S Durai

@veltech.edu.in

Associate Professor and CSE
Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyThis link is disabled.

S Durai


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

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Computer Vision and Pattern Recognition
50

Scopus Publications

Scopus Publications

  • Personalized product recommendation system using OpenAI
    Durai Selvaraj, Sujithra Thandapani, Bhuvanya Raghunathanu, Mohamed Iqbal Mahaboob, Kishore Kumar Kabaleeswaran, T. John Peter
    Aip Conference Proceedings, 2026
  • Security and flexible framework key plan for dynamic gaming approach
    N. Manjunathan, G. Prabaharan, A. Prathik, S. Ravikumar, N. K. Manikandan, S. Durai
    Aip Conference Proceedings, 2026
  • Harnessing Advanced AI Technologies to Enhance the Diagnosis of Alzheimer’s Disease
    U. Hemavathi, S. Durai
    Journal of Multiscale Modelling, 2026
    The chronic evolving neurodegenerative disorder Alzheimer’s Disease (AD) presents with memory deficits, cognitive impairment, and loss of abilities. AD prevalence is increasing as the world ages, necessitating more precise and easily obtainable diagnostic and treatment approaches. Artificial Intelligence (AI) technologies, and more specifically, machine learning and deep learning, have become game-changers in Alzheimer’s disease patient care, including optimizing care, enabling early diagnosis, supporting differential diagnosis, and predicting disease progression over the last few years. To detect amyloid plaques and hippocampal atrophy, this study investigates how AI-driven imaging analysis, specifically convolutional neural networks applied to MRI (Magnetic Resonance Imaging) and PET (Positron Emission Tomography) scans, provides higher sensitivity and specificity. Artificial intelligence models are also being used to analyze clinical and genomic data to identify biomarkers and support risk stratification. AI-assisted cognitive tests provide scalable, noninvasive, and real-time screening. Telemedicine platforms and AI-based Clinical Decision Support Systems (CDSS) are also improving patient management, particularly in remote or underserved areas. Heterogeneity of data, model explainability, ethics, and regulatory guideline requirements remain issues, despite these latest developments. Beyond recent developments such as federated learning and digital twins, the study comprehensively reviews AI’s contributions to AD diagnosis and therapy. It also establishes a guide for future research directions for the ethical and equitable integration of AI in clinical practice.
  • AI-Driven Precision Agriculture System for Crop Health Monitoring & Yield Prediction
    S.Durai, Velluri Pranay, KVD Abhinav
    Proceedings of 4th International Conference on Electronics and Renewable Systems Icears 2026, 2026
  • Simulation and Optimization of Biofuel Production from Agri Residues using Machine Learning Models
    S. Durai, Nukala Syam Venkata Dhanush, Bagadi Karthik
    Proceedings of 8th International Conference on Intelligent Sustainable Systems Iciss 2026, 2026
    Ever increasing energy demands in the world and environmental concerns have been driving the search for green counterparts to fossil fuels. Agriculture residues proved to be interesting remediation, and biofuels made from it could present the renewable energy chance and the unused management chance. Nonetheless, the production of biofuels has complicated (nonlinear) relations between different factors like the temperature, catalyst concentration, time of reaction, and the feedstock composition. This research paper proposes an Agri residue biofuel production AI-based simulation and optimization system that incorporates the concepts of Machine Learning (ML) and Artificial Intelligence (AI) to optimize the efficiency, yield, and performance of producing biofuels. This study identifies the need to use AI as a transformative factor in developing sustainable bioenergy systems as a source of efficient biofuel production through agricultural waste. Results of the study will lead to sustainability of the environment and lead to the introduction of the adaptive and real-time optimization systems in the biofuel industries of the future.
  • AI and Machine Learning Powered Impacted Test Case Generation From Multimodal User Stories Using Retrieval Augmented Generation
    S Durai, Saddapalli Komala, G Dillep
    Proceedings of 5th International Conference on Communication Computing and Electronics Systems Iccces 2026, 2026
    Because requirements are constantly changing, modern software systems are subject to continual development. As a result, it takes more time to create or keep up-to-date manual tests than it does to develop test cases automatically. Also, developing and creating automated tests through traditional means typically involves using some type of rule-based approach to extract data and/or rely on only one type of isolated natural language processing technique. In this article, we have developed a new type of intelligent system that can automatically create and re-create testing artifacts by bringing together multiple sources of information (e.g., text, images, etc.), using RAG, machine learning models, and hybrid impact analysis mechanisms. The components within this intelligent system utilize techniques such as semantic role labelling, entity extraction, and vector retrieving to process requirements expressed through different forms of text, various documents, and images. Finally, large language models are being used to automatically create structured test case scenarios from the results of using the RAG methodology and producing the testing artifacts mentioned above. The proposal for a new hybrid impact scoring model is based on calculating how many different types of impacts can occur (full, partial and integrated) through examining the similarity of records (based on embedding), the relevance of clusters (based on historical edits), and other assessment tools. The new model allows for focusing on regenerating only those test cases that were impacted by the change (from the previous release) through empirical validation of results, which clearly show the following advantages over traditional methods: improved accuracy of testing, increased confidence in detecting the impact of a change, decreased manual work effort to identify impacted test cases, and so on. Therefore, the proposed method provides a flexible, adaptable, and scalable solution for maintaining high-quality test suites in a continuously changing software development environment.
  • A Random Forest Regressor Model for Forecasting Agricultural Yield Using Agronomic and Climatic Parameters
    Gayathri S, P. Alagu Manoharan, S. Durai
    Proceedings of 8th International Conference on Intelligent Sustainable Systems Iciss 2026, 2026
    This project builds a data-based system to predict crop yield per hectare in Tamil Nadu, India. Crop yield prediction is difficult because it depends on many changing factors like rainfall, temperature, soil type, and nutrient levels. To handle this, the system uses a machine learning method called the Random Forest Regressor, which is strong and can find complex patterns in data. The model uses six main inputs rainfall, temperature, soil <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{p H}$</tex>, nitrogen <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(\mathbf{N})$</tex>, phosphorus <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(\mathbf{P})$</tex>, potassium (K) content, district, and crop type. It is trained and tested using past data and synthetic data, and it performs well based on MAE(Mean Absolute Error), RMSE(Root Mean Square Error), and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{R}^{\mathbf{2}}$</tex> scores. A MySQL database is used to manage data efficiently and support real-time updates, creating a full system from data collection to prediction. This system gives useful insights to farmers and policymakers, helping them choose crops wisely and use resources effectively. It supports sustainable farming and food security in Tamil Nadu. In the future, it can include real-time weather data, satellite images, and profit analysis to make predictions even better.
  • An efficient patient’s response predicting system using multi-scale dilated ensemble network framework with optimization strategy
    Nalini Manogaran, Nirupama Panabakam, Durai Selvaraj, Koteeswaran Seerangan, Firoz Khan, Shitharth Selvarajan
    Scientific Reports, 2025
    The forecasting of a patient's response to radiotherapy and the likelihood of experiencing harmful long-term health impacts would considerably enhance individual treatment plans. Due to the continuous exposure to radiation, cardiovascular disease and pulmonary fibrosis might occur. For forecasting the response of patients to chemotherapy, the Convolutional Neural Networks (CNN) technique is widely used. With the help of radiotherapy, cancer diseases are diagnosed, but some patients suffer from side effects. The toxicity of radiotherapy and chemotherapy should be estimated. For validating the patient's improvement in treatments, a patient response prediction system is essential. In this paper, a Deep Learning (DL) based patient response prediction system is developed to effectively predict the response of patients, predict prognosis and inform the treatment plans in the early stage. The necessary data for the response prediction are collected manually. The collected data are then processed through the feature selection segment. The Repeated Exploration and Exploitation-based Coati Optimization Algorithm (REE-COA) is employed to select the features. The selected weight features are input into the prediction process. Here, the prediction is performed by Multi-scale Dilated Ensemble Network (MDEN), where we integrated Long-Short term Memory (LSTM), Recurrent Neural Network (RNN) and One-dimensional Convolutional Neural Networks (1DCNN). The final prediction scores are averaged to develop an effective MDEN-based model to predict the patient's response. The proposed MDEN-based patient's response prediction scheme is 0.79%, 2.98%, 2.21% and 1.40% finer than RAN, RNN, LSTM and 1DCNN, respectively. Hence, the proposed system minimizes error rates and enhances accuracy using a weight optimization technique.
  • High resolution spatial modelling of soil parent material: An initial investigation study using random forest machine learning techniques
    A. Vijayakumar, Amal Alshardan, Abdulaziz G. Alghamdi, S. Durai
    Journal of South American Earth Sciences, 2025
  • Swift and efficient cinnamon plant disease classification using robust feature extraction and machine learning techniques
    Sujithra Thandapani, Durai Selvaraj, Mohamed Iqbal Mahaboob, Venkatakrishnan Chakravarathi Bharathi, Prabhu Vinayagam
    Bulletin of Electrical Engineering and Informatics, 2025
    The extraction of features and textures holds a crucial significance in the realm of image processing and machine vision systems. Even though artificial intelligence (AI) techniques are superior in attaining the best results in image processing, several challenges remain open for further research in computation complexity, memory, and power requirements. In this context, robust preprocessing techniques are required to address such shortcomings and reduce the computational cost of predictive tasks. This paper employed two feature extraction levels to extract the best possible features from images of the cinnamon plant. Local directional positional pattern (LDPP) extracts global image features, while local triangular coded pattern (LTCP) extracts local features. It helps to provide detailed and more relevant information about the image texture. Once features are extracted, identifying and categorizing diverse textures within an image relies on recognizing their unique features. Typically, descriptors serve as the means for representing images in our work. Afterwards, we used ensemble learning to attain better classification results with the help of weak classifiers. Extracted features are provided to machine learning (ML) models like support vector machines (SVM), random forest (RF), and k-nearest neighbors (KNN) for better classification of the cinnamon category.
  • A Novel Speech-Aware Framework (SACENet) for Non-Invasive Detection of Alzheimer's Disease
    Hemavathi. U, Durai. S
    Proceedings of 5th International Conference on Soft Computing for Security Applications Icscsa 2025, 2025
  • NeuroVision-XNet: A Hybrid Vision Transformer Framework for Early Alzheimer's Disease Prediction using Structural MRI
    Hemavathi U, Durai S
    Proceedings of 3rd International Conference on Sustainable Computing and Data Communication Systems Icscds 2025, 2025
  • Enhanced Security in IoT Networks through Optimized Deep Learning-Based Intrusion Detection
    Y. Gold Anand, S. Durai
    3rd International Conference on Data Science and Information System Icdsis 2025, 2025
  • TOWARDS SEED SELECTION AND YIELD ASSESSMENT FOR AGRICULTURAL PRODUCTIVITY IN INDIA
    Durai Selvaraj, Sujithra Thandapani, Mohamed Iqbal Mahaboob, K Kishore Kumar
    Proceedings on Engineering Sciences, 2025
  • Revolutionizing Agriculture: Smart Irrigation Systems for Optimized Water Management and Enhanced Crop Yield
    S. Durai, Rajkumar N, Darsh Chatrani, Kishore Kumar K, T Vaishnavi, S Vikas
    Proceedings 1st International Conference on Frontier Technologies and Solutions Icfts 2025, 2025
  • Code Generation Empowered by Natural Language Processing and Machine Learning Algorithms
    S.Girirajan
    Advances in Nonlinear Variational Inequalities, 2025
  • Prediction of vitiligo skin disease spreading rate by image processing
    Durai Selvaraj, M. Mohamed Iqbal, Mukkoti Maruthi Venkata Chalapathi
    Research Advances in Intelligent Computing Volume 2, 2024
  • IoT based Automatic Fertilizer Mixer and Sprinkler System
    K Kishore Kumar, N Rajkumar, Brahmaji Godi, S. Durai
    2nd International Conference on Self Sustainable Artificial Intelligence Systems Icssas 2024 Proceedings, 2024
  • Advanced Security Model for Cloud Infrastructure Using Cryptography and Steganography
    T. Sujithra, Vivek Justus, Mohamed Iqbal Mahaboob, S.Durai
    International Conference on Intelligent and Innovative Practices in Engineering and Management 2024 Iipem 2024, 2024
  • Post-Quantum Cryptography Security with CSPM for Secure Data Transmission in Cloud Environments
    N Rajkumar, K Kishore Kumar, M. Gokul, S. Durai
    Proceedings of the 4th International Conference on Ubiquitous Computing and Intelligent Information Systems Icuis 2024, 2024
  • Revolutionizing Cardiovascular Attack Prediction: A Comprehensive Machine Learning Approach for Accurate and Timely Detection
    S. Durai, D. Jaganathan, Prabhu V, R. Harini
    Proceedings 2024 International Conference on Expert Clouds and Applications Icoeca 2024, 2024
  • Enhancing Accessibility for the Visually Impaired through Text Voice-Activated Images
    C. Shyamala Kumari, S. Durai, Dornadula Sudha Karthisri, Maliga Hemanth Kumar, Potlluru Venkata Sai Sukhesh
    2nd International Conference on Self Sustainable Artificial Intelligence Systems Icssas 2024 Proceedings, 2024
  • Real Time Facial Recognition-Based Criminal Identification Using MTCNN
    S. Durai, T. Sujithra, Battula Vishnuwardhan Satyam, Sai Neeraj Keshetty, Chilakapati Narasimha Shruti Sagar, Athmakuri Sai Charan
    2nd International Conference on Sustainable Computing and Smart Systems Icscss 2024 Proceedings, 2024
  • Image Classification for Potato Plant Leaf Disease Detection using Deep Learning
    S. Durai, T. Sujithra, M. Mohamed Iqbal
    International Conference on Sustainable Computing and Smart Systems Icscss 2023 Proceedings, 2023
  • Deep Learning-Based Facial Emotion Analysis
    M. Mohamed Iqbal, M. M. Venkata Chalapathi, S. Aarif Ahamed, S. Durai
    Lecture Notes in Networks and Systems, 2023
  • Data Visualization for Corona Patients Globally using Real-Time APIs
    S. Durai, M. Mohamed Iqbal, S Niresh Kumar, Chockalingam Alagappan
    2nd International Conference on Sustainable Computing and Data Communication Systems Icscds 2023 Proceedings, 2023
  • Car Defect Detection Using Image Processing
    S. Durai, T. Sujithra, Athmakuri Sai Charan, Sai Kiran Pulyala, Battula Vishnuwardhan Satyam
    Proceedings of the International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering Iceconf 2023, 2023
  • IoMT with Deep CNN: AI-Based Intelligent Support System for Pandemic Diseases
    Sujithra Thandapani, Mohamed Iqbal Mahaboob, Celestine Iwendi, Durai Selvaraj, Ankur Dumka, Mamoon Rashid, Senthilkumar Mohan
    Electronics Switzerland, 2023
  • Cloud Computing based Multipurpose E-Service Application using Flutter
    S. Durai, C. Shyamalakumari, T. Sujithra
    Proceedings 6th International Conference on Computing Methodologies and Communication Iccmc 2022, 2022
  • Swift and Secure Medical Data Transaction
    T. Sujithra, N. M. Masoodhu Banu, N. Poornima, S. Durai
    Lecture Notes in Networks and Systems, 2022
  • Germination Prediction System for Rice seed using CNN Pre-Trained models
    S. Durai, C. Mahesh, T. Sujithra, C. Shyamalakumari
    Proceedings IEEE International Conference on Advances in Computing Communication and Applied Informatics Accai 2022, 2022
  • Research on varietal classification and germination evaluation system for rice seed using hand-held devices
    S. Durai, C. Mahesh
    Acta Agriculturae Scandinavica Section B Soil and Plant Science, 2021
  • Research on germination prediction and varietal classification for rice seed quality
    S. Durai, , Dr. C. Mahesh, and
    International Journal of Engineering and Advanced Technology, 2019
  • Human activity pattern in bigdata for healthcare application
    S Durai, M Viswanathan, C. Shyamala Kumari, S Florence
    Journal of Computational and Theoretical Nanoscience, 2018
  • Online high priced motor vehicle rental system
    S Durai, C Shyamalakumari, S Florence
    Journal of Computational and Theoretical Nanoscience, 2018
  • Smart attendance marking system using face recognition
    S Florence, C. Shyamala Kumari, S Durai
    Journal of Computational and Theoretical Nanoscience, 2018
  • Remote medical assistant system using automated medical Gadget
    C. Shyamala Kumari, S Florence, S Durai
    Journal of Computational and Theoretical Nanoscience, 2018
  • Telecom infrastructure policy tracker for quick reference and easy access
    N. K Manikandan, D Manivannan, S Durai
    Journal of Computational and Theoretical Nanoscience, 2018
  • Secured cryptographic data model for cloud
    International Journal of Engineering and Technology Uae, 2018
  • Comparative study on satellite-based data communication techniques
    International Journal of Engineering and Technology Uae, 2018
  • Survey of rice seed quality analysis for varietal purity estimation by using image processing techniques
    International Journal of Engineering and Technology Uae, 2018
  • Smart traffic system using raspberry pi by applying dynamic color changer algorithm
    K. Kishore Kumar, S. Durai, M. Thanjai Vadivel, K. Antony Kumar
    2017 IEEE International Conference on Smart Technologies and Management for Computing Communication Controls Energy and Materials Icstm 2017 Proceedings, 2017
  • Survey of effective teaching mechanisms and ICT tools for education
    International Journal of Civil Engineering and Technology, 2017
  • INternet of things and its need to the existing world
    International Journal of Civil Engineering and Technology, 2017
  • Measuring macro nutrients of the soil for smart agriculture in coconut cultivation
    International Journal of Civil Engineering and Technology, 2017
  • Fertilizer recommendation system for coconut cultivation
    International Journal of Civil Engineering and Technology, 2017
  • Data entry works in computer using voice keyboard
    S. Durai, N. Rajkumar, N. K. Manikandan, D. Manivannan
    Indian Journal of Science and Technology, 2016
  • Manual detection of feature envy bad smell in software code
    International Journal of Applied Engineering Research, 2015
  • A survey on recent security threats and its prevention methodologies
    International Journal of Applied Engineering Research, 2015
  • Thor-Fd: The hierarchial online ranking fraud detecting for mobile apps using sentiword dictionary
    International Journal of Applied Engineering Research, 2015