V. Thamilarasi

@srisaradacollege.ac.in

ASSISTANT PROFESSOR IN COMPUTER SCIENCE
SRI SARADA COLLEGE FOR WOMEN(AUTONOMOUS)

V. Thamilarasi


                     Download Compact PDF  
https://researchid.co/v.thamilarasi
ASSISTANT PROFESSOR IN SRI SARADA COLLEGE FOR WOMEN(AUTONOMOUS)

EDUCATION

M.Sc, M.Phil, MCA., Ph.D IN COMPUTER SCIENCE

RESEARCH INTERESTS

MEDICAL IMAGE PROCESSING, DATA MINING

FUTURE PROJECTS

Efficient Classification by RESNET-50 and compare by deep learning architectures for lung chest X-ray images

I have already completed this work and i need collaboration for SCI publishing only


Applications Invited
Interested persons communicate me
15

Scopus Publications

Scopus Publications

  • AUDITORY LIBRARY GUIDE: A DIGITAL SOLUTION FOR VISUALLY IMPAIRED READERS
    V. Thamilarasi
    Journal of Engineering and Technology for Industrial Applications, 2026
    This paper's main objective is to use the Auditory Library Guide to assist visually impaired people in finding and accessing library books.  People with visual impairments have trouble locating the book in the library.  Although library services for these individuals were insufficient up until now, everyone now understands how important it is to make information accessible to those who are visually impaired.  In light of this, a method is suggested and created to enable them to utilize library resources.  Through the use of text-to-speech conversion and voice recognition technology, they can utilize the system to access the library and hear the contents of the books.The purpose of this study is to improve the social issues faced by visually impaired persons and to help them read library books like everyone else.
  • Exploring AI Tools and Framework for Supply Chain Management
    V. Thamilarasi, Janaki Sivakumar, R. Roselin, N. Jeysankar, Kirti Hemant Wanjale, S.Janet Grace Susila
    Industry 6 0 and Digital Transformation in Supply Chain Assets and Services, 2026
    The rise of Artificial Intelligence plays dominant role in education, healthcare, agriculture and business and its growth boost the development of every sectors. Here data plays dominant role and its needs proper tools and frameworks to carryout analysis. Data science is a field to explore data. In this digital era data is everything and every industry needs data to improve their performance to next level in economically and standard in the market. In health care industries data is everything and due to Internet of Things, Cloud, Body networks, data handling needs specific tool and analysis requires specific frame work. In finance and bank sectors every data stored in excel and databases and which assess the data visualization tools to explore further, safety and security. Hence the role of data is unavoidable and which seeks data processing techniques, handling tools and frameworks. This study explore the nature of AI driven tools and available frameworks for supply chain management.
  • Blockchain-Enabled Smart Contracts for Secure Digital Transformation
    V. Thamilarasi, S. Biruntha, Biswo Ranjan Mishra, S. Tamizharasu, M. Muthalagu, M. Thangamani
    Conference Proceedngs Wccst 2026 World Conference on Computational Science and Technology, 2026
  • QINN-Based Approach to Detect Anomalies in High-Dimensional Secure Data
    V. Thamilarasi, Nitendra Kumar, P Ganesh Kumar, G. Sivaraman, R. RajiniGanth, Janaki Sivakumar
    Advancing Cyber Threat Detection Through Quantum and Edge Computing, 2025
    Anomaly discovery is a crucial aspect of modern data analysis to finding unusual trends or behaviours in datasets across various domains like cybersecurity and finance and the healthcare. However, overfitting, in which the model becomes overly adapted to training data, results in false negatives and misclassifications, makes it difficult to target optimal detection capabilities. To get around this, training data must be carefully sanitized, eliminating unknown and irregular anomalous instances to guarantee precise anomaly detection. It is already difficult to accomplish optimal and significant feature extraction when working with noisy, high-dimensional data, like that found in network traffic. When features are too similar, overfitting and incorrect classifications may occur. However, classification accuracy may suffer if important features are removed. By improving likelihood estimation and feature separability, unsupervised techniques can assist in finding and keeping pertinent features to enhance model performance.
  • Intelligent decision model based on deep reinforcement learning for soccer games outcome prediction using optimal feature extraction and optimization
    V. Thamilarasi, R. Roselin, Kirti H. Wanjale, P. Pushpa
    Revolutionizing Data Science and Analytics for Industry Transformation, 2025
    In this study, the authors propose an intelligent decision model, the deep reinforcement learning for soccer games outcome prediction (DRL-SGO), using optimal feature extraction and optimization. Initially, they design a feature extraction model based on DenseNet to extract soccer games domain knowledge, including recency and rating features, from the given dataset. Subsequently, they use the artificial rabbit optimization (ARO) algorithm to optimize features, selecting the best among a multitude of options. Additionally, they employ deep reinforcement learning (DRL) techniques to enhance the accuracy of predicting soccer game outcomes. Finally, they validate the performance of the proposed DRL-SGO model using the 2017 soccer prediction challenge dataset. Remarkably, the DRL-SGO model achieved an accuracy of 93.991%, precision of 89.169%, recall of 90.537%, and F-measure of 89.843%, showcasing its impressive predictive in the realm of soccer game outcome forecasting.
  • Novel Study of MRI Brain Tumor Detection and Segmentation by Digital Image Processing Techniques
    V. Thamilarasi, N. Kanya, R. Roselin, Dahlia Sam, S. Babu
    Brain Informatics Technology, 2025
    The brain is a more complicated organ that controls the overall activities of the human body. It captures information through sensory organs and acts accordingly once cognitive ability, memory power, and emotions are controlled by the brain. It is a combination of the cerebrum, cerebellum, and brainstem. The brain may be affected by various diseases, including brain tumors, Alzheimer's disease, Parkinson's disorder, and stroke. Maximum diseases result from neurological disorders. Tumors are different from neurological disorders. A brain tumor is the second leading disease around the world, and it destroys people's lives. It needs more research to attain the solution and proper treatment. Radiologists use various modalities to capture the brain, and different types of images are available for brain image analysis. Particularly, magnetic resonance imaging (MRI) is a very basic method among other methods that produce various modalities of brain tissues, such as T1-weighted, T2-weighted, and proton density (PD)–weighted images. Normally, MRI images capture white matter, gray matter, and cerebrospinal tissues from the brain. MRI images need more support from computer-aided diagnosis to remove outliers, noise, and unwanted areas in the image. Medical image processing plays a prominent role in disease diagnosis. Early detection of abnormal changes in brain tissues may prolong the life of patients. This study explores various tumor detection and partitioning techniques, such as thresholding, region-based segmentation, k-means clustering, contour detection, and morphology-based segmentation; discusses implementation details; and recommends suitable segmentation techniques for tumor detection in the brain. The performance of algorithms was experimented with by the Dice similarity index, Jaccard similarity index, accuracy, precision, recall, and F1-score.
  • Intelligent Deep Learning Algorithms for Autism Spectrum Disorder Diagnosis
    V. Thamilarasi, R. Roselin, P. Pushpa, M. Kannan, B. P. Sreejith Vignesh
    Computational Intelligence Algorithms for the Diagnosis of Neurological Disorders, 2025
  • Enhancing Personalized Brand Recommendations through Machine Learning- Driven Analysis of User Behavior and Brand Interaction
    V. Thamilarasi, G. Sivaraman, R. Harihara Krishnan, S. K. Kavitha, P. Pushpa
    Intelligent Business Analytics Harnessing the Power of Soft Computing for Data Driven Insights, 2025
    In today’s digital world, every business relies on web-scraped data to understand customer preferences and to increase sales via personalized brand recommendations. The market is becoming increasingly competitive in the data-driven world. Businesses start focusing on targeted marketing to save expenses and boost their competitiveness and marketing effectiveness. To analyze this type of data, there is an increasing demand for advanced analytical techniques and customized brand recommendations. This study aims to provide an insightful perspective on the utility of data analytics methods to find user behavior in brand interactions. Furthermore, the research offers a comprehensive overview of the procedure for creating and evaluating platforms to enhance machine learning techniques for business development. To achieve accurate marketing, this paper deploys machine learning algorithms like K-nearest neighbor (KNN), super vector machine (SVM), and Naive Bayes (NB) to analyze customer attributes and characteristics with previous purchase records. The article attempts to investigate how customer purchase intention and the phenomenon of personalization relate to each other. According to the findings, KNN gives 92% accuracy for estimating brand and behavior to enhance the sales force.
  • Fuzzy Logic-Based Deep Learning for Human-Machine Interaction and Gesture Recognition in Uncertain and Noisy Environments
    John Anand, V. Thamilarasi, Ashish Rayal, Himanshu Kumar Gupta, Kamboji Jyothi, Pramatma Vishwakarma
    1st International Conference on Advances in Computer Science Electrical Electronics and Communication Technologies Ce2ct 2025, 2025
    Conventional deep learning methods have considerable hurdles when it comes to Human-Machine Interaction (HMI) and gesture identification in noisy and uncertain situations. A Fuzzy Logic-Based Deep Learning (Fuzzy DL) method is presented in this work to improve the resilience, accuracy, and adaptability of human gesture recognition in a variety of scenarios. We test several algorithms on various datasets, lighting situations, and noise levels, such as CNN, LSTM, Transformer, and Fuzzy DL. The outcomes show that Fuzzy DL functions better than other systems, retaining 91.0% accuracy at high noise levels and reaching 97.5% accuracy under typical circumstances. In comparison to traditional structures, it also shows faster inference times and a lower mean squared error. Its superiority is further demonstrated by comparative analysis on precision, recall, and F1-score. This study presents a robust and noise-resilient solution for real-world HMI applications, including as assistive systems and virtual interfaces. The outcomes indicate that incorporating fuzzy logic with DL substantially enhances gesture recognition in difficult environments.
  • Artificial Intelligence Driven Kyphosis Classification
    V. Thamilarasi, R. Harihara Krishnan, V. Vijayalakshmi, J. Mary Catherine, V. Poornima, S. Pratheepa
    Lecture Notes in Networks and Systems, 2025
  • Quantum Computing - Navigating the Frontier with Shor's Algorithm and Quantum Cryptography
    V. Thamilarasi, Pramod Kumar Naik, Isha Sharma, V. Porkodi, M. Sivaram, M. Lawanyashri
    Tqcebt 2024 2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies 2024, 2024
  • AI-Powered Real-Time Runway Safety: UAV-Based Video Analysis with ICSO-Enhanced Deep Learning
    V. Thamilarasi, R. Hema, A. Noble Mary Juliet, Adlin Sheeba, Gauri Ghule, A. Raja
    International Journal of Computational and Experimental Science and Engineering, 2024
  • Application of machine learning in chest X-ray images
    Machine Learning for Healthcare Systems Foundations and Applications, 2023
  • Classification of Lung Chest X-Ray Images Using Deep Learning with Efficient Optimizers
    A. Asaithambi, V. Thamilarasi
    2023 IEEE 13th Annual Computing and Communication Workshop and Conference Ccwc 2023, 2023
  • Automatic thresholding for segmentation in chest X-ray images based on green channel using mean and standard deviation
    International Journal of Innovative Technology and Exploring Engineering, 2019