This issue comprises articles presented at the 3rd International Conference on Emerging Applications of Artificial Intelligence, Machine Learning, and Cybersecurity (ICAMC 2025), held on May 1–2, 2025, and organized by HMR Institute of Technology and Management, New Delhi, India. ICAMC 2025 emphasizes both the foundational scientific principles essential for integrating intelligence and the advancement of technologies, tools, architectures, and infrastructure required for system development, with a focus on the design, implementation, and exploration.
Proceeding Articles:
CRIME PREDICTION AND ANALYSIS USING MACHINE LEARNING
Authors: Anant Samrat, Amar Deep Gupta, Shubham Dadwal, Adarsh Samrat,, Mayank, Priya Kumari
Abstract: Crime is a significant challenge in modern society, necessitating effective prevention strategies. Machine learning (ML) offers promising solutions for crime analysis and prediction. This study explores algorithms like Naive Bayes, SVM, Linear Regression, Decision Trees, Bagging, Stacking, and Random Forest for accurate crime prediction. The proposed Naive Bayes-based model achieved 99.9% classification accuracy on test data, outperforming previous models. By integrating empirical data and criminological insights, this approach effectively forecasts crimes, reducing crime and deterring criminal activities.
DOI: https://doi.org/10.5281/zenodo.16409884
AI-BASED GESTURE RECOGNITION FOR EMERGENCY SITUATIONS USING SVM AND OpenCV
Authors: Ms. Aneesha Shokeen, Mr. Yash Mittal
Abstract: In emergency situations, quick response and hands-free communication are critical for safety. This research introduces an AI-driven gesture recognition system designed to activate an SOS alert using simple hand gestures. The system employs MediaPipe for precise hand tracking, an SVM classifier for real-time gesture recognition, and an integrated SMS alert system that includes GPS location tracking. The proposed approach ensures accessibility for individuals in distress, particularly those with disabilities or in high-risk environments where traditional emergency triggers may be impractical. The experimental results show a 95.19% accuracy in gesture classification, demonstrating the system’s effectiveness in real-world scenarios. Future work aims to incorporate deep learning-based recognition models and deploy the system on wearable and mobile platforms to enhance usability and responsiveness
DOI: https://doi.org/10.5281/zenodo.16410503
Enhancing Classroom Attendance Systems By Face Recognition Using OpenCV And ESP32-CAM
Authors: Vishal Kumar Pandey, Vishal Jaiswal, Vishal Yadav, Shilpee Patil
Abstract: Classroom attendance tracking was a fundamental task in educational institutions, traditionally managed through manual roll calls or sign-in sheets. These methods were time-consuming, error-prone, and susceptible to manipulation. With advancements in computer vision and embedded systems, there was an opportunity to automate this process. In this research paper, a novel approach to classroom attendance management was presented, utilizing OpenCV and face recognition technologies, implemented on the ESP32-CAM microcontroller. The proposed system was designed to automatically identify and record student attendance, offering enhanced accuracy and efficiency. Comparative results demonstrated that the face recognition-based approach significantly outperformed traditional manual methods and other automated systems in terms of accuracy and processing speed. The system's architecture, implementation, and evaluation were outlined, showcasing its potential to transform attendance tracking in educational settings.
DOI: https://doi.org/10.5281/zenodo.16410064
Multimodal Approaches Of Mental Stress Detection: A Comparative Study
Authors: Senthil Kumar T, Vedant Kolhe, Rithvee Chandak
Abstract: Recently mental health has been regarded as an important issue with stress being one of the factors behind many health conditions. Prompt detection of mental stress is critical in preventing chronic conditions. Artificial intelligence has been helping to fight against chronic stress and tension. This study provides a review of the current understanding of stress and artificial intelligence as well as the approaches for overcoming it with AI algorithms. Some of the approaches studied in development include LSTM networks self-organizing maps and natural language processing applied to datasets. The comparative analysis of these methods enables us to determine the most successful approaches their limitations and ways in which they can be improved.
DOI: https://doi.org/10.5281/zenodo.16410131
Revolutionizing Solar Efficiency Harnessing Iot Innovation For Intelligent Dust Monitoring And Cleaning Solutions
Authors: Usha Dhankar, Nikeeta, Sompriya N Tiwary, Suhani Singh, Pooja Sharma, AS Susanna Grace
Abstract: Solar photovoltaic (PV) panels were a broadly implemented renewable energy source but their efficiency was substantially influenced by dust accumulation which hindered sunlight absorption and reduced power output Regular cleaning and monitoring were essential to sustain their performance Traditional cleaning mechanisms such as manual or semiautomatic cleaning were often inefficient labor-intensive and costly which demanded the development of automated solutions This research introduced an IoTbased cleaning and monitoring system designed to enhance the efficiency of solar PV panels The system combined realtime data acquisition through IoT sensors to detect dust accumulation and environmental conditions activating an automated cleaning mechanism when necessary Additionally machine learning algorithms analyzed historical data to optimize cleaning schedules maintaining minimal energy loss and improved reliability A review of prevalent dust removal techniques such as passive coatings electrostatic cleaning and robotic solutions revealed that many methods were either highmaintenance or not costeffective for largescale deployment IoTbased solutions when integrated with predictive analytics provided a potential substitute by enabling realtime monitoring and analytical decisionmaking for panel maintenance The outlined methodology enhanced energy output while reducing operational costs and minimizing manual intervention making solar energy systems more efficient and sustainable This innovation contributed to the prolonged effectiveness of solar power by addressing one of its key operational challenges thereby fostering a cleaner and more reliable renewable energy future.
DOI: https://doi.org/10.5281/zenodo.16410228
Designing Edge Architectures For Underwater Sensor Networks To Enable Realtime Data Processing In Extreme Environments
Authors: Yajat Singh, Ms. Gurpreet Kaur, Barun Singh Bisht, Pushpam Kumar
Abstract: Underwater Sensor Networks USNs play a critical role in environmental monitoring marine exploration and defense applications. However traditional cloudbased data processing introduces significant latency and energy consumption making realtime decisionmaking challenging in extreme underwater environments. This paper proposes a novel edge computing architecture tailored for USNs enabling localized realtime data processing and anomaly detection. The architecture integrates a CNNLSTM deep learning model optimized for lowpower edge devices significantly reducing the need for cloudbased processing. Our experimental evaluation demonstrates a 39 reduction in latency and a 36 improvement in energy efficiency compared to cloudbased solutions. Additionally we present performance benchmarks showing a higher packet delivery ratio and improved data throughput. The proposed approach enhances the autonomy and efficiency of underwater sensor networks making it a viable solution for realtime applications in extreme environments.
DOI: https://doi.org/10.5281/zenodo.16610646
Enhancing Flower Identification Using Deep Learning: A Comparative Study Using Multi-Statistical Models
Authors: Himanshu Shahoo, GautamYadav, ChinmayeeTripathy, Padmaja Panda
Abstract: Flower identification is a crucial aspect of plant classification and ecological research, playing a significant role in understanding biodiversity and ecosystem dynamics. This research paper presents a new approach to flower identification using advanced deep learning techniques. The proposed system used folding networks (CNNs) to automatically extract hierarchical features from high-resolution images of flowers, allowing for more accurate and efficient classification. The procedure is implemented as a multi-stage process, beginning with data preprocessing to enhance image quality and remove noise. Using another data record, educated CNN models such as modified reset 50, VGG16, or Google are then fine-tuned with commented flower images. Furthermore, transfer learning is used to properly use knowledge from large data records and improve the ability of models to generalize different types of flowers.. In the end, our approach achieved an accuracy of 82.04% using VGG16, the highest compared to other algorithms.
DOI: http://doi.org/10.5281/zenodo.16610684
Role of Django inWeb Application Development
Authors: Saba Zaidi, Thakur Nikhil, Tripti Goyal, Veersavarkar
Abstract: To meet the need of productivity concerns, project timelines, and changing needs, this research explores the interesting realm of web service development. The overall purpose of this research is to develop an easy-to-use and effective development system based on the Django framework. This provides programmers with the facility to simply develop web services that are efficient, effective, and reliable. Utilizing the Model-View-Template (MVT) design pattern is important, as it is compatible with list management systems. The overall effectiveness and efficiency of the system are improved by web page creation being automated using HTML, CSS, and Python modules; protocols for data sharing are standardized, system users are decentralized, and user login and registration processes are accelerated are all prioritized at their best. My SQL maintains the data base efficiently, and Django manages the smooth data interaction to provide an integrated and efficient user experience. Another central area of focus in this research is the development of a web application that provides secure, real-time user interactions while encrypting data to preserve its confidentiality and integrity. Django REST framework is employed to create a stable service that integrates with the front-end seamlessly through REST APIs. This allows HTML/CSS and JavaScript to drive a dynamic and interactive user interface. The research points out the key features of Django, including its administrative capabilities, Object-Relational Mapping (ORM), comprehensive documentation, secure and rapid development features, and REST API support. A deeper understanding of this dynamic subject attempts to shed light on the development, importance, challenges, and modern solutions in web technology and web service development. Following our research, the goal is to use Django to develop are liable, effective, and secure online application. Our goal is to use all of its characteristics to streamline the development process. Django's solid frame work promises the assurance of scalability and reliability .Our aim is to utilize its benefits for an extensive, modern, and efficient web service creation, ensuring a successful outcome meeting the increasing demands for efficient web services. In today’s digital world, websites and web applications play a very important role in how we communicate, do business, and share information. To build these websites, developers use tools called web frameworks. One of the most popular frameworks is Django, which is written in the Python programming language. This research paper explains how Django helps developers create websites faster and more efficiently. Django follows a structure called MVC (Model-View-Controller), or in Django’s case, MTV (Model-Template-View). This helps keep the code organized and easy to manage. Django also comes with many built-in features like user authentication, database management, security, and admin interface, which save time and effort for developers. The paper highlights Django’s advantages like its security features, scalability, and reusability of code. It also compares Django with other popular frameworks to show where Django performs better and where it might not be the best choice. In short, Django is a powerful tool that allows both beginners and professional developers to build high-quality web applications quickly and securely. This research explores Django’s role in modern web development and why it is a preferred choice for many developers and companies .The research by Idris et al. emphasizes Django's comprehensive nature, highlighting its suitability for developers seeking a full-featured framework that handles various aspects of web development out-of-the-box. This contrasts with frameworks like Flask, which offer more flexibility but require additional setup for features that Django provides by default. Moreover, Django's emphasis on security is notable. It includes protections against common web vulnerabilities like cross-site scripting (XSS), cross-site request forgery (CSRF), and SQL injection, ensuring that applications built with Django are robust and secure.
Blockchain-Based Courier Tracking Services Using Smart Contracts
Authors: Deepti Ram Gangurde, Arun Mishra, Shantanu Singh
Abstract: This research proposes a decentralized courier tracking system using blockchain technol- ogy and smart contracts, aimed at enhancing transparency, trust, and security in logistics. The solution is implemented on the Volta blockchain and integrates MetaMask[3] to facilitate se- cure interactions between participants without relying on centralized intermediaries. The sys- tem automates shipment updates, maintains immutable tracking records, and protects sensitive data through cryptographic mechanisms. The implementation demonstrates improved trace- ability, operational efficiency, and stakeholder accountability. Performance evaluation indi- cates significant enhancements in security, cost-effectiveness, and scalability when compared to conventional courier tracking methods. The proposed system offers a robust alternative for modern supply chain management[6].
Polyglot: Deep Learning-Powered Language Translation
Authors: Sharath Chandra Kodtihyala, Riddhi kinnera, Shashikiran Sangisetti, Praveem Kumar, Prasanthrao A
Abstract: This study presents Polyglot, a deep learning-based language translation system that utilizes Transformer, LSTM, Attention, and Seq2Seq models to enhance context-aware translation. While well-known systems like Google Translate provide reliable translations, Polyglot offers improved contextual understanding through a hybrid approach that balances accuracy and efficiency. The study evaluates Polyglot’s performance using BLEU scores and user satisfaction, demonstrating its effectiveness. It includes a detailed discussion on the dataset, model architecture, training process, and evaluation criteria. The results indicate a significant improvement in translation quality compared to baseline models. Future work will focus on real-time improvements and customization to further enhance translation accuracy and user experience
Autonomous Penetration Testing with Cyberguardian: A Large Language Model-Based Approach
Authors: Jeslin Hashly, Jestin K Sunil, Alby Shinoj
Abstract: This paper introduces CyberGuardian, a new LLM-based agent for autonomous penetration testing. CyberGuardian is composed of two parts: a planner and a summarizer. These parts cooperate to create and carry out commands in an iterative manner. To evaluate CyberGuardian, we introduce two new benchmark suites based on the popular Capture the Flag (CTF) systems PicoCTF and OverTheWire, comprising 200 challenges in various domains and levels of difficulty. Our experiments check CyberGuardian's most critical parameters, such as levels of creativity and token usage, on LLM. Results reaffirm the need of good security procedures and show how LLM-based agents can advance autonomous penetration monitoring.
Comparisons of Machine Learning Algorithms for Fraud Detection
Authors: Sudhanshu Gupta, Avinash Aganihotri, Harsh Sharma, Tanya Handa
Abstract: More people understand the use of technology and that is being used on their daily life. This will increase the chances of losing valuable data and information to the scammers who might use your data for your own detriment or have a word or a spell with you or harm you in any possible manner or way. Consequently, fraud detection Systems are employed in different fields of businesses such as banking, e-commerce, healthcare, and cybers security to identify and terminate fraud. They are essential because of the prevention of monetary losses, the protection of private information, the attainment of client confidence, and compliant with legal requirements. Some of the modern systems employ machine learning methods, while supervised learning methods are adopted to ascertain pre-defined fraud patterns and the unsupervised ones to extract anomalies. Techniques to increase precision of the identification of fraud include anomaly detection, graph based method and ensemble. Consequently, to guarantee an effective fraud detection for user it is necessary to find best fraud detection algorithm while maintaining regulatory standards and customer satisfaction , the best fraud detection algorithm must handle all aspects; efficiency, false positive disrupts, F1 score, dealing with imbalanced data and cost.
Student Dropout Forecasting with Machine Learning: A Review
Authors: Mohammed Obaid Baba, Muddam Siddartha, Pulluri Sai Vardhan, Swati Sucharita, M.A Jabbar
Abstract: The rapid evolution of machine learning (ML) technologies has significantly impacted various sectors, including education. This analysis reviews the advancements in machine learning-driven models within the educational system, highlighting their roles in enhancing teaching methods, supporting personalized learning, and predicting student performance. By employing a range of ML techniques from traditional algorithms to hybrid and deep learning approaches educators can better assess student engagement, identify at-risk learners, and tailor interventions to improve academic outcomes. The review also explores key applications such as early academic performance prediction, intelligent tutoring systems, and adaptive learning environments that respond dynamically to individual student needs. Despite the promising results, challenges such as data privacy concerns, ethical considerations, and the need for comprehensive, unbiased datasets persist. This review aims to provide a holistic view of how machine learning is reshaping the educational landscape, while discussing existing limitations and suggesting future directions to maximize the benefits of ML in education.
Finlytics AI: Financial Platform Using Artificial Intelligence
Authors: Assistant Professor Mr Pradeep, Mr. Kunal Pandey, Mr Deepanshu Tyagi
Abstract: Effective financial management is essential for individuals and businesses to track income, expenses, and overall financial health. This study presents Finlytics AI, an intelligent finance and budget management platform that leverages machine learning to enhance financial tracking, budgeting, and analysis. By integrating real-time transaction categorization, AI-powered receipt scanning, and interactive financial visualizations, the system provides users with deeper insights into their spending habits. The platform also supports multi-account tracking, recurring transaction management, and automated budget alerts to help users maintain financial discipline. With AI-driven financial reports and trend analysis, Finlytics AI empowers users to make informed financial decisions, improving both short-term budgeting and long-term financial planning. Through advanced data analytics and automation, this approach enhances the efficiency, accuracy, and accessibility of financial management, offering a scalable and intelligent solution for personal and business finance.
Design and Implementation of a Full-Stack Healthcare Appointment Scheduling System
Authors: Ms. Suman, Mr. Kartik Gossain
Abstract: Healthcare appointment scheduling is crucial for improving patient access and optimizing medical resources. Traditional booking methods often lead to inefficiencies, delays, and poor user experience. This research presents the design and implementation of MediConnect, a Full-Stack Healthcare Appointment Scheduling System, developed using the MERN (MongoDB, Express.js, React, Node.js) stack. The system enables seamless appointment booking, user authentication, real-time availability updates, secure payments, and role-based access for patients, doctors, and admins. The MERN stack was chosen for its scalability, flexibility, and performance, offering advantages over traditional web technologies. Implementation results demonstrate improved efficiency and accessibility in healthcare booking. Future work may include AI-driven doctor recommendations, telemedicine integration, and enhanced security measures.
Universal Encryption For Secure Cloud Storage
Authors: Senthil Kumar T, Mardeni Roslee, Jayapradha, Shubhanshu Tiwari, Pranjal Mishra
Abstract: Classroom attendance tracking was a fundamental task in educational institutions, traditionally managed through manual roll calls or sign-in sheets. These methods were time-consuming, error-prone, and susceptible to manipulation. With advancements in computer vision and embedded systems, there was an opportunity to automate this process. In this research paper, a novel approach to classroom attendance management was presented, utilizing OpenCV and face recognition technologies, implemented on the ESP32-CAM microcontroller. The proposed system was designed to automatically identify and record student attendance, offering enhanced accuracy and efficiency. Comparative results demonstrated that the face recognition-based approach significantly outperformed traditional manual methods and other automated systems in terms of accuracy and processing speed. The system's architecture, implementation, and evaluation were outlined, showcasing its potential to transform attendance tracking in educational settings.
DOI: https://doi.org/10.5281/zenodo.16440464
Food Waste Management And Giving App
Authors: Gautam Yadav, Sakshi Singh, Dharna, Ankit Kumar, Deepanshu Bhola, Aryan
Abstract: Food waste is growing daily, and hunger is a major problem in the globe today. An online food management system called Surplus Food for Orphanage (SFO) oversees excess food for malnourished individuals who don't have enough to sustain themselves. The goal of the study is to create a web-based platform called "Surplus Food for Orphanage" that facilitates communication between food seekers and donors. This paper is an example of a new online platform that will be useful for giving away used items and surplus food to anyone in need. The donor can create an account on this website. Donors can access this website by logging into their accounts after completing the registration process. The donor will publish their post by providing the name of the food item, the amount of food they wish to donate, their location, and their phone number. Food waste will be lessened thanks to this technique, which will also encourage more people to give food to orphanages.
DOI: https://doi.org/10.5281/zenodo.16440477
Vision Play – Using Advance Artificial Intelligence And Machine Learning Algorithms
Authors: Usha Dhankar, Aditya Prakash Rai, Harsh Maheshwari, Deepanjal Uppal, Ankit Singhal
Abstract: Vision Play" is an advanced AI-driven video analysis system based on artificial intelligence, machine learning, and computer vision that is aimed at redefining traditional visual data processing. Initially designed to support football analysis, the platform has grown to be a flexible and scalable architecture used in sports, surveillance, and real-time monitoring applications. The system supports current models like YOLOv5 for real-time object recognition, optical flow for movement tracking, and KMeans clustering for team or object identification. Perspective transformation is applied to translate pixel-level information to real-world coordinates, making possible precise speed, distance, and positioning measurement.The system handles video streams to identify, categorize, and track objects such as players, referees, or pedestrians with accuracy, even for very dynamic or crowded scenes. It produces relevant visualizations such as movement traces, heatmaps, and performance dashboards to enable users to gain profound insights into behavior trends and spatial dynamics. Built in modularity and real-time capacity, "Vision Play" can handle varied camera feeds and is extensible to cloud or edge infrastructures.Through automated processing of advanced video analysis operations, the system lowers human labor by a large margin and increases accuracy, uniformity, and decision-making efficiency. Its multi-industry suitability makes it a desirable asset for analysts, strategists, security organizations, and researchers seeking to leverage smart video insights for performance optimization, security enhancement, and data-driven operation.
DOI: https://doi.org/10.5281/zenodo.16444484
The Transformative Impact Of Artificial
Authors: Arsh Ahmed , Abhishek , Shivam Bhardwaj , Piyush Tiwari , Ms. Jyoti
Abstract: This comprehensive study examines the multifaceted impact of Artificial Intelligence (AI) on global education systems. Through an analysis of current implementations, case studies, and empirical data, we explore how AI-driven technologies are reshaping pedagogical approaches, institutional administration, and learning outcomes. The paper investigates adaptive learning platforms like Squirrel AI, ALEKS, and ALO7 through the lens of Bloom's 2 Sigma Problem, while critically analyzing both the transformative potential and ethical challenges of educational AI. Our findings suggest that while AI offers unprecedented opportunities for personalization and accessibility, its successful integration requires careful consideration of pedagogical, ethical, and socioeconomic factors. The study concludes with policy recommendations for balanced adoption in educational contexts.
DOI: https://doi.org/10.5281/zenodo.16444680
Retrieval-Augmented Generation For Intelligent Question Answering From OCR-Processed PDFs
Authors: Ms.Usha Dhankar, Ms. Preeti Kalra, Ms.Agrima Samanotra, Mr.Aaditya Shriv Astava
Abstract: This research explores the application of Retrieval-Augmented Generation (RAG) for enhancing information extraction and question-answering tasks from scanned PDF documents using Optical Character Recognition (OCR). By integrating a retrieval mechanism with a generative language model, we present a novel framework that intelligently interprets noisy, unstructured OCR outputs and enables contextual interaction via natural language queries[1][2]. The approach bridges the gap between image-based document archives and intelligent systems, facilitating improved document accessibility in fields like legal, academic, and archival research.
DOI: https://doi.org/10.5281/zenodo.16445198
AI-Driven Smart Home Remedy Advisor: Integrating Pytesseract Medicinal Plant Recognition And LLMs For Real-Time Symptom And Image-Based Analysis
Authors: Shubham Mishra, Meenu Garg, Neha Agarwal
Abstract: In an era where access to healthcare can be limited by geography, cost, or time constraints, the need for intelligent and accessible health support systems is more critical than ever. This project presents a smart, AI-powered home remedy advisor designed to provide users with real-time suggestions for natural remedies based on symptom inputs and visual content analysis. The system integrates Pytesseract for optical character recognition (OCR) of handwritten or printed symptom descriptions, medicinal plant recognition APIs for identifying natural treatment options from user-uploaded images, and Large Language Models (LLMs) for contextual understanding and generation of personalised remedy recommendations. The application enables both textual and image-based inputs, processing them with advanced AI to detect symptoms, match them with known herbal treatments, and deliver safe, practical, and easily accessible home remedies. This multi- modal approach enhances usability and broadens access to non- pharmaceutical treatment options, especially in rural or under- served communities. The solution is scalable and adaptable, with potential for integration into telemedicine ecosystems or wellness apps.
DOI: https://doi.org/10.5281/zenodo.16445463
Exploring The Capabilities Of ChatGPT-4 In Generative Text Tasks
Authors: Kanan Bajaj, Savita Baerda, Manni Kumar
Abstract: This research paper aimed to find out various things ChatGPT could do. Especially in the areas of reasoning, healthcare, and education, the authors observed how ChatGPT’s learning was more personal. It adapted to student needs, offering a personalized learning experience. This truly drew students into the equation. They found that ChatGPT’s skills in logical reasoning were effective for solving problems and performing critical thinking tasks. However, a large part of their research focused on healthcare. Here, they placed ChatGPT alongside other AIs such as Gemini and Copilot. They discussed how each of them was managed in terms of diagnostic accuracy and interac-tion. There were also some differences in specialization ChatGPT performed well with general medical questions and maintained coherent conversations. Nevertheless, Gemini and Copilot generally worked better when it came to specific medical operations because those programs were designed specifically for that purpose. The paper further explored how exactly ChatGPT operated in detail. It employed modern NLP techniques and certain methods from the field of machine learning. The authors believed its evolving design made it capable of handling numerous topics. However, they also explained that it had some moderate limitations at the time, and how it could potentially be im-proved in the future. Finally, they offered a brief overview of the strengths and weaknesses of ChatGPT depending on the area of application. Hopefully, it provided some valuable insights into where it stood in the ever-expanding li-brary of AI solutions.
DOI: http://doi.org/10.5281/zenodo.16605610
ANDROID BASED PICK AND PLACE ROBOTIC ARM VEHICLE
Authors: Srinivasan K, Thri shanth S, Thameswer U, ELLingesh M*, ANGOVAN K
Abstract: This project presents the design and implementation of an Android based pick and place robotic arm vehicle aimed at improving automation in industrial and hazardous workspaces The system consists of a robotic arm with four degrees of freedom mounted on a mobile platform that allows accurate object manipulation and controlled movement A Raspberry Pi is used as the central controller to operate motor drivers servos and sensors while receiving commands from a custom Android application Communication between the app and the Raspberry Pi is achieved wirelessly through Bluetooth or WiFi which enables real time control and monitoring An optional camera module is included to support image processing and object recognition giving the robot the ability to identify and sort objects with minimal human input This addition enhances the system’s adaptability to more complex tasks The use of open source hardware and software ensures that the solution remains cost effective scalable and accessible for small and medium enterprises During testing the robot successfully picked and placed items weighing up to 500 grams and responded effectively to user instructions sent through the app The Android interface provided a smooth user experience with intuitive controls The system performed reliably on flat surfaces but encountered minor difficulties on uneven terrain and showed limited gripper flexibility when handling irregular shaped objects This project highlights the potential of integrating mobile technology with robotics to reduce manual labor increase precision and improve operational safety in various fields The modular build and open design allow for easy future upgrades including artificial intelligence based object recognition adaptive gripping mechanisms and enhanced navigation over different types of surfaces The outcome of this project demonstrates a practical and efficient approach to developing robotic systems using widely available components and modern mobile interfaces
DOI: http://doi.org/10.5281/zenodo.16606087
OBSTACLE AVOIDING ROBOT CAR
Authors: Dr. Prakash P, Kannagi L, Aakash K, Amizhdhan L, Pragathesh Kumar
Abstract: The intelligent autonomous vehicle utilizing GPS and camera technology has been programmed to avoid obstacles in its environment. Unlike normal vehicles, this car combines computer vision features with GPS technology. The technology helps the car recognize obstacles and make evasive maneuvers in real-time. A camera is fixed on the car's chassis, and it is constantly recording the environment around it. The video frames are then analyzed using machine learning techniques to detect obstructions like walls, cars, pedestrians as well as anything else that may prevent the car from moving. The car is able to gather accurate visual information which helps it identify the obstacles shape, size, and position. In addition, the automobile contains a GPS module that provides adequate positioning to pinpoint the exact location of the car. The GPS module picks up signals from satellites to ascertain the car's current position with a high degree of accuracy. Likewise, the car also uses a decision-making algorithm that takes into consideration visual data from the camera, GPS data, and predefined permissible routes. The algorithm processes the relevant data and helps the system determine the most optimal route while avoiding obstacles. When an obstacle is detected in its path, the car automatically alters its trajectory to avoid the obstacle while maintaining its intended route. In summary, the obstacle-avoiding car that utilizes a camera and GPS module offers a promising approach to autonomous navigation [1]. By integrating computer vision methods with GPS positioning, the car can sense and react to its surroundings, ensuring safe and efficient travel in complex and ever-changing environments.
DOI: http://doi.org/10.5281/zenodo.16606351
The Role of Technology in Modern Marketing: Trends Tools and Future Directions
Authors: Gautam Yadav, Sachin Rawat, Ayush Ranjan, Mehul Sharma, Aditya Singh
Abstract: The rapid evolution of technology has revolutionized the field of marketing, enabling businesses to engage with customers more effectively, optimize campaigns, and drive sales. This paper explores the transformative role of technology in modern marketing, focusing on key advancements such as artificial intelligence (AI), big data analytics, automation, augmented reality (AR), virtual reality (VR), and blockchain. Beyond a conceptual review, this study contributes original findings through experimental evaluation of leading AI-powered tools such as IBM Watson and HubSpot. The comparative analysis quantifies setup time, engagement rate, ROI, and computational cost, offering practical guidance for tool adoption. The paper also addresses challenges like data privacy and ethical concerns and discusses emerging trends such as the metaverse and IoT integration. This hybrid approach makes the study a valuable resource for both academic researchers and industry professionals.
DOI: http://doi.org/10.5281/zenodo.16608872
AI-Powered Intrusion Detection System for Drone-Based Surveillance Environments
Authors: Mr.Ayush, Mr.Aditya
Abstract: The rapid advancements in artificial intelligence (AI) and drone technology have revolutionized surveillance, enabling real-time, automated security solutions. This paper presents an AI-powered intrusion detection system (IDS) for drone-based surveillance, leveraging YOLO (You Only Look Once) deep learning models for real-time object detection. The system autonomously identifies potential threats, such as weapons, sharp objects, or unauthorized personnel, and triggers automated alerts. By integrating high-definition cameras and AI-driven decision-making, the proposed system enhances security while reducing human intervention. Experimental evaluations confirm its efficiency in detecting intrusions with high accuracy. Future enhancements include integrating thermal imaging and LiDAR for improved detection.
DOI: http://doi.org/10.5281/zenodo.16608428
Career Compass: AI-Driven Placement Prediction and Personalized Career Development
Authors: Babu S, Preetish Majumdar, Devarenti Hemanth
Abstract: Career Compass is an AI-powered job recommendation and career development system aimed at optimizing university students’ job placement outcomes. This version integrates advanced ML models, user feedback loops, and dynamic APIs. Key features include university shortlisting via the Gemini API, AI-powered mock interviews, a resume generator with feedback, an ATS score calculator, real-time news API, and an AI assistant for career guidance. This paper explores the architecture, implementation, and performance of Career Compass, demonstrating improvements in precision, recall, and user satisfaction.
DOI: http://doi.org/10.5281/zenodo.16608494
Research on AI – Powered Medical Chat – Bot Using Rag
Authors: Ms. Gurpreet Kaur, Mayank Gupta, Kanak Sharma, Sarthak Goel
Abstract: The use of artificial intelligence (AI) in medicine has created medical Chat – bots that supports real -time patients, symptom assessment, early diagnosis and supportive patient training. However, traditional Chat – bot models based on static database or pre-influensing reactions have problems with chronic information, reference upheaval and the possibility of incorrect information. Recovery-sized generation (RAG) is a sophisticated AI model that supports the chat bot capacity by integrating a recovery system with generative AI, and ensures that reactions are relevant sounds and most infected with today's medical knowledge. This article emphasizes the main elements of the theoretical base and the real application of Raga-based medical chat bots that enable better accuracy, flexibility and user interactions. We discuss architecture, recycling process and response generation mechanisms that distinguish rag from traditional NLP – based chat-bots. In addition, we explain in detail about the significant strength of Rag, such as medical accuracy, real -time flexibility and adapted patient interaction. While the possibilities are very good, the implementation of carpet -based medical chat-bots is accompanied by computational overhead, data security and difficulties with regulatory requirements. We discuss these boundaries in adding possible solutions to make chat bot more reliable and effective. Case studies of real implementation also give us a picture of how effective they are and practically how they are used in modern health care. Finally, we identify future research directions by integrating RAG-based medical chat bot with new techniques such as IOT, Block chain and Multi-model AI to further change the digital health service. By addressing these main areas, this research tries to contribute to continuous progress of AI-driven medical chat bot, so that they can become an integral part of both health care professionals and patients.
DOI: http://doi.org/10.5281/zenodo.16608602
Network Security Visualization: Techniques, Challenges And Future Discussions
Authors: Ms. Usha Dhankar, Ms. Srishty Goswami, Himanshu Sharma, Nikhil Tiwari, Vansh Gupta
Abstract: – As networks become more complex and expansive, traditional security monitoring methods often fall short in detecting and responding to fast-evolving threats. This is where visualization steps in—turning overwhelming amounts of raw data into clear, intuitive visuals that help security teams spot anomalies, recognize attack patterns, and make faster, more informed decisions. In this paper, we explore how visualization techniques are revolutionizing network security, from analysing traffic and detecting intrusions to correlating security events. We also address real-world challenges, such as information overload, false alarms, and the difficulties of integrating these tools into large-scale systems. Looking ahead, we examine the future of security visualization—AI-driven insights, immersive environments like VR, and dynamic dashboards that make threat detection more interactive. By shedding light on these advancements, we highlight how visualization isn’t just a helpful tool but a critical component of modern, proactive cybersecurity.
DOI: http://doi.org/10.5281/zenodo.16607552
AUTONOMOUS ROBOTIC SYSTEM FOR EFFICIENT FARMING
Authors: P Prakash, Aakash K, Amizhdhan L, Pragathesh Kumar, L. Kannagi
Abstract: This autonomous agricultural vehicle, equipped with a camera and GPS, is designed to optimize farming efficiency by automating critical tasks such as harvesting, weed removal, and pest control. The vehicle autonomously navigates through fields, reducing the reliance on manual labor while ensuring precise and timely execution of agricultural operations. For harvesting, the vehicle identifies and collects ripe crops efficiently, minimizing losses and enhancing overall productivity. In weed removal, it detects and eliminates unwanted plants, ensuring crops have access to nutrients without competition. For pest control, the vehicle monitors plant health and identifies areas affected by pests, applying treatments only where necessary. This targeted approach reduces pesticide use, contributing to eco-friendly and sustainable farming practices. With smart navigation and obstacle avoidance, the vehicle operates seamlessly in large and complex agricultural environments. By integrating automation into farming practices, this vehicle not only enhances productivity but also reduces costs, making it an essential component of modern precision agriculture.
DOI: http://doi.org/10.5281/zenodo.16607776
SMART MIRROR
Authors: Ms. Sonia, Mr. Aditya Goel, Mr. Aneek Kumar, Mr. Kushagra, Ms. Chandni Kumari
Abstract: – This paper presented the development of a Smart Mirror, a device that integrates real- time information display with everyday utility. Designed by college students, the Smart Mirror was built entirely using Python libraries and provided functionalities such as news feeds, weather updates, calendar events, reminders, and basic time and date display. The project emphasized software development using Python and various APIs to create an interactive and user- friendly interface. The Smart Mirror aims to enhance daily routines by reducing the need for multiple devices while maintaining simplicity and efficiency.
DOI: http://doi.org/10.5281/zenodo.16608809
The Transformative Impact Of Artificial Intelligence on the Modern Education System
Authors: Arsh Ahmed , Abhishek , Shivam Bhardwaj , Piyush Tiwari , Ms. Jyoti
Abstract: This comprehensive study examines the multifaceted impact of Artificial Intelligence (AI) on global education systems. Through an analysis of current implementations, case studies, and empirical data, we explore how AI-driven technologies are reshaping pedagogical approaches, institutional administration, and learning outcomes. The paper investigates adaptive learning platforms like Squirrel AI, ALEKS, and ALO7 through the lens of Bloom's 2 Sigma Problem, while critically analyzing both the transformative potential and ethical challenges of educational AI. Our findings suggest that while AI offers unprecedented opportunities for personalization and accessibility, its successful integration requires careful consideration of pedagogical, ethical, and socioeconomic factors. The study concludes with policy recommendations for balanced adoption in educational contexts.
DOI: https://doi.org/10.5281/zenodo.16444680
Transforming Beauty And Wellness: A Case Study Of TikishNutra’s E-Commerce Model
Authors: Abhishek Baghel, Usha Dhankar Vicky Mona
Abstract: The beauty and wellness industry is undergoing a dynamic transformation driven by changing consumer behaviors increased digital engagement and rising demand for natural and personalized solutions. As traditional retail models struggle to keep pace with these evolving expectations e-commerce has emerged as a critical enabler of growth and accessibility. This research focuses on the conceptualization and development of an e-commerce solution specifically tailored to the beauty and wellness sector. The study aimed to address the need for seamless product discovery transparency and convenience by integrating modern design practices with personalized shopping experiences. A user-centric approach was adopted to incorporate features such as secure payment systems high-speed delivery services product transparency and user reviews. The platform emphasizes accessibility for a diverse consumer base and delivers intuitive navigation and personalized recommendations to support informed decision-making. Additionally the inclusion of virtual assistance and educational features helps users better understand product ingredients usage and wellness practices. The methodology involved analyzing current market challenges identifying user needs and designing a scalable modular system architecture supported by modern web technologies. Results demonstrate the potential of digital platforms in building trust improving customer retention and delivering a holistic shopping experience in a competitive market. The study concludes by showcasing a case implementation that reflects these design and functionality goals offering a practical example of how digital transformation can reshape customer engagement in the beauty and wellness domain
DOI: https://doi.org/10.5281/zenodo.16595853