S.R.Vignesh

@srmist.edu.in

Assistant Professor, Engineering & Technology
Assistant Professor, Engineering & Technology
SRM Institute of Science and Technology

S.R.Vignesh


            Download Compact PDF  
https://researchid.co/vigneshrajkumar

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Computer Science, Computer Networks and Communications, Software
25

Scopus Publications

Scopus Publications

  • Video based crowd analysis using deep learning
    L. Sujihelen, Sama Subhadra, Sai Preethi Kota, S. Vignesh
    Aip Conference Proceedings, 2025
  • Cutting-Edge validation system: A safe methodology integrating facial and manuscript passwords, image lattices, searching info retrieval and login activity pursuing with efficient database connectivity
    D. Saravanan, G. Arun Kumar, Singirikonda Umesh, E. Polam Naga Nooka Raju, S. Vignesh
    Aip Conference Proceedings, 2025
  • Create an Intrusion Detection System to Detect Threats in Public WiFi Networks
    Vignesh S, Durgashivani S, Harida W
    2025 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation Iatmsi 2025, 2025
    Public wireless networks are currently one of the vectors for security threats such as unauthorized access and injection of malware. The current systems have mostly signature-based approaches that prove inefficient against novel and evolving threats. Consequently, significant vulnerabilities arise because users remain at risk of data breaches and privacy violations. We thus design a hybrid IDS by merging signature-based detection with advanced LSTM for sequential anomaly detection and Random Forest or XGBoost for strong classification of traffic patterns. The system is designed to detect in real time as known as unknown threats with the help of deep packet inspection and behavioral analysis of network traffic. LSTMs capture temporal dependencies in network behavior, while Random Forest/XGBoost efficiently classifies anomalous patterns. This solution is expected to raise the accuracy of detection, minimize false positives, and build dynamic adaptability for emerging threats, thereby enhancing public WiFi network security and protection of user data by a much higher margin.
  • Cutting-Edge Machine Learning Methods for Liver Disease Forecasting
    Sindhuja S, Lingabarani M G, Kamalakrishnan K S, Vignesh S
    Proceedings of 2025 2nd International Conference on Cognitive Robotics and Intelligent Systems Icc Robins 2025, 2025
    Liver disease is a worldwide health problem, and early identification and correct diagnosis are critical to better patient outcomes. However, traditional diagnostic procedures are often inadequate due to the complex interplay of clinical and biochemical factors. This study applies advanced machine learning techniques such as logistic regression, decision trees, and neural networks to analyze clinical and biochemical data to enhance diagnostic accuracy. The dataset used includes liver function test results and other relevant clinical variables. Data preprocessing is performed to clean and normalize the dataset, and the models are trained using cross-validation to ensure robustness. The machine learning models demonstrated improves accuracy in liver disease prediction, with XG boost achieving the highest accuracy of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 3. 6 7 \%}$</tex>, followed by random forest and neural networks. These models significantly outperforms the traditional methods by identifying patterns and making early predictions based on biochemical markers. The proposed system increases diagnostic precision, offering a valuable tool for healthcare providers. This method has the potential to improve patient care and liver disease management results through early diagnosis and individualized treatment plans.
  • Privacy-Aware Reconstruction and Profiling Using Advanced Contextual Embeddings
    Vignesh S, Senthilkumar Mathi, Dayanand V, Gowtham Ramesh
    Procedia Computer Science, 2025
    The proposed research aims to develop a secure and confidential system for identifying mental health disorders in individuals, with a focus on preserving the privacy of mental health data. This is achieved by generating encoded mental health profiles through the fine-tuning of a large language model (LLM) and applying advanced machine learning techniques. A transformer-based architecture within the LLM creates an embedding that serves as an encrypted key, incorporating Classification tokens. To maintain contextual accuracy, an autoencoder is trained to reconstruct these Classification tokens using the weights of a fine-tuned sentence Classification model. This design ensures that the network retains context while remaining secure. The system integrates demographic data and questionnaire responses into latent vectors that represent privacy-preserved mental health profiles. A fusion layer merges these vectors in the latent space to produce the final mental health profile. This privacy-conscious approach enables individuals to express mental health concerns securely, serving as a first step toward intervention. By employing natural language processing (NLP) techniques along with autoencoders, the research ensures data utility without compromising individual privacy. By leveraging this methodology, the research aims to improve mental health assessment while protecting sensitive data.
  • Challenges future trends and research direction in FL methods
    Energy Optimization and Security in Federated Learning for Iot Environments, 2025
  • Obstacle Detection on Autonomous Driving Systems
    Vignesh S, K Karunya, Vijaya Sankar K P, S L Jany Shabu, D Poornima
    International Conference on Advanced Computing Technologies Icoact 2025, 2025
    Self-driving cars, also known as autonomous vehicles are capable of supplanting automobiles driven by humans. In situations that humans find difficult, autonomous vehicles are able to examine their surroundings and ease through roadways. Many people might soon turn very dependent on AVs and overconfident that there won't be any failures owing to this. This has resulted in AVs having both affirmative as well as bad hands on the society. A combination of hardware, software, people, and their interactions, AVs are X-ware systems. There are still a lot of unanswered questions regarding AVs despite the abundance of research on the subject. Communication with pedestrians and other cars on the road is one of the biggest problems facing AVs. There must be an interaction between AVs and other transport users if autonomous cars have to replace human- driven vehicles. Few previous studies have examined the role of humans in the present shift to a society where self-driving cars are the norm, whereas the majority have focused on software errors. Three perspectives are examined in this paper: I that of the AV's driver and passenger; II that of pedestrians; and III that of the AV's interactions with other users of the transportation network. We also talk about relevant behavioral research.
  • Energy-efficient federated learning
    Energy Optimization and Security in Federated Learning for Iot Environments, 2025
  • An Explainable and Optimal Deep Transfer Learning Approach for Forest Fire Detection Using Grad-CAM Visualizations
    Sameer Mansoori, Aishwarya Pitchumani, Nila Sangamitra Arul, S Vignesh, Arti Anuragi
    Ised 2025 13th International Conference on Intelligent Systems and Embedded Design Proceedings, 2025
    Forest fires pose severe environmental, economic, and human threats. Traditional detection methods such as satellite imagery, manual observation, and sensor-based technologies, suffer from high false alarm rates, slow response times, and high installation costs. Thus, this study proposes an Advanced Deep Learning-based Detection Framework that uses Transfer learning to enhance fire detection and response in real-time. The framework consists of several pretrained models-MobileNet, InceptionV3, ResNet50, VGG16, EfficientNet, and Xception-that are fine-tuned through hyperparameter tuning and LwF for maximized classification accuracy with minimized false positives. We used 3 datasets, each with 3 classes - Fire, Normal and Smoke. Performance evaluation was carried out using accuracy, precision, recall and confusion matrices. It was then established that MobileNet provided the highest classification accuracy of 98.2% with low computational cost while LwF greatly advanced generalization over complex datasets. Furthermore, to boost model interpretability and ensure trustworthy decisionmaking, Grad-CAM visualization was also put into play. The results suggest that integration of deep learning based wildfire detection with focus on explainability can result in significant improvement in early warning systems. Future research will focus on incorporating Vision Transformers (ViTs), multimodal sensor fusion, and edge computing architectures. This study indicates the advantages of pretrained models to enhance disaster preparedness by mitigating the impacts of climate change.
  • Optimization Techniques for Predictive Maintenance in Industry 4.0
    Arul Prakash A., S. Vignesh, Rahin Batcha R., D. Saravanan, Vijay Ramalingam
    Data Analytics and Artificial Intelligence for Predictive Maintenance in Industry 4 0, 2025
    In Industry 4.0, “intelligent factories” collect and analyze data to keep tabs on the production process. Machine learning, data mining, and other statistical AI technologies can identify and forecast possible manufacturing procedure abnormalities, improving productivity and dependability. Nevertheless, the information retrieved from manufacturing information is sometimes presented in a complex structure due to the heterogeneous nature of the data. This puts up the semantic gap problem, which is shorthand for the reality that various production systems are incompatible. In addition, a unified knowledge model of physical assets and the ability to think in real time about analytical activities are essential for automating the decision-making process of Computerized Physical Systems (CPS), which are growing more data-intensive. Using symbolic AI in predictive maintenance could be a promising solution to these problems. Through numerous examinations, predictive upkeep offers a comprehensive review of the identification, localization, and identification of malfunctions in associated machinery. RAMI4.0 provides a structure to analyze the several initiatives that comprise Industry 4.0. The hierarchical structure, functional classification, and product life cycle are all encompassed. The Corporate Data Space, currently known as the International Data Space, is an online database that allows for the safe transfer and simple linking of data between corporate ecosystems using shared standards and governance frameworks. It guarantees data owners' online privacy while laying the groundwork for developing and using intelligent services and novel business procedures. In light of Industry 4.0, this article investigates potential ways to bolster maintenance prediction. Data exchange between businesses with varying security needs and the subsequent modularization of relevant functions are outcomes of implementing the RAMI 4.0 architecture, which facilitates predictive maintenance utilizing the FIWARE framework.
  • WordFix: From Levenshtein to Dynamic Spell Checking
    16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
  • Intellibus: An Ai-Powered Fleet Management System with Predictive Maintenance and Smart Routing
    16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
  • Machine learning techniques for heart disease detection using E-Health monitoring system
    Vijay Ramalingam, T. Ragupathi, A. Arul Prakash, S. Vignesh, R. Rahin Batcha, D. Saravanan
    Online Social Networks in Business Frameworks, 2024
  • A hybrid method for image encryption using lagrange's interpolation
    S. Vignesh, R. Rahin Batcha, D. Saravanan, Vijay Ramalingam, T. Ragupathi, A. Arul Prakash
    Online Social Networks in Business Frameworks, 2024
  • A review of various applications of Internet of Things with related security issues and challenges
    T. Ragupathi, A. Arul Prakash, S. Vignesh, R. Rahin Batcha, D. Saravanan, Vijay Ramalingam, K. P. Yuvaraj
    Online Social Networks in Business Frameworks, 2024
  • Privacy preservation in online social networks
    Arul Prakash, S. Vignesh, R. Rahin Batcha, D. Saravanan, Vijay Ramalingam, T. Ragupathi, Meenakshi
    Online Social Networks in Business Frameworks, 2024
  • Various threats and attacks on online social networks and their counter measures
    D. Saravanan, Vijay Ramalingam, T. Ragupathi, Arul Prakash, S. Vignesh, R. Rahin Batcha, M. Belsam Jeba Ananth, Meenakshi
    Online Social Networks in Business Frameworks, 2024
  • Spammer detection in online social networks
    R. Rahin Batcha, D. Saravanan, Vijay Ramalingam, T. Ragupathi, A. Arul Prakash, S. Vignesh, M. Belsam Jeba Ananth, K. Arumugam
    Online Social Networks in Business Frameworks, 2024
  • Mobile Application and QR Code for Attendance System
    A. Yovan Felix, S. Vignesh, M. Jonathan Andrew
    Aip Conference Proceedings, 2024
  • Unlocking the Mysteries of the Deep: Leveraging the Power of MobileNet and YOLOv5 for Efficient and Accurate Sea Cucumber Detection in Underwater Environments
    S. Vignesh, S. Dhamodaran
    2024 International Conference on Recent Innovation in Smart and Sustainable Technology Icrisst 2024, 2024
  • Development of Automated Hybrid Fusion System for Poisson Noise Mitigation in X-Ray Images of Osteoarthritis
    Pavithra Mani, Swetha R, Nirmaladevi P, Suthir S, Vijay V L, Kawin S, Manojkumar D, Vignesh S
    10th International Conference on Advanced Computing and Communication Systems Icaccs 2024, 2024
  • Enhancing Human Action Recognition through advanced Motion Descriptors and Machine Learning
    Vijay Ramalingam, D Saravanan, S. Vignesh, Rahin Batcha R
    2023 1st International Conference on Optimization Techniques for Learning Icotl 2023 Proceedings, 2023
  • Arduino Uno-Powered Parking Guidance System with Ultrasonic Sensors
    Subathra, Arul Prakash A, Vijay Ramalingam, S. Vignesh
    2023 1st International Conference on Optimization Techniques for Learning Icotl 2023 Proceedings, 2023
  • Customized Creation of ERC 20 Standard Cryptocurrency on the Ethereum Network
    R Rahin Batcha, S. Vignesh, Subathra, D Saravanan, G ArunKumar
    2023 1st International Conference on Optimization Techniques for Learning Icotl 2023 Proceedings, 2023
  • Vision based Fall Detection using Optimized Convolutional Neural Network
    R.R. Rajalaxmi, E. Gothai, Suganth V, S. Vignesh, T. Varun
    2022 International Conference on Computer Communication and Informatics Iccci 2022, 2022