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.

 

Published by: vikaspatanker

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.

 

 

Published by: vikaspatanker

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.

 

 

Published by: vikaspatanker

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

 

Published by: vikaspatanker

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.

 

 

Published by: vikaspatanker

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.

 

 

Published by: vikaspatanker

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.

 

 

Published by: vikaspatanker

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.

Published by: vikaspatanker

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./

Published by: vikaspatanker

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.

 

 

Published by: vikaspatanker