Ms.Payal Kamble, Ms.Aishwarya Bansode

Abstract: This paper explores the applications of Artificial Intelligence (AI) in smart city management, focusing on traffic, waste, and resource management. We discuss the benefits and challenges of implementing AI-powered solutions in urban settings and propose a framework for integrating AI into smart city infrastructure.

Design And Development Of An E-Commerce Platform For Livestock And Cattle Feed Trading

Authors: Madhura.M.Raste, Aniruddha. R. Sawant,, Prathmesh.S.Patil,, Sourabh. S. Kurne, Sandip.S.Sawant,

Abstract: – In today’s digital age, farmers and livestock owners still face challenges when it comes to buying and selling animals or cattle feed. Traditional methods are often time-consuming, limited by geography, and involve middlemen who may increase costs. This project aims to develop a user-friendly website that serves as an online marketplace where farmers, feed suppliers, and livestock traders can connect directly. The platform allows users to list livestock for sale, browse available cattle feed, compare prices, and make purchases or inquiries all from their mobile or computer. It includes features like secure user accounts, search filters (by location, type of animal or feed, price range), and contact options for buyers and sellers. By bringing these transactions online, the platform helps reduce market inefficiencies, increase transparency, and give rural communities better access to trade opportunities. This website is designed to be simple, multilingual, and accessible even in low-connectivity areas. Overall, the goal is to modernize livestock and cattle feed trading, empowering farmers with the tools they need to grow their businesses more efficiently.

Biofuels and Engine Technology

Authors: Assistant Professor S.N.Sudhal, Mr.Vishal Patil, Mr.Aniruddha Jagadale, Mr.Harshvardhan Jadhav

Abstract: The growing global demand for sustainable energy solutions has accelerated the development and integration of biofuels in modern engine technologies. Biofuels—renewable fuels derived from biological sources such as crops, algae, and waste—offer a cleaner and more environmentally friendly alternative to fossil fuels. This paper explores the types of biofuels, including first, second, and third-generation fuels, and examines their physical and chemical properties relevant to combustion performance. Emphasis is placed on the compatibility of various biofuels with current internal combustion engine (ICE) systems, including spark-ignition and compression-ignition engines. Advances in engine modifications, fuel injection systems, and emission control technologies are discussed in the context of optimizing engine performance while minimizing environmental impact. The paper also addresses the technical and economic challenges in large-scale biofuel adoption and outlines future directions for research and development. Ultimately, the synergy between biofuels and evolving engine technology presents a promising pathway toward a more sustainable and energy-secure future.

Augmented Reality (AR) & Virtual Reality (VR)

Authors: Assistant Professor K.M.Jadhav, Ms.Shreya Deshmukh, Ms.Anushka Kshirsagar, Ms.Sanika Patil, Ms.Gauri Mharanur, Ms.Priya Kolar, Ms.Tanuja Patil, Ms.Ashish Katkar, Ms.Shlok Katu, Ms.Umer Ibuse

Abstract: Augmented Reality (AR) and Virtual Reality (VR) are rapidly transforming how users interact with digital environments by enhancing real-world experiences and simulating fully immersive virtual scenarios. This paper explores the current landscape, practical applications, and future directions of AR and VR technologies, with a focus on their role in education, healthcare, engineering, and retail. A qualitative research approach was adopted, incorporating academic literature, platform documentation, and real-world use cases. The study also highlights sector-specific challenges including usability, cost, and cultural limitations, while discussing technological trends such as gesture recognition, virtual simulations, and cross-platform development. Through this analysis, the paper underscores the importance of context-aware, user-centred design in maximizing the impact of immersive technologies.

Drug Discovery Using Artificial Intelligence

Authors: Ms. Tanvi Parab, Ms.Saloni Pawar, Dr. Jasbir Kaur, Assistant Professor Ms. Sandhya Thakkar

Abstract: The field of drug discovery has undergone a remarkable transformation with the integration of artificial intelligence (AI) techniques. AI-driven approaches have the potential to significantly accelerate and enhance the drug discovery pipeline by streamlining key stages such as target identification, compound screening, lead optimization, and preclinical prediction. This paper provides a comprehensive overview of the various AI methodologies employed in drug discovery, including machine learning, deep learning, reinforcement learning, and natural language processing. We explore how these technologies are being utilized to analyze complex biological data, predict molecular interactions, and identify promising drug candidates with greater efficiency and accuracy. Furthermore, the paper examines the challenges and limitations associated with data quality, model interpretability, and regulatory acceptance. We also highlight recent advancements and successful case studies demonstrating real-world applications of AI in pharmaceutical research. Ethical implications, data privacy concerns, and the evolving role of human expertise in AI- assisted workflows are critically discussed. Finally, the paper outlines future prospects, emphasizing the potential of AI to revolutionize personalized medicine and accelerate the development of novel therapeutics in a cost-effective and time- efficient manner.

Cooperative Learning Strategies And Learning Outcomes

Authors: Ramlah Ampatuan Duge,, Taya Panigel Adam, Salahudin D. Solaiman

Abstract: – This research determined the level of cooperative learning strategies in group activities, group games, peer mentoring, and problem-solving activities; the students level of learning outcomes on the 2nd and 3rd quarter of the S.Y. 2023-2024; and the relationship of demographic profile to cooperative learning strategies on students’ learning outcomes. Additionally, this study determined the relationship between cooperative learning strategies and learning outcomes; and the significant influence of cooperative learning strategies on students’ learning outcomes. Descriptive-correlation research design was utilized to analyze the gathered data from the respondents who were identified using stratified sampling with proportional allocation and complete enumeration. Mean and the spearman’s rho with correlation coefficient were used to describe the results and to test the hypotheses of the study correspondingly.Results of the statistical analyses revealed that the majority of the respondents strongly agreed on their cooperative learning strategies in peer mentoring and problem-solving activities. Subsequently, most of the respondents strongly agreed that there are learning outcomes in their subjects such as English, Mathematics, and Science. Findings revealed that cooperative learning strategies have a significant relationship with the learning outcomes in English, Mathematics and Science subjects. Moreover, cooperative learning strategies have a significant influence on learning outcomes in the same subjects.

DOI: https://doi.org/10.5281/zenodo.15738047

A Review on AI integration in Firefighting and Emergency Responses

Authors: Rishav Bairagya, Barshan Kundu, Arghya Biswas, Nikhilesh Sil

Abstract: Artificial intelligence (AI)-based emergency response systems provide emerging as key enablers of smart infrastructure safety, improved real-time decision-making, risk assessment, and catastrophe mitigation tactics across multiple domains. The combination of machine learning (ML), deep learning (DL), computer vision, IoT-enabled predictive analytics, and AI-powered robotics in optimising emergency response mechanisms is examined in this systematic literature review, which includes more than 100 eligible papers. In addition to offering a thorough evaluation of technological developments and adoption bar-riers, the study thoroughly investigates AI applications in disaster management, real-time incident detection, healthcare emergency response, industrial hazard prevention, cybersecurity frameworks, and intelligent traffic control. According to the findings, artificial intelligence (AI) has greatly increased automated hazard detection, predictive accuracy, and emergency resource optimisation. These improvements have sped up reaction times, reduced human error, and improved situational awareness in crisis management. Early warning systems for earth-quakes, floods, and wildfires have been made possible by AI-driven predictive analytics models, promoting proactive risk mitigation and catastrophe prepar-edness. Artificial intelligence (AI)-driven computer vision and sensor-based surveillance technologies have enhanced incident detection in real-time emergency response, cutting down on intervention delays and guaranteeing more effective use of emergency resources. Triage automation, geospatial analytics for ambulance dispatch, and AI-enhanced diagnostic technologies have simplified medical crisis management in the healthcare industry, increasing survival rates and cutting down on treatment delays. Furthermore, cybersecurity intelligence systems, robotic automation, and AI-integrated industrial safety frameworks have improved workplace hazard prevention and cyber threat identification. In an emergency, an AI-powered drone-based system facilitates communication between firefighters via light, sound, and a graphical user interface. AI-driven technology solves problems based on situational awareness (SA). Emergency response systems powered by AI improve the security of smart infrastructure. Real-time emergency response optimisation, automated hazard detection, and enhanced risk assessment are all made possible by AI technologies. Real-time fire scenarios are identified using an AI-powered smart firefighting system. During disasters, artificial intelligence (AI) can improve the efficiency of emergency response.AI’s role as a crucial enabler of intelligent, data-driven emergency response frameworks, fire fighting, and emergency response will be further reinforced as AI technologies continue to advance and are incorporated into emergency management strategies. This will improve crisis preparedness, real-time intervention capabilities, and global disaster resilience. // This review offers a thorough synthesis of AI’s revolutionary role in contemporary emergency management, including insights into technological advancements, constraints, and policy considerations.

Review On Internet Of Things (IoT) Based Smart Agriculture System

Authors: Kalpesh Desai, Komal Yadav, Jasbir Kaur, Suraj Kanal, Sandhya Thakkar

Abstract: The Internet of Things (IoT) based smart agriculture system is an emerging technology that uses sensors, gateways, cloud platforms, and mobile applications to provide real-time data on weather, soil moisture, crop growth, and livestock health to farmers. This research paper focuses on developing and implementing an IoT-based smart agriculture system. The system offers several benefits: increased efficiency, improved resource management, enhanced crop quality, better decision-making, and remote monitoring. However, potential negative impacts, such as cost, technical skills, dependence on technology, data privacy and security, and environmental impact, must be considered. Careful planning, implementation, and monitoring can help to mitigate these risks and ensure that smart agriculture systems are sustainable and effective. This research aims to give an overview of how predictive analysis and Internet of Things (IoT) devices, along with cloud management and security systems, can be used in agriculture to support multiple crops. It also takes into account the experiences of farmers and highlights the challenges and difficulties that may arise when introducing modern technology into traditional farming practices. By utilizing statistical and quantitative methods, this research seeks to bring about significant and positive changes in the current agriculture system. In simpler terms, this study explores how smart farming can enhance food production, resource management, and labor efficiency, while acknowledging the challenges and benefits of integrating modern technology into traditional farming practices.

Sentiment Analysis Using Social Media Big Data

Authors: Mr. Satish Yadav, Ashish Khandagale, Dr. Jasbir Kaur, Ms. Sandhya Thakar, MS. Ifra Kampoo

Abstract: The exponential growth of social media platforms has generated unprecedented volumes of user-generated content, creating vast repositories of public opinion and sentiment. This research investigates the application of sentiment analysis techniques to social media big data, examining methodologies for extracting, processing, and analyzing emotional insights from large-scale social media datasets. Through a comprehensive review of machine learning approaches, natural language processing techniques, and big data analytics frameworks, this study evaluates the effectiveness of various sentiment classification models when applied to Twitter, Facebook, and Instagram data. Our findings demonstrate that hybrid approaches combining lexicon-based methods with deep learning architectures achieve superior accuracy rates of 89.3% compared to traditional rule-based systems. The research also addresses critical challenges including data preprocessing, feature engineering, and scalability issues inherent in social media sentiment analysis. The implications of this work extend to business intelligence, political analysis, brand monitoring, and public health surveillance applications.

Implementation Of Deep Learning And Artificial Intelligence For The Goals Of Corporate Sentiment Analysis And Performance Prediction

Authors: Professor Dr. Rajendra Singh Kushwah, Ritesh Kumar

Abstract: The most popular method of forecasting SPs throughout the course of history was to make use of statistical models such as moving averages, ARIMA, and the GARCH. This was the most common strategy. It is difficult for these models to accurately predict future SPs due to the fact that financial markets are characterized by their complexity, non-linearity, and unending change. In spite of the fact that these models are able to effectively recognize particular linear trends within historical data, they often have a difficult time accurately predicting events that will occur in the future. As a result of the fact that price changes are impacted by a large variety of different factors, these models do not allow for the precise estimation of future SPs. These models are not particularly accurate as a consequence of this. In recent years, there has been an increase in interest in the topic of financial forecasting in relation to the capabilities of machine learning and deep learning approaches. This attention has brought about a number of interesting developments. The methodologies in question are able to accurately characterize not only the time-dependent patterns that are present in the data, but also the intricate and non-linear linkages that are there. In the field of time series prediction, recurrent neural networks (RNN) and long short-term memory (LSTM) networks, in addition to generalized recurrent units (GRU), have been shown to be successful tools. When it comes to capturing long-range dependencies in supply chains, it is preferable to traditional methods since it is more accurate.

Finite Element Modeling and Simulation of Concrete-Filled Steel Tubular Sections under Axial Compression

Authors: Research Scholar Venugopal Burugupally, Dr Ajay Swarup

Abstract: Concrete-filled steel tubular (CFST) sections are widely used in structural applications due to their superior mechanical properties, including high axial load capacity, energy dissipation, and fire resistance. This study presents a finite element analysis (FEA) of CFST columns under axial compression using ANSYS Workbench. The numerical model incorporates nonlinear material behavior, including an elastoplastic model with strain hardening for steel and the Drucker–Prager plasticity model for concrete to account for confinement effects. A structured finite element mesh was employed, with solid elements for concrete and shell elements for steel. The analysis considered realistic boundary conditions, applying displacement-controlled axial loading with fixed base constraints. The FEM results were validated against experimental data from the literature, showing a maximum deviation of less than 5% in peak axial load prediction. Load-displacement curves confirmed that steel confinement enhances concrete performance, delaying local buckling and increasing overall strength. Stress distribution analysis indicated effective load transfer between the steel tube and concrete core, while buckling patterns demonstrated progressive load redistribution, preventing sudden failure. These findings confirm that FEM is an effective tool for optimizing CFST designs and predicting their structural response under varying load conditions.

Convolutional Neural Network For The Detection Of Conjunctivitis In Eye Image

Authors: Bhagwan, Assistant Professor Ashwini Sangam

Abstract: Conjunctivitis, a frequent eye illness characterized by inflammation of the conjunctiva – the delicate tissue lining the inner eyelids and covering the eye’s white region, may occur from numerous causes such as bacterial or viral agents, as well as allergies. While often non-severe and self-resolving after a few of weeks, it might cause pain and hamper good vision. Harnessing the power of Convolutional Neural Networks (CNNs), a type of artificial intelligence, provides a revolutionary way to diagnose conjunctivitis in ocular pictures. CNNs excel at recognizing subtle picture patterns by learning from an enormous dataset covering both healthy and sick eyes. Trained CNN models exhibit amazing skill in detecting conjunctivitis within fresh photos with great accuracy

DOI: https://doi.org/10.5281/zenodo.15753155

Smart Waste Detection And Sorting System

Authors: Prathibha M, Dr. Manjunath M, Dr. Evangelin Geetha D

Abstract: This study introduces an intelligent waste detection and sorting system driven by artificial intelligence and deep learning models such as YOLO and TensorFlow. It efficiently classifies waste into categories like recyclable, organic, and hazardous using real-time image analysis. A tailored model trained on waste datasets enables accurate recognition across varying environments. Developed with Python and OpenCV, the system also recommends appropriate disposal methods. Its compact design supports integration into smart bins and industrial workflows. The approach promotes automation in waste segregation, offering a sustainable and scalable solution for effective waste management.

DOI: http://doi.org/

Improvement Of Network Life Time And Throughput Using AI Based Leach Protocol

Authors: Bishnu Kumar, Dr. Ayonija Pathre

Abstract: In wireless sensor networks (WSNs), many sensor devices are spread throughout the environment with the goal of collecting data and sending them to a base station (BS) for further studies. The issue of their limited battery power has aroused the interest of researchers, and several protocols were developed to optimize energy use and thus increase the network’s lifetime. The present research enhances the well-known low-energy adaptive clustering hierarchy (LEACH) protocol with a new artificial intelligence (AI) protocol named energy distance NN LEACH. For this purpose, an innovative clustering strategy built on the machine learning NN algorithm is used in WSNs to improve the cluster formation process and maximise network stability. By implementing an objective function that considers each node’s residual energy and distance from the cluster centre when selecting the cluster head (CH) of each cluster, LEACH also eliminates the inherent randomness in LEACH during the CH election process. The proposed protocol has the advantage of ensuring better CH distribution throughout the network surface with a balanced load across all network nodes. In comparison with the known LEACH, the simulation results demonstrate the efficiency of our approach: the lifetime of the network is extended and the energy consumption is reduced.

Installation Of Geosynthetic Interlayers During Overlay Construction

Authors: Shriti Malviya, Professor Shashikant B. Dhobale

Abstract: The present study demonstrates the study and modelling of the geo polymer and Geo-Jute Fabric Pavement. The main idea is to reduce the Water Infiltration and the Erosive property of the traditional bitumen roads. In this project we have introduced 2 layers of Geo-Jute Fabric which are placed between the Subgrade and the Base course and another one is placed between the Binder course and the Surface course. The Geo-Jute layer between the Subgrade and Base course will reduce the Water Infiltration property whereas the Geo-Jute Fabric between the Binder course and the Surface course will reduce the progression of wear and tear underneath the Surface course. The table compares the key properties of two materials: GeoJute and Geopolymer, focusing on their CBR value, water absorption, and cost. GeoJute shows a higher California Bearing Ratio (CBR) value of 4.6, compared to 3.5 for Geopolymer. This indicates that GeoJute provides better strength and load-bearing capacity in subgrade soil reinforcement applications. GeoJute exhibits significantly higher water absorption, with a rate of 200%, while Geopolymer has a much lower absorption rate of 10%. This suggests that GeoJute retains more moisture, which might affect its performance in wet conditions.

Biodegradable Plastics And Environmental Safety: Opportunities And Challenges

Authors: A. S. Bagawan, C. S. Katageri, S. N. Benal

Abstract: Biodegradable plastics have emerged as a potential solution to mitigate the environmental impacts of conventional plastics, which persist in ecosystems for centuries. This article evaluates the environmental safety of biodegradable plastics, focusing on their degradation mechanisms, ecological impacts, and lifecycle sustainability. Through a mixed-methods approach combining literature review and experimental analysis, we assess the performance of common biodegradable plastics like polylactic acid (PLA) and polyhydroxyalkanoates (PHA) under various environmental conditions. Findings indicate that while biodegradable plastics offer reduced persistence compared to conventional plastics, their environmental safety depends on proper waste management infrastructure and environmental conditions conducive to biodegradation. Challenges such as incomplete degradation, microplastic formation, and high production costs underscore the need for improved materials and policies. This study highlights the potential of biodegradable plastics to enhance environmental safety while identifying critical areas for future research and development.

DOI: http://doi.org/10.5281/zenodo.15754651

Indian_Cultural_Wedding_Architecture_Journal

Authors: Riya Dadarao Gawai

Abstract: India’s wedding traditions are deeply rooted in cultural rituals, symbolic gestures, and spatial expressions. With the rise of destination weddings in India, there’s an increasing demand for architectural spaces that not only cater to luxury and comfort but also honor the rituals, aesthetics, and materiality of Indian traditions. This research investigates how contemporary wedding venues can reflect India’s cultural diversity through regional architectural language, use of traditional materials, and planning of ritual-centric spaces. The goal is to bridge modern hospitality design with traditional Indian values.

Advanced Machine Learning Techniques for Predicting Road Traffic Accident Severity

Authors: Research Scholar Mitali Khandelwal, Dr. Kshmasheel Mishra

Abstract: Road traffic accidents are a leading cause of fatalities and injuries worldwide, with their severity influenced by numerous dynamic and interrelated factors. Predicting the severity of such accidents is critical for timely emergency response, infrastructure planning, and overall road safety enhancement. This study explores advanced machine learning (ML) techniques to accurately predict accident severity using diverse datasets comprising weather conditions, road characteristics, vehicle information, and driver behavior. A novel hybrid model is proposed, integrating classical pre-trained models with ensemble learning and deep neural networks to capture complex nonlinear relationships within the data. To address class imbalance a common issue in accident datasets, strategies such as data augmentation and cost-sensitive learning are incorporated. The proposed architecture undergoes rigorous performance evaluation using metrics like accuracy, precision, recall, and F1-score, demonstrating superior predictive capability compared to traditional models. Further, the study emphasizes model interpretability through tools like SHAP and LIME to enhance transparency and trust. By leveraging real-world traffic data and scalable ML infrastructure, the developed model offers a reliable solution for severity prediction, aiding emergency services and policy decisions. Ultimately, this research contributes to the reduction of road casualties and the advancement of intelligent transport systems.

Beyond The Lie: AI-Powered Deep Detection Of Deception In The Social Media Era

Authors: Aryan Bhatt, Aryan Verma, Syed Qayam
Abstract: Social media has transformed the way people consume news by providing affordable, readily available, and quick information communication. Unfortunately, it has also provided a breeding ground for fake news—intentionally misleading or untruthful information—that can have serious consequences for individuals and society. Identification of fake news on social media has therefore become an essential research area. This problem differs from conventional news media, since false news is deliberately designed to mislead and thus cannot be easily detected by content alone. To overcome this, auxiliary data, including user behavior and social interactions, are usually needed. But it is hard to make use of this information because it is large-scale, incomplete, unstructured, and noisy. Considering the significance and complexity of the issue, the paper discusses Artificial Intelligence (AI) in the detection of false news on social media. We present an overview of the fake news features according to psychological theory and social theory, discuss previous AI-based detection algorithms, as well as assessment metrics and corpora. Further, we stress major challenges, current research work, and the possible future areas of AI use in detecting fake news.

Bridging Global Cybersecurity Governance Gaps: A Comparative Legal Analysis of the European Union and Emerging Frameworks in South Asia and Latin America

Authors: Mr. Shantanu Gamre, Dr. Jasbir Kaur, Assistant Professor Mr. Suraj Kanal

Abstract: This research takes a close look at how different parts of the world are tackling cybersecurity, comparing the well-established approach of the European Union with the evolving systems in South Asia and Latin America. We found that there are still big gaps in global cybersecurity efforts. These gaps exist because cyber threats don’t respect borders, countries have very different levels of readiness and resources, and cybersecurity laws often clash or aren’t consistent worldwide. The European Union stands out with its strong, rights-focused legal framework, including key laws like GDPR and NIS2, and powerful agencies like ENISA. In contrast, South Asian countries are rapidly embracing digital technology but often struggle with outdated or inconsistent laws, political challenges, and a tricky balance between national security and individual online freedoms. Meanwhile, Latin American nations face advanced cybercrime and even attacks from other governments. While some, like Brazil with its LGPD, have made good progress in data protection, the region generally suffers from a shortage of skilled cybersecurity professionals and difficulties in putting plans into action. Ultimately, this research concludes that to truly make our digital world safer and more fair, we need a global shift towards shared responsibility, focused efforts to build up cybersecurity capabilities where they’re weakest, and much stronger international cooperation.

Enhancing Fake Profile Detection in Social Media Using Explainable Ai for Cybersecurity in Machine Learning

Authors: – P. Meiyazhagan, R. Harish Muthu, M.V. Kowshika, S. Mohammed Kaif

Abstract: The rapid proliferation of fake profiles across heterogeneous social media platforms presents a significant challenge to online security, misinformation control, and digital trust. Traditional machine learning models for fake profile detection often operate as black-box systems, making it difficult to interpret their decisions. To address this, we propose a novel Explainable AI (XAI)-driven framework that enhances transparency and accountability in fake profile identification. Our approach integrates ensemble machine learning models (Random Forest, XGBoost, and Support Vector Machines) with SHapley Additive Explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) to provide interpretable feature importance insights. By analyzing user metadata, behavioral patterns, and social network interactions, our system detects fake profiles while justifying its predictions in a human-understandable manner. Furthermore, an interactive XAI dashboard enables users and platform moderators to visualize decision factors, improving trust and ethical AI adoption. Experimental results demonstrate high detection accuracy and explainability, making this framework a promising solution for combating fake identities across diverse social media ecosystems

Car Price Prediction

Authors: Mr. Muskan Aherwar, Tushar Ahirwar, Dr. Jasbir Kaur, Ms. Ifrah Kampoo

Abstract: This paper aims to build a model to predict used car’s reasonable prices based on multiple aspects, including vehicle mileage, year of manufacturing, fuel consumption, trans- mission, fuel type, and engine size. This model can benefit sellers, buyers, and car manufacturers in the used cars market. Upon completion, it can output a relatively accurate price prediction based on the information that user’s input. The model building process involves machine learning and data science. The dataset used was scraped from listings of used cars. Various regression methods, including linear regression, deci- sion tree regression, and random forest regression, were applied in the research to achieve the highest accuracy. Before the actual start of model-building, this project visualized the data to under- stand the dataset better. The dataset was divided and modified to fit the regression, thus ensure the performance of the regression. To evaluate the performance of each regression, R-square was calculated. Among all regressions in this project, random forest achieved the highest R-square of 0.90416. Compared to previous research, the resulting model includes more aspects of used cars while also having a higher prediction accuracy.

The Brain Behind The Map: AI And Traffic Prediction In Google Maps

Authors:- Ayush Vishwakarma, Yashi Verma

Abstract:- Accurate estimation of travel time is no longer a luxury but a necessity in modern navigation systems, directly impacting user trust and urban transportation efficiency. As cities grow more complex and dynamic, conventional prediction models struggle to adapt to real-time changes. This paper explores the transformative role of big data and artificial intelligence (AI) in refining Estimated Time of Arrival (ETA) predictions, with a focus on Google Maps. Leveraging massive datasets—including GPS trajectories, historical travel data, real-time traffic flows, and userreported incidents—Google Maps employs advanced machine learning algorithms to make adaptive and reliable ETA forecasts [3][4][8][9]. This study investigates how these AI models interpret multilayered traffic data to generate predictions, even under volatile traffic conditions. It further examines how deep learning architectures and neural networks detect patterns, anomalies, and geographic variations in travel behaviours [1][2][19]. A time-based graphical analysis illustrates the improvements in ETA prediction accuracy from 2017 to 2025, emphasizing the system’s continual evolution. Additionally, the paper breaks down the core data sources that fuel this predictive engine, offering insights into the structure and effectiveness of Google Maps’ data pipeline [5][6][7]. As part of this research, we also propose a novel real-time user feedback mechanism designed to enhance live traffic prediction by incorporating human intelligence in the loop. The system enables commuters to quickly report congestion, blockages, or discrepancies, providing hyper-local input that can improve ETA accuracy, especially in under-reported areas.

Determinants Of Repurchase Intention For Skincare Serums Among Young Women: A Quantitative Study Of Consumer Behaviour On Nykaa

Authors: Shreya Dabral

Abstract: The growing market for beauty serums, especially on online shopping websites such as Nykaa, offers a strong research case to study consumer repurchase behavior. This research examines the drivers of consumers’ loyalty towards certain serum brands, with specific emphasis on the efficacy of Korean beauty serums and the importance of ingredient transparency. The study utilizes a quantitative approach, conducting a survey of 100 participants made up mainly of young women, a group that accounts for a large part of the serum market. Key takeaways indicate that 67% of consumers focus on product efficacy when making purchasing decisions, while 51% consider ingredients, showing a turn towards ingredient-driven purchasing habits. The findings also indicate that 37% of respondents buy serums every 2-3 months, showing moderate devotion to serum consumption and indicating the development of brand loyalty. Most importantly, 55% of consumers prefer buying online, indicating the vital role of ecommerce in the beauty sector. Even though brands such as Dot & Key and L’Oréal enjoy popularity, according to the research, 60% of the respondents have never used Korean serums and are also indifferent to their effectiveness, with 36.7% viewing them as a fleeting trend. This lack of trust is a challenge to K-beauty brands that need to present strong evidence of their product’s effectiveness in order to change consumer attitudes. In addition, before-and-after outcome importance, highly rated by 57% of participants, shows the necessity to boost consumer faith by making strategies more transparent and open. Solving this research issue is essential because not only does it enrich the knowledge about consumer behaviour within the beauty segment, but also offers practical solutions for brands willing to boost market presence and cultivate consumer loyalty. Through an analysis of repurchase intentions, the present study tries to inform marketing strategies that would appeal to changing consumer preferences within the serum sector.

DOI: http://doi.org/10.5281/zenodo.15780127

The Technical Efficiency On Zero Effect And Zero-Defect In Chennai Automotive Components Cluster

Authors: E.Bhaskaran, S.Baskara Sethupathy, Harikumar Pallathadka

Abstract: The study on Zero Defect and Zero Effect for MSMEs leads to getting bronze, silver and gold certification. The objective is to study on 20 ZED parameters performance for 40 Automotive Components Manufacturing Enterprises at Tirumudivakkam. The methodology adopted is getting 5-point scale data and analysing using business analytics / artificial intelligence techniques like descriptive analysis, correlation analysis, predictive analysis and decision analysis using Difference in Difference method and Technical Efficiency where Traditional is considered as Control Variable and AI + Robotics implementation is considered as Treated Variable. To conclude technical efficiency of traditional and AI + Robotics are calculated and found that the Technical Efficiency of AI + Robotics implemented is greater than Technical Efficiency of Traditional one. It is also found that Measurement and Analysis is ranked as No.1, Risk Management is ranked as No.2, Human Resource Management is ranked as No.3, Product Quality & Safety is ranked no. 4, Quality Management is ranked no. 5, waste management and Technology Upgradation is ranked no. 6 , Occupational Safety is ranked no. 7, Timely delivery, Daily works management and Material Management is ranked no. 8, Natural Resource Conservation is ranked no. 9 and Leadership, Planned Maintenance & Calibration, Environment Management and Supply Chain Management is ranked no.10. The remaining 3 parameters like the swach work place ranked no. 11, Process Control ranked no. 12 and Energy Management ranked no. 13 needs improvement in DID score so that the overall performance of Automotive Components will improve and also all will get 3 certifications like bronze, silver and gold.

DOI: https://doi.org/10.5281/zenodo.15813467

HATE SPEECH DETECTION USING MACHINE LEARNING

Authors: Dr. Mainka Saharan, Mainka Saharan, Prince Kumar, Anuj Sharma, Sonu Kashyap, Yash Saxsenad

Abstract: Hate speech on social media has become a critical issue, posing a threat to societal harmony and individual well-being. As online platforms have become integral to communication, the dissemination of hateful and offensive language is increasingly unchecked, necessitating automated systems to detect and mitigate its impact [1][3]. This project aims to develop an automated hate speech detection system using advanced deep learning techniques, specifically the DistilBERT model, a lightweight transformer architecture known for its efficiency and accuracy [2][9]. The system categorizes textual content into three distinct classes: hate speech, offensive language, and neutral speech [1][4]. By employing comprehensive preprocessing methods to clean the text and leveraging tokenization to capture semantic meaning [1][6], the model is fine-tuned on a labeled dataset and achieves a test accuracy of 90.5%. The proposed system is designed for scalability and real-time deployment, addressing the challenge of moderating the vast amount of user-generated content on social media [5]. This study highlights the importance of using robust transformer models to analyze linguistic nuances, ensuring accurate classification even in complex and implicit cases of hate speech [9][2]. The project’s contributions include the development of a deployable application, introduction of data balancing techniques, and an evaluation of various preprocessing and modeling approaches [1][4].

Using Ensemble Of Multiple Fine-Tuned EfficientNet Models For Skin Cancer Classification

Authors: Mr. Rohit Daundkar, Mr. Kaustubh Shirke, Dr. Jasbir Kaur, Assistant Professor Mr. Suraj Kanal

Abstract: Skin cancer is a prevalent form of cancer, and its early and accurate identification is critical for effective treatment. In this research paper, using an ensemble of fine- tuned Efficient Net models we proposed an improved approach for skin cancer classification. Our methodology incorporates data augmentation techniques to augment the dataset size, fine- tuning of the Efficient Net model by unfreezing the last few blocks, and employing an average ensemble for enhanced classification accuracy. The proposed approach when compared with other related work proved its effectiveness by outperforming them. Furthermore, our proposed ensemble method shows a precision value of 0.990, and accuracy of 0.988. Our findings demonstrate the effectiveness of the proposed methodology and its potential to significantly improve the diagnosis and treatment of skin cancer.

Carbon Sequestration Potential Of C3 Vs. C4 Plants Under Climate Change Conditions

Authors: Assistant Professor Ajay Kumar

Abstract: The accelerating rise in atmospheric carbon dioxide (CO₂) concentrations has intensified efforts to enhance terrestrial carbon sinks, particularly through strategic deployment of C₃ and C₄ photosynthetic pathways. This study synthesizes current knowledge on the carbon sequestration potential of C₃ plants, which benefit markedly from CO₂ enrichment but suffer from photorespiration and nutrient constraints, and C₄ plants, which maintain efficiency under heat, drought, and low CO₂ conditions due to their biochemical CO₂-concentrating mechanism. We review field-based flux measurements, remote sensing classification, and genome-scale metabolic models to quantify net primary production responses, soil carbon inputs, and distributional shifts under projected climate scenarios. Findings indicate that C₃ afforestation can maximize sequestration in temperate regions when nutrient limitations are managed, while C₄ bioenergy crops offer robust carbon capture and water-use advantages in warmer, water-limited biomes. We recommend region-specific species selection, integrated methodological frameworks combining eddy-covariance, high-resolution imagery, and mechanistic models, and exploration of synthetic biology and machine-learning tools to refine sequestration estimates. This comprehensive approach informs land-management and policy strategies aimed at mitigating climate change through optimized carbon-negative land uses.

Fingerprint Segmentation System Across Age Variations

Authors: Ms J. Alfreena, Professor Dr. F. Ramesh Dhanaseelan, Associate Professor Dr. M. Jeya Sutha

Abstract: Fingerprints are widely used in security, healthcare, and criminal investigations for identification. Slap fingerprint images, which capture multiple fingerprints in one scan, improve accuracy but are hard to process due to different angles, background noise, and small fingerprint sizes. This system includes Clarkson Rotated Fingerprint Segmentation that accurately detects and labels fingerprints using bounding boxes. It performs better than traditional systems like National Fingerprint Segmentation, handling rotated images effectively and feature extraction with the Canny edge detection algorithm to accurately detect fingerprint edges. These advancements reduce errors, improve real-time scanning, and enhance fingerprint security systems. This makes fingerprint recognition more accurate and adaptable across different conditions.

DOI: https://doi.org/10.5281/zenodo.15833678

Big Data Analysis In Social Media

Authors: Ms. Muskan Shaikh, Dr.Jasbir Kaur, Mr.Suraj Kanal

Abstract: – This paper discusses the importance and advantages of big data analysis and application in social media marketing. With the popularity of social media platforms, big data analysis provides enterprises with opportunities to deeply understand user needs, optimize marketing strategies and improve marketing effects. This paper introduces the current situation of social media marketing, and expounds in detail the application of big data analysis in user portrait analysis, user behavior analysis and marketing effect evaluation. Through big data analysis, enterprises can formulate more accurate marketing strategies, improve marketing accuracy, optimize user experience and improve marketing efficiency. However, big data analysis also faces challenges such as data quality and privacy protection, which requires enterprises to pay attention to data security and compliance in the process of application.

Multimodal Deep Learning For Enhanced Segmentation Of Histotripsy Ablation Zones

Authors: Ms Merlin Steffy M, Professor Dr. F. Ramesh Dhanaseelan, Associate Professor Dr. M. Jeya Sutha

Abstract: This research presents histotripsy is a non-invasive ultrasound technique used for precise tissue ablation, showing promise in treating conditions like kidney tumors. This project proposes a deep learning-based segmentation system using a Convolutional Neural Network (CNN) with a ResNet-18 backbone to identify ablated regions in ultrasound images automatically. The system is trained on phantom images and uses digital photographs as ground truth. In addition to image segmentation, the system overlays segmented zones, counts treatment pulses, and supports real-time monitoring significantly improving speed, accuracy, and clinical decision- making.

DOI: http://doi.org/10.5281/zenodo.15833637

Federated Learning For Privacy-Preserving Healthcare Data Analysis

Authors: Rutik Jadyar, Hritik Acharya, Dr. Jasbir Kaur, Assistant Professor Ms. Ifra kampoo

Abstract: In recent years, the use of digital health data has grown rapidly. However, sharing sensitive medical information can lead to serious privacy concerns. Traditional data analysis methods require centralizing data, which poses a risk of exposing private information. Federated Learning (FL) is a new method that allows hospitals and healthcare institutions to collaborate on machine learning models without sharing actual patient data. Instead, the model is trained across different devices or servers holding local data. This paper explains how FL works, its benefits for healthcare, and how it can be applied to protect patient privacy while still enabling powerful data analysis.

 

 

ETL Vs ELT: Comparative Analysis In Modern Data Pipelines

Authors: Mr.Gurudas jadhav, Mr. Mayur Shinde, Dr. Jasbir Kaur, Assistant Professor Mr. Suraj Kana

Abstract: With the explosion of data in recent years, the methods used for extracting, transforming, and loading (ETL) or extracting, loading, and transforming (ELT) data have become critical in the design of modern data pipelines. These methodologies are pivotal in ensuring that raw data from disparate sources is cleansed, structured, and made analytics-ready for business decision-making and operational insight. The efficiency and effectiveness of these processes directly impact the performance of data warehouses and the value extracted from data analytics initiatives. This paper presents a comprehensive comparison of ETL and ELT paradigms in terms of architecture, performance, scalability, cost efficiency, governance, and use-case suitability. Through an in-depth exploration of their underlying technologies, application scenarios, and industry adoption patterns, we aim to clarify the decision-making process for choosing the right approach in different organizational contexts. We consider technical, operational, and business dimensions that influence the selection between ETL and ELT, including data volume, regulatory compliance, tool ecosystems, and team skillsets. Moreover, we delve into the role of emerging cloud-native platforms that support ELT’s rise, and how modern engineering practices such as version control, CI/CD, and modular design are redefining data transformation workflows. Case studies from leading technology firms illustrate practical implementations and benefits of these approaches, highlighting real-world trade-offs. We also explore the future trends and hybrid architectures that aim to harness the strengths of both paradigms in increasingly complex data environments, particularly in light of advancements in artificial intelligence, real-time processing, and decentralized data ownership models such as data mesh. By synthesizing insights from academic research, industry white papers, and technical documentation, this paper provides a strategic framework to guide enterprises in architecting resilient, scalable, and future-ready data integration solutions. The paper concludes with references to academic research, industry white papers, and technical documentation.

 

 

Advancing Content-Based Image Retrieval for Medical Visualization Using Machine Learning: A Focus on Diabetes and Related Complications

Authors: Mr. Battu Rajesh, Associate Professor Mr. M. Satyanarayana

Abstract: In this study, a content-based image retrieval (CBIR) system was built as an efficient image retrieval tool, allowing the user to send a query to the system, which then retrieves the user’s desired image from the image database. We wanted to present a quick overview of the novel coronavirus (SARS-CoV-2) and a better knowledge of the coronavirus illness (COVID-19) in diabetics and its therapy. In this study, we use the COVID-19 dataset to train machine learning algorithms, which subsequently predict whether a person has type diabetes. If type 2 diabetes is detected in a person’s test record, he is more prone to COVID-19 disease, heart disease, or renal disease.

DOI: https://doi.org/10.5281/zenodo.15789601

Intelligent Phishing Defence: An ENASSEMBLE-Driven Paradigm For High-Fidelity Website Identification

Authors: Ms. Manepalli Kavya, Mrs. Jitendar Ahuja

Abstract: Recent years have seen a significant increase in phishing attacks targeting websites, posing persistent challenges to digital security. While numerous detection tools have been developed, they often fall short in comprehensively identifying all threats and struggle with subtle, evolving forms of deception. Integrating machine learning (ML) techniques has emerged as the most effective strategy to overcome these limitations, significantly enhancing detection accuracy and computational efficiency. This approach is crucial for addressing the shortcomings of existing phishing detection models. This paper introduces an Intelligent Phishing defence paradigm, leveraging an ENASSEMBLE-driven ML model specifically trained on a designed dataset for high-fidelity website identification. Our objective is to demonstrate how the ENASSEMBLE model not only bolsters the overall accuracy of phishing detection but also offers a robust and efficient solution capable of recognizing complex and evasive fraudulent sites, thereby fortifying online security.

DOI: https://doi.org/10.5281/zenodo.15790035

 

Advanced Machine Learning Techniques For Detecting QUIC Traffic Flood Attacks

Authors: Mrs . Kolli Kundana Bhavya Sree, Mrs. B Sirisha, Mtech, Associate Professor

 

 

Abstract: To ensure the reliability of connected devices, machine learning is employed to analyse network traffic, facilitating quicker identification of unusual behaviour and congestion. The application of machine learning methods improves the ability to manage traffic and supports the maintenance of service quality. Furthermore, the role of machine learning in network security is to identify anomalies and classify traffic in real-time, aiming to optimize network performance and uncover potential threats. This study highlights the beneficial effects of utilizing machine learning techniques to improve network reliability and security. One of our contributions is an examination of an example of HTTP/3 traffic interacting with a web server. We implemented machine learning algorithms to differentiate between standard traffic and possible HTTP/3 flood attacks. Additionally, we developed a dataset of traffic samples featuring 23 attributes categorized into six subgroups. From traffic captured in a simulated environment, we evaluated the significance of these attributes and discovered that employing machine learning techniques can greatly enhance both network security and reliability. We utilized four supervised classification algorithms: Support Vector Machine (SVM), Logistic Regression, Random Forest, and K-Nearest Neighbours (KNN). These algorithms represent a category of supervised classification methods. They played a crucial role in training datasets of network traffic, which were carefully labelled to distinguish between Distributed Denial-of-Service (DDoS) attacks and normal traffic. The results of this research demonstrate the efficacy of machine learning algorithms in analysing network traffic to detect specific types of DDoS attacks, especially those that use QUIC traffic. This illustrates the significant potential of machine learning techniques in strengthening the overall security and reliability of networks.

DOI: http://doi.org/

 

 

EVnomics: A Machine Learning Framework For Discerning And Forecasting Electric Vehicle Total Cost Of Ownership

Authors: Ms . Nellipudi Sai Sravani1, Dr Sivabalan Settu Ph.D, Postdoc 2

Abstract: Despite the numerous advantages that electric vehicles (EVs) offer in terms of environmental protection and emission reduction, their widespread acceptance is primarily influenced by their pricing. By utilizing machine learning (ML) algorithms, it is possible to forecast these costs. This study seeks to evaluate the effectiveness of several prominent ML algorithms to ascertain which one is most capable of accurately predicting the prices of electric vehicles. In order to pinpoint the essential factors, we conducted a literature review to investigate the elements that influence the pricing of electric vehicles, facilitating our cost estimation. We theoretically assessed these ML algorithms to corroborate our results and subsequently compared the findings of this comparative analysis with the results obtained from the simulations.

DOI: https://doi.org/10.5281/zenodo.15790332

 

Vision-Based Fuzzy Inference For Enhanced Fault Detection And Classification In Railway Infrastructure

Authors: Ms. Bobbili Bhargavi, Mrs. K. Sowjanya

Abstract: The complex evolution of railway cars influences transit routes. Many mistakes arise from the utilization of train lines. Both Manufacturing mistakes and improper rail usage are responsible. For these deficiencies. There are numerous techniques for detection. Errors must be recognized promptly and rectified. The camera-based technique is One of these methods. By utilizing cameras affixed to the railway vehicle, images of the rail components are examined. Flaws are identified in the rail components. A method for detecting and analysing defects in rail tracks. Surfaces are proposed in this document. The recommended method employs image processing to identify the rail surface. High resolution images captured by specialized cameras mounted on the proposed system encompasses railway inspection cars. A Variety of track issues, including cracks, weld defects, and track Misalignment and ballast degradation are detected. These images were utilized to perform an analysis. Pre-processing and feature extraction. Image processing entails the application of segmentation techniques. Procedures to isolate the track area and emphasize any Potential defects. Fuzzy logic is employed to prioritize maintenance tasks. Based on urgency once issues have been identified and their Severity has been evaluated. Fuzzy logic is particularly adept at capturing the subjective assessments involved in evaluating. track conditions as it offers a flexible framework. Processing ambiguous and imprecise data. To assign appropriate severity ratings for the identified features of each issue. Type, fuzzy rules, and membership functions are developed.

DOI: http://doi.org/10.5281/zenodo.15790262

 

Machine Learning-Driven Predictive Maintenance: Enhancing Reliability In High-Pressure Processing Systems

Authors: Mrs. Penki Tulasi Bai, Mrs. P. Manasa

Abstract: This study suggests employing predictive maintenance to enhance the operational efficiency and prolong the lifespan of industrial machinery and equipment through machine-learning techniques. As producers prioritize reducing downtime and cutting expenses, proactive maintenance strategies are becoming increasingly vital for ensuring operational reliability. The research aims to gather historical data to train machine-learning models that can predict equipment failures and develop an algorithmic framework for scheduling preventive maintenance. The primary objective is to assist in forming an effective anticipatory maintenance strategy, which can lower industrial maintenance costs and improve product prices. Various machine-learning techniques, along with extensive data preprocessing and feature engineering methods, will be utilized in this research. Data preprocessing will involve tasks such as cleaning, dataset conversion, and normalization prior to model training. Feature engineering will focus on identifying the most important characteristics for accurate prediction of machine failures. Numerous machine-learning methods, including Random Forest (RF), Long Short-Term Memory (LSTM), and Support Vector Machines (SVM), will be evaluated to determine the most effective model for precise forecasting. The performance of these models will be compared using metrics such as Root Mean Square Error (RMSE), R-squared (R²), and Mean Absolute Error (MAE) as indicators. Ultimately, the top-performing machine-learning models will be integrated into real industrial settings, with the optimal model expected to achieve a 5-10% increase in operational efficiency.

DOI: http://doi.org/10.5281/zenodo.15790457

 

Aerodynamic Analysis of A Concept Car Model

Authors: Jupaka Mukesh Kumar, Kasaboina Mahesh, Thulugu Dileep, Dr. Yagya Dutta Dwivedi

Abstract: This project presents an overall aerodynamic analysis of an Audi R8 using computational fluid dynamics (CFD) for performance enhancement in terms of decreasing drag and increasing downforce. The study proposes to investigate the effect of a Selig S1223 (s1223-il) rear spoiler at varying angles of attack 0°, 3°, and 5° at varying inlet speeds of 20 m/s, 30 m/s, and 40 m/s. The analysis was conducted by simulating the model in SolidWorks for geometry and ANSYS Fluent for the flow study. The car was first analyzed in the base state without a spoiler, exhibiting growth in Coefficient of lift (CL) and Coefficient of drag (CD) coefficients as speed increases. After installing the spoiler, the lift decreased by a remarkable margin (with creation of downforce) while the drag increased. The study presents that the higher the angle of attack, the higher the downforce, thus improving the vehicle’s stability but at greater drag forces. Using a experimental analysis of the result from the two cases involving a spoiler and no spoiler, this project proves optimal aerodynamic design changes that minimize drag and increase the aerodynamic efficiency of the vehicle as a whole. Such results are useful in designing performance vehicles with greater handling and lesser aerodynamic drag.

DOI: http://doi.org/

 

AI-Based Mental Health Detection And Therapy Recommendation System

Authors: Prachi Babasaheb Desai

Abstract: Mental health is an essential aspect of human well- being, yet millions remain undiagnosed or untreated due to stigma and lack of access to care. This research presents an AI-Based Mental Health Detection and Therapy Recommendation System designed to identify early signs of stress, anxiety, and depression using natural language processing (NLP), voice tone analysis, and user responses to validated questionnaires. The system recommends tailored therapeutic interventions such as mindfulness techniques, journaling, and referrals to professionals. This scalable, explainable, and user- friendly solution aims to democratize access to mental health support.

DOI: https://doi.org/10.5281/zenodo.15813444

 

ENHANCED MOVEMENT OF ARDUINO VOICE CONTROLLED ROBOT USING MOTOR CONTROL ALGORITHM IN MACHINE LEARNING

Authors: Ms. Samyadevi V Assistant Professor, GuruPrakash VM, Nishbha R, Raagul R

Abstract: A voice-controlled robot is developed to perform accurate and reliable movements in response to spoken commands. The system combines a machine learning-based speech recognition module with an advanced motor control algorithm to enable natural human-robot interaction. The speech module converts voice to text, accurately interpreting commands even in noisy environments and across various accents. Recognized commands are processed and translated into actions, which are executed through a motor control system using pulse-width modulation (PWM) and directional control to manage motor speed and direction. This ensures smooth, synchronized movements, adapting to load changes without delays or jerks. Challenges like background noise and command errors are minimized through noise filtering, adaptive models, and an optimized processing pipeline. The system’s performance—measured by response time, accuracy, and movement reliability—confirms fast and precise execution, showcasing the robot’s effectiveness in real-world scenarios.

DOI:

 

 

The Impact Of Sentiment Analysis In Identifying Depression Symptoms

Authors: Professor Dr. Satya Singh, Ratnesh Kumar Sharma

Abstract: COVID-19 harmed the lives of people in every region of the world. It has been established that, in addition to the physical symptoms, it significantly influences the patient’s mental health. Depression has been identified as one of the most widespread disorders that can hasten a person’s mortality at an early age. This is one of the conditions that has been singled out for this distinction. The trajectory of life for millions of people has been altered as a result of this illness. We conducted a survey that consisted of 21 questions based on the Hamilton instrument and the advice of a psychiatrist. This was done so that we could continue forward with the inquiry into the identification of depression in individuals. After the data were compiled and analysed, it became clear that people younger than 45 years of age had a higher risk of suffering from depression when compared to those older than 45 years of age. This is because most people at this age are concerned about getting married or schooling their children. On the other side, research has revealed that those whose ages fall between 18 and 25 are also at an increased risk of suffering from depression. This is likely because, at this stage in their lives, these individuals are more conscious of the potential outcomes of their lives. Based on all of the replies received, the findings of the survey were put through several different machine learning algorithms, including Decision Tree, KNN, and Naive Bayes. These algorithms were used to analyse the results. Further investigation is being done into how these two techniques are similar to and different from one another. According to the findings of the research, KNN has produced better results than other approaches in terms of accuracy, whereas decision trees have produced better results in terms of the amount of time needed to detect depression in a person. In conclusion, to overcome the traditional approach to a depression diagnosis, which is made up of affirmative questions and constant feedback from individuals, a model that is based on machine learning is offered as a potential alternative.

DOI: https://doi.org/10.5281/zenodo.15804697

Potato Disease Detection

Authors: Ms. Komala R, Shreya Sankannavar,

Abstract: The farming industry is a mainstay of the world economy, with potato cultivation contributing immensely to food security. Despite this, potato plants are very prone to several diseases like Earl y Blight, Late Blight, and bacterial infections, causing them to experience tremendous losses in yields. Conventional methods of disease detection involve the use of manual checking, which is time-consuming, labor-intensive, and inaccurate because of human error. To overcome such challenges, the project suggests a mac hine learning-based automatic potato disease detection system. The suggested system applies image processing and deep learning models to identify and classify diseases from leaf images with high accuracy. A dataset of healthy and diseased potato leaf images is preprocessed and utilized for training a convolutional neural network (CNN) model. The model is trained to classify different diseases and healthy leaves by learning from visual attributes. After training, the model detects diseases with high accuracy in real- time, allowing timely intervention and minimizing crop loss. This framework can help farmers and agricultural professionals keep track of crop health more effectively, increasing productivity and encouraging sustainable agriculture. The project indicates the use of machine learning in precision farming and how it can revolutionize conventio nal farming practices.

TRANSACTINET: An Asynchronous, Scalable, And Secure Transactional Backend For Multi-Channel Environments

Authors: Indra Bhuwan Yadav, B.Tech (C.S.E),, Neeharika Sengar, Assistant Professor, SOET, Dr. Rajendra Singh, HOD, SOET

Abstract:-With the surge in digital services, backend infrastructure must manage high-volume transactions across diverse platforms with minimal latency and high reliability. Synchronous systems often struggle under concurrent loads, leading to performance bottlenecks. To address these limitations, this research introduces TRANSACTINET, a backend framework developed using the Tornado Python library. Designed with an event-driven model, the system supports asynchronous processing, modular architecture, and robust security protocols. This paper outlines its design, deployment strategy, and performance evaluation across real-world applications such as banking and agent-based commerce.

Multimodal Sentiment Analysis

Authors: MCA,M.Phil., Ms.S.Prathi

Abstract:- Multimodal sentiment analysis (MSA) integrates data from multiple sources, such as text, audio, and visual cues, to enhance the accuracy and interpretability of sentiment classification models. Traditional sentiment analysis predominantly relies on textual data, which can be limited in capturing non-verbal nuances like tone of voice or facial expressions. This paper explores the synergy between text, speech, and visual data in sentiment analysis tasks, addressing key challenges such as data alignment, feature extraction, and fusion techniques. We compare various fusion strategies, including early, late, and hybrid fusion, using state-of-the-art deep learning architectures such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers. Experimental results demonstrate that multimodal approaches significantly outperform unimodal systems, providing higher accuracy and robustness in sentiment detection. We discuss the potential applications of multimodal sentiment analysis in fields such as social media monitoring, customer sentiment analysis, and healthcare. Finally, the paper outlines future research directions, emphasizing the need for more efficient fusion techniques and the incorporation of emerging models to advance multimodal sentiment analysis further.

Valorization of Waste Plastic Bottles and Diapers in the Production of Sustainable Pavement Blocks

Authors: Ndongkeh Nelson Maineh, Edith Bate Etakah, Edna Buhnyuy Visiy, Mbeck Prosper Wanlo

Abstract: Plastic and diaper waste are major pollution problems worldwide. Approximately 72% of global plastic and diaper wastes end up in landfills, exacerbating environmental degradation, highlighting the urgent need for valorization strategies. This study investigated the potential use of Polyethylene Terephthalate (PET) plastics, diaper wastes and sand for the production of pavement blocks, with the goal of developing an environmentally sustainable method for repurposing these waste materials into valuable construction products. Four formulations of the paving blocks were produced and their mechanical and physical properties evaluated through various testing methods. For the four formulations, the plastic (binder) content was maintained at a constant 45% while the diaper (aggregate) content was being varied across formulations, replacing sand at percentages of 0%, 2.5%, 5% and 10% respectively. The results showed that the compressive strength of the blocks remained relatively constant across the first three formulations, with values of 10.23 MPa, 10.25 MPa, and 10.25 MPa, respectively, but dropped significantly in the fourth formulation (5.57 MPa). This indicated that a 10% replacement of sand by diapers in the fourth formulation is not advisable, as their compressive strength falls below the minimum of 8.5 MPa recommended by the SNI 03-0691-1996 standard. Moreover, the results also indicated that both flexural strength and abrasion resistance of the blocks declined as the diaper concentration increased, suggesting an optimal threshold concentration for incorporating waste diapers into the waste blocks. Also, the water absorption rate of the paving blocks increased with increasing diaper concentration with values of 0.34%, 0.34%, 0.92%, and 2.18%, respectively. However, all values were within the <20% limit for high quality blocks (ISS 1077-1970 Standard) suggesting that the blocks can withstand extreme environmental conditions, such as floods. The research demonstrates the potential to co-valorize waste plastics, diapers, and sand for the production of sustainable pavement blocks.

Disease Prediction Chatbot Using Machine Learning & NLP Techniques.

Authors: Ms. Ifrah Kampoo, Ms. Tejashree Khandekar, Dr. Jasbir Kaur, Assistant Professor
Abstract: – In healthcare demand of giving a rapid solutions led in digital health services. The chatbot employs natural language processing to interpret user inputs and leverages supervised machine algorithms. We use Natural Language Processing(NLP)extracting the structure symptoms from the text. ML algorithm use like Naive Bayes use by Probabilistic mode good for text classification fast works with small datasets.Another algorithm Decision Tree use to Rule-based predicate from symptom combinations easy to interpret and fast. Random Forest also use by Ensemble of decision trees used in more accurate, handles noisy data well. Support Vector Machine(SVM) that algorithm used as Bnary/multi-class classification of symptoms high accuracy, effective with high-dimensional data. An associated symptom-disease dataset is used to train and validate the model. Technology is accelerating innovations in healthcare domain has increasing people living years.

Disease Prediction Chatbot Using Machine Learning & NLP Techniques.

Authors: Ms. Ifrah Kampoo, Ms. Tejashree Khandekar, Dr. Jasbir Kaur, Assistant Professor
Abstract: – In healthcare demand of giving a rapid solutions led in digital health services. The chatbot employs natural language processing to interpret user inputs and leverages supervised machine algorithms. We use Natural Language Processing(NLP)extracting the structure symptoms from the text. ML algorithm use like Naive Bayes use by Probabilistic mode good for text classification fast works with small datasets.Another algorithm Decision Tree use to Rule-based predicate from symptom combinations easy to interpret and fast. Random Forest also use by Ensemble of decision trees used in more accurate, handles noisy data well. Support Vector Machine(SVM) that algorithm used as Bnary/multi-class classification of symptoms high accuracy, effective with high-dimensional data. An associated symptom-disease dataset is used to train and validate the model. Technology is accelerating innovations in healthcare domain has increasing people living years.

Disease Prediction Chatbot Using Machine Learning & NLP Techniques.

Authors: Ms. Ifrah Kampoo, Ms. Tejashree Khandekar, Dr. Jasbir Kaur, Assistant Professor
Abstract: – In healthcare demand of giving a rapid solutions led in digital health services. The chatbot employs natural language processing to interpret user inputs and leverages supervised machine algorithms. We use Natural Language Processing(NLP)extracting the structure symptoms from the text. ML algorithm use like Naive Bayes use by Probabilistic mode good for text classification fast works with small datasets.Another algorithm Decision Tree use to Rule-based predicate from symptom combinations easy to interpret and fast. Random Forest also use by Ensemble of decision trees used in more accurate, handles noisy data well. Support Vector Machine(SVM) that algorithm used as Bnary/multi-class classification of symptoms high accuracy, effective with high-dimensional data. An associated symptom-disease dataset is used to train and validate the model. Technology is accelerating innovations in healthcare domain has increasing people living years.

Trends And Threats In Biometric Data Usage Perspective On AI-Driven Identity Recognition Systems

Authors: Mr. Adnan Shafiq Mangaonkar, Ritesh Kumar Indrajit Sharma

Abstract: India’s rapid adoption of biometric technology has positioned it as a global leader in AI-driven identity recognition systems, with over 1.3 billion citizens enrolled in the Aadhaar database. This research examines the evolving trends and emerging threats in biometric data usage across India’s digital ecosystem through secondary data analysis. The study analyzes five comprehensive case studies spanning government identification systems, law enforcement surveillance, banking sector authentication, consumer mobile applications, and healthcare implementations. Key findings reveal a biometric market valued at INR 24,303.6 crores in 2024, growing at 12.18% CAGR, alongside concerning security vulnerabilities including 815 million healthcare records breached in 2023 and a 300% increase in biometric data breaches between 2020-2023. The research identifies critical gaps in privacy frameworks, discriminatory policing practices using 80% accuracy thresholds, and inadequate regulatory oversight of consumer applications. While biometric authentication has enhanced financial inclusion and service delivery efficiency, significant threats include deepfake attacks, algorithmic bias, and mass surveillance capabilities. The study recommends strengthened data protection laws, transparent AI governance frameworks, and enhanced user consent mechanisms to balance technological innovation with fundamental privacy rights.

Accident Prevention and Detection Using Iot and Machine Learning

Authors: Mr Kanhu Panigrahi ¹, Mr Aditya Singh ², Dr. Jasbir Kaur’ ³, Ms Sandhya Thakkar ⁴
Abstract: In today’s world, a significant number of car accidents occur due to drivers’ lack of attention and alertness, commonly known as driver drowsiness. This poses a serious threat to human lives and necessitates effective measures for detection and response. Various methods have been developed, including those based on vehicle motion and driver behavior. However, some of these methods require expensive sensors and handle extensive data. This research aims to address these limitations by proposing a real-time drowsiness detection system that is both accurate and practical. The system utilizes a webcam to capture and record the driver’s facial expressions, employing specific techniques to analyse movement in each frame. By comparing calculated values with predefined thresholds, the system can effectively detect drowsiness. Additionally, the system includes alcohol detection capabilities using gas and ultrasonic sensors to prevent accidents. Importantly, this model system is designed to be compatible with all types of vehicles.

Enhancing Domestic Violence Investigations: Leveraging Smart Water Technology for Forensic Detection and Perpetrator Identification

Authors: Dr Foram Pandya, Ms. Dipal Bhayani
Abstract: Domestic violence represents a pervasive and deeply concerning issue that affects individuals and families worldwide. Combating this societal problem requires innovative approaches that empower law enforcement agencies and enhance investigative capabilities. SmartWater technology offers a unique forensic solution by providing an invisible, traceable marking that can be applied to various items within a household. This marking serves as a potent deterrent to potential offenders, as they are aware that their actions can be traced back to the scene of the crime. In domestic violence cases, Smart Water technology plays a crucial role in two primary aspects: forensic detection and perpetrator identification. Firstly, Smart Water’s forensic detection capabilities allow investigators to mark items and areas prone to incidents within a household discreetly. These markings serve as silent witnesses, aiding in reconstructing events and identifying critical pieces of evidence. Secondly, SmartWater facilitates perpetrator identification by linking marked items or individuals with the scene of the crime. This research article presents a critical analysis of SmartWater technology and its application as forensic evidence, particularly in the context of domestic violence cases, with a focus on India where domestic abuse remains persistently prevalent.

Decision – Based Algorithm for Automated Waste Segregation and Management Using Internet of Things

Authors: Assistant Professor Pavithra S, Janapriya R, Jawahar K P, Mahima R, Mowlitharan V

Abstract: To improve environmental sustainability, this paper presents an intelligent IoT-based smart waste management system that streamlines the waste sorting procedure and provides real-time monitoring. Using a Node MCU microcontroller and moisture, ultrasonic, and conductivity sensors, the system uses a decision-based algorithm to accurately sort waste into three categories: wet, dry, and metallic. A cloud-based analytics platform receives real-time data from ultrasonic sensors that continuously measure the bins’ fill level. Using a data transmission algorithm, the system automatically notifies users via SMS or Telegram when the fill level reaches a preset level, enabling timely waste collection and avoiding overflow.

Early Detection Of Stroke Risk Factors Using Machine Learning Models

Authors: Pravin P, Vinodhkumar S,, Siva Sankaralingam G

Abstract: The occurrence of strokes through a model and prediction helps to find out the utilizing data on demographic aspects, lifestyle, and other parameters of a fairly well-known and public healthcare dataset containing information about age, gender, hypertension, heart disease, smoking, BMI, and average glucose level. Preprocessing of the data involved dealing with missing values, encoding the categorical variables, and balancing the data through the Synthetic Minority Oversampling Tech- nique (SMOTE) to overcome the problem of imbalance. Then, several algorithms were trained and tested, including Logistic Regression, Decision Trees, Random Forest, SVM, and Naive Bayes, and the performance was evaluated in terms of accuracy, precision, recall, and F1 score. The results show that ensemble and tree-based algorithms obtain high precision with more than 90% accuracy in predicting who could have a main risk for stroke. Onset feature importance shows age, hypertension, heart disease, and glucose level as important predictors. The gists from the results show that potential exists in machine-learning methods for early risk assessment of stroke and strongly support the implementation of data-driven tools in clinical decision-making to provide timely intervention to reduce stroke morbidity and mortality.

Evaluation of Emulsion-Based Warm Mix Asphalt Using Marshall Mix Design

Authors: Research Scholor Mr. Arun Kumar Pyasi, Assistant Professor Mr. Hariram Sahu

Abstract: This study evaluates the extended performance and environmental benefits of Warm Mix Asphalt (WMA) prepared using a medium-setting bitumen emulsion and VG 30 binder. Building on prior mix design optimization, this work investigates moisture susceptibility and tensile strength performance across varying conditions. Indirect Tensile Strength (ITS) tests were conducted at 5°C to 40°C and showed that mixes with a 70:30 bitumen-emulsion ratio at 120°C achieved a peak ITS of 1.14 MPa at 25°C. Tensile Strength Ratio (TSR) values exceeded 80%, indicating strong resistance to moisture damage. Retained Stability tests confirmed the durability of the mix with a value of 85.6%, well above the minimum threshold. Additionally, fuel efficiency analysis for a hypothetical pavement section demonstrated a 25–30% reduction in diesel consumption when using WMA instead of HMA. This translated to a 28% reduction in CO₂ emissions per ton of mix. These findings reinforce the potential of emulsion-based WMA as a technically viable and environmentally superior alternative for sustainable pavement construction in India.

Mechanical Behavior of Fly Ash-Based SIFCON Reinforced with Hooked-End Steel Fibers for High-Strength and Sustainable Structures

Authors: P.Parthiban, Dasari Sai Vishnu Babu, Shaik Mustafa, Molla Baji

Abstract: Slurry-Infiltrated Fibrous Concrete (SIFCON) is a high-performance cementitious composite recognized for its outstanding ductility, impact resistance, and strength. This study evaluates the effects of varying hooked-end steel fiber content (1%, 3%, 5%, 7%, and 9%) and partial fly ash replacement on the flexural behavior of SIFCON. Designed to enhance sustainability and structural efficiency, the research explores how different fiber volumes and matrix compositions influence mechanical performance. Using simply supported beams tested under three-point bending, key parameters such as load capacity, deflection, crack patterns, and energy absorption are assessed. The findings reveal that flexural strength and toughness improve with increased fiber content, peaking at 8% volume. However, higher fiber concentrations lead to workability challenges and fiber clustering, which hinder stress uniformity. The study concludes that fly ash-based SIFCON with optimized fiber reinforcement offers a sustainable and robust solution for structural applications requiring superior flexural performance.

DOI: https://doi.org/10.5281/zenodo.15963222

STUDY ON PERFORMANCE OF SELF-COMPACTING CONCRETE USING SCBA AND GGBS FOR SUSTAINABLE CONSTRUCTION

Authors: Shankar.K, Mrs.J.ANITHA, M.E.

Abstract: Concrete is the most widely used construction material in the world, and its production is responsible for a significant amount of CO2 emissions, making it a major contributor to global warming. Selfcompacting concrete (SCC) is a type of concrete that can flow under its own weight and fill all the spaces in the formwork without the need for external vibration, which makes it more sustainable compared to traditional concrete. In this study, the performance of SCC using Sugarcane bagasse ash (SCBA) and Ground granulated blast furnace slag (GGBS) as mineral admixtures was investigated for sustainable construction. The study focused on determining the optimum percentages of both SCBA and GGBS to produce SCC with enhanced properties. The SCC mix with SCBA10 GGBS20 achieved a compressive strength, which is significantly higher than the control mix without any mineral admixtures. The flexural strength and tensile strength of SCC mixes with SCBA10 GGBS20 were also higher than the control mix. In terms of durability, the SCC mixes with SCBA10 GGBS20 exhibited better resistance to water penetration, chloride ion penetration, and acid attack compared to the control mix. The UPV test results showed that SCC mixes with SCBA10 GGBS20 had a more uniform and dense structure, which indicates better overall durability. The study is aligned with Sustainable Development Goal 12 (SDG 12) of the United Nations, which aims to ensure sustainable consumption and production patterns. The optimal mix of SCBA10 GGBS20 can lead to the production of high- performance SCC, which is crucial for sustainable construction practices. In conclusion, this study demonstrates the feasibility of using SCBA and GGBS as mineral admixtures in SCC production to enhance its performance and sustainability. The study's findings provide valuable insights for researchers, engineers, and construction professionals to develop sustainable and costeffective concrete mixes for construction projects.

The Evolution And Strategic Imperative Of HR: Toward A New Model Of Organizational Impact Measurement

Authors: Assistant Professor Dr. Atul Kumar, Professor Dr. Vinit Kumar Sharma

Abstract: Over the course of the last hundred years, the Human Resources (HR) profession has undergone a profound evolution. What was once regarded primarily as an administrative and compliance-driven function has steadily developed into a critical strategic component within modern organizations. Initially tasked with duties such as payroll management, employee record-keeping, and enforcement of labor laws, HR has now assumed a broader and more influential role—one that encompasses talent management, leadership development, organizational culture, and workforce planning aligned with business objectives. Despite this strategic repositioning, a significant challenge continues to limit the credibility and impact of the HR function: the absence of comprehensive and reliable mechanisms for measuring its true contribution to organizational success. Traditional HR metrics, while useful for tracking operational efficiency (e.g., turnover rates, time-to-hire, or training hours), are often insufficient in demonstrating the extent to which HR initiatives support or drive strategic outcomes. As businesses face increasing pressure to quantify return on investment across all departments, HR must develop more sophisticated tools to validate its role as a value-adding partner. This paper addresses this critical issue by examining the limitations of conventional HR measurement systems and emphasizing the need for a more integrative and multidimensional approach. Drawing upon both theoretical frameworks and empirical evidence, the study proposes a comprehensive model designed to assess the influence of HR on organizational performance. This model goes beyond input-output measures and includes three core dimensions: people-related outcomes (such as employee engagement and leadership effectiveness), process efficiencies (such as the agility of HR interventions and innovation in talent practices), and performance metrics (including business growth, productivity, and customer impact). By capturing the complex interplay between human capital and business execution, this proposed framework aims to provide organizations with a practical and evidence-based method to assess the strategic value of their HR functions. Ultimately, the goal is to support HR’s continued evolution into a fully integrated and analytically grounded contributor to sustainable business success.

DOI: http://doi.org/10.5281/zenodo.16743969

Smart Tongue Diagnosis For Gastrointestinal Diseases Using ResNet50

Authors: Anjali Kadam, Aishwarya Bhosale, Vaishnavi Jadhav, Swara Chavan, Dnyaneshwari Mohotkar

Abstract: Tongue diagnosis has traditionally been a non-invasive method for detecting gastrointestinal (GI) disorders, widely practiced in Eastern medicine. This research explores the use of a fine-tuned ResNet50 model for tongue image classification to aid in the diagnosis of gastrointestinal (GI) disorders. The model was trained on labeled images focused on three conditions: fissure, constipation, and hyperacidity. The dataset was manually collected from patients with assistance from an Ayurvedic practitioner, including hospital visits and shared tongue images. Preprocessing and augmentation techniques were applied to enhance generalization. The model achieved 80–97% accuracy on known images but dropped to 50–60% on unseen data, highlighting the need for a larger dataset. This project is intended as a foundation for future research, with the expectation that
the accuracy and number of diagnosable conditions will improve as the dataset expands.

DOI: http://doi.org/

SECURITY ENHANCED WSN DSR PROTOCOL TO PREVENT BLACK HOLE ATTACKS ON MANETS

Authors: Jitendra Sharma, Professor Amit Thakur

Abstract: Wireless Sensor Networks (WSNs) demand energy-efficient and reliable routing mechanisms due to the constrained resources of sensor nodes and the dynamic nature of wireless links. Traditional Dynamic Source Routing (DSR) operates efficiently in on-demand route discovery but fails to account for multiple correlated parameters such as residual energy, link stability, delay, and packet reception rate, which are critical in WSN environments. In this paper, we propose a Principal Component Analysis based Dynamic Source Routing (PCA-DSR) protocol that integrates statistical feature reduction with classical DSR. Multiple network and link parameters are periodically collected and transformed using PCA into a single principal component score that reflects overall route quality. This score is embedded in route discovery and maintenance phases to enable the selection of stable and energy-aware paths. Simulation results demonstrate that PCA-DSR achieves higher packet delivery ratio, reduced end-to-end delay, balanced energy consumption, and extended network lifetime compared to conventional DSR. The proposed approach highlights the effectiveness of dimensionality reduction techniques in enhancing routing decisions for resource-constrained WSNs.

DOI: http://doi.org/10.5281/zenodo.16948386

An Analysis on Attacks and Defense Metrics of Routing Mechanism in Wsn Mobile Ad Hoc Networks.

Authors: Bhupesh Paliwal, Professor Amit Thakur

 

Abstract: A Mobile Ad hoc Network (MANET) is a dynamic wireless network that can be formed infrastructure less connections in which each node can act as a router. The nodes in MANET themselves are responsible for dynamically discovering other nodes to communicate. Although the ongoing trend is to adopt ad hoc networks for commercial uses due to their certain unique properties, the main challenge is the vulnerability to security attacks. In the presence of malicious nodes, one of the main challenges in MANET is to design the robust security solution that can protect MANET from various routing attacks. Different mechanisms have been proposed using various cryptographic techniques to countermeasure the routing attacks against MANET. As a result, attacks with malicious intent have been and will be devised to exploit these vulnerabilities and to cripple the MANET operations. Attack prevention measures, such as authentication and encryption, can be used as the first line of defense for reducing the possibilities of attacks. However, these mechanisms are not suitable for MANET resource constraints, i.e., limited bandwidth and battery power, because they introduce heavy traffic load to exchange and verifying keys. In this paper, we identify the existent security threats an ad hoc network faces, the security services required to be achieved and the countermeasures for attacks in routing protocols. To accomplish our goal, we have done literature survey in gathering information related to various types of attacks and solutions. Finally, we have identified the challenges and proposed solutions to overcome them. In our survey, we focus on the findings and related works from which to provide secure protocols for MANETs. However, in short, we can say that the complete security solution requires the prevention, detection and reaction mechanisms applied in MANET.

Machine Learning for Performance and Fault Detection in Thermal Power Plants

Authors: Praveen bodana, Assistant Professor Khemraj Beragi

Abstract: Thermal power plants (TPPs) are a critical component of global electricity generation, yet they often suffer from efficiency loss and unplanned outages due to equipment faults. Traditional maintenance strategies (reactive or preventive) are often too slow or costly. In contrast, machine learning (ML) methods can analyze large historical and real-time sensor data to detect anomalies and predict failures early. This paper surveys supervised methods (SVM, random forests, neural networks), unsupervised models (autoencoders, clustering, PCA), and hybrid physics-ML approaches for TPP monitoring. It also examines sensor optimization and IoT-enabled real-time monitoring. Case examples from the literature show that ML-based predictive maintenance can greatly reduce unplanned downtime and maintenance costs (e.g., cutting costs by roughly 20–40%) while improving equipment availability. The findings indicate that optimized sensor networks, integrated IoT data, and advanced ML models can substantially enhance fault detection accuracy and overall plant efficiency.

DOI: http://doi.org/10.5281/zenodo.16964139

Performance Comparison Of Segmental, Helical, Flower, And Hybrid Baffle Configurations In Shell-and-Tube Heat Exchangers

Authors: Ashwani sagar, Assistant Professor Khemraj Beragi

Abstract: Shell-and-tube heat exchangers remain vital in industrial applications, and baffle design plays a key role in their thermal performance. This review paper provides a comprehensive comparison of four baffle configurations – segmental, helical, flower, and hybrid – highlighting their impact on heat transfer and pressure drop characteristics. Conventional segmental baffles generate strong cross-flow and high heat transfer but suffer from flow stagnation regions and significant pressure losses. Helical baffles have been developed to promote a smoother shell-side flow, yielding comparable heat transfer with markedly reduced pressure drop and fouling tendency. Flower baffles, a newer biomimetic design, employ petal-like baffle plates to induce swirling flows, achieving an excellent compromise between enhanced convective heat transfer and lower pumping power requirements. Hybrid baffles combine features of segmental and helical designs to further intensify heat transfer, albeit with some pressure drop penalty. The paper synthesizes findings from recent experimental and computational studies (including the author’s thesis work) to quantitatively compare performance metrics of these baffle types. A comparative analysis is presented with a summary table of key metrics and a graphical illustration of heat transfer vs. pressure drop trade-offs. The review also discusses practical considerations, such as manufacturing complexity and fouling behavior, and identifies research gaps. Overall, advanced baffle configurations demonstrate significant potential for improving energy efficiency in heat exchangers, and ongoing innovations in baffle design offer promising opportunities for future thermal performance enhancements.

DOI: http://doi.org/10.5281/zenodo.16981738

Review Of Novel Approach Of WSN Routing To Data Communication Between Sensor Node On Energy Warning

Authors: Pankaj kumar singh, Professor Amit Thakur

Abstract: Energy utilization via every node is a significant concern in Wireless Sensor Network (WSN). Therefore, the main complexity deception in communicating the data that have the route with to the lowest degree distance as well as concentrates energy. Many investigators have residential different routing approaches for Cluster Head (CH) collection to communicate the packets to the BS. The choice of suitable CH, through the location also energy, is a main dispute in WSN. But, it can’t focuses on the network delay. Thus it decreases the network efficiency. To overcome this problem this paper Energy and data Communication delay aware Routing in WSN. Here, the fitness function is introduced for enhancing both the energy efficiency as well as lifespan of nodes through choosing the CH optimally. In this strategy, distance, energy, and delay of sensor nodes fitness function is used for selecting the optimal CH in the network. The network function is enhanced in this approach when equated to the conventional protocol.

Energy Infrastructure As A Catalyst For Mineral-Based Industrialization In Africa: A U.S. Investment Perspective

Authors: Raymond Ashieyi-Ahorgah

Abstract: – Africa's abundant mineral resources present unprecedented opportunities for industrial transformation, yet the continent's industrial development remains constrained by inadequate energy infrastructure. This study examines the critical relationship between energy infrastructure development and mineral-based industrialization in Africa from a United States investment perspective. Drawing on recent empirical evidence and policy developments through 2025, we analyze how strategic energy investments can unlock Africa's mineral wealth while creating sustainable industrial value chains. Our analysis reveals that energy infrastructure serves as a fundamental catalyst for mineral-based industrialization, with renewable energy transitions offering particular promise for long-term sustainable development. The findings suggest that U.S. investments in Africa's energy infrastructure, particularly in renewable energy systems, can generate substantial returns while supporting the continent's industrial transformation. We recommend targeted investment strategies that leverage public-private partnerships and address key barriers including financing constraints, regulatory frameworks, and technical capacity limitations.

DOI: https://doi.org/10.5281/zenodo.17212450