Senthamil Selvi R

@saranathan.ac.in

Computer Science and Engineering
Saranathan college of Engineering

Senthamil Selvi R


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

RESEARCH INTERESTS

Big data classification, Data Mining, Machine Learning
12

Scopus Publications

112

Scholar Citations

5

Scholar h-index

4

Scholar i10-index

Scopus Publications

  • A Novel Semi-Supervised Skeleton Data-Based Action Recognition System using Graph Representation Alignment Model
    V. Sankari, R.Senthamil Selvi
    IEEE International Conference on Electronic Systems and Intelligent Computing Icesic 2026 Proceedings, 2026
    Action recognition based on skeleton has received considerable interest because it is highly resilient to the background noise, light changes, and privacy issues as opposed to the RGB-based system. Nevertheless, the current deep learning techniques are highly dependent on the availability of large-scale labeled data, which are costly and not applicable to practice. In order to cope with this drawback, this paper suggests a new semi-supervised skeleton data-based action recognition system based on a Graph Representation Alignment Model (GRAM). The framework proposed converts 3D skeleton sequences into spatio-temporal graphs, which affirms anatomical relationship of joints, and dispensation of movement. A Temporal-Spatial Graph Convolutional Network (TS-GCN) is used to obtain discriminative features and a semisupervised learning approach is adopted based on a small number of labeled samples and a large number of unlabeled samples. A dual-branch teacher-student system that uses exponential moving average stabilization to align graph representations is proposed that uses contrastive and structurepreserving objectives. A lot of experiments performed on the Kinetics-Skeleton data set reveal that the proposed method has a better classification accuracy of 96.01, that is, it is more effective than the current supervised and semi-supervised baselines. The findings agree that graph alignment and consistency regularization are useful in boosting recognition with low-label conditions, and the framework can be used in scalable and realistic action recognition scenarios.
  • An Enhanced Text Classification Performance Using Hybrid Deep Learning Procedure
    R. Deepa, R.Senthamil Selvi
    IEEE International Conference on Electronic Systems and Intelligent Computing Icesic 2026 Proceedings, 2026
    Text classification is a key procedure in natural language processing (NLP), as it is the basis of sentiment analysis, topic labeling, and emotion detection. Although the accuracy of text classification through deep learning has grown considerably, solitary models tend to be burdened with issues such as inability to generalize, inefficiency in modeling the context, or are biased to certain text patterns. According to this research, a hybrid deep learning network, which combines Convolutional Neural Networks (CNN) with local pattern recognition, Bidirectional Long Short-Term Memory (BiLSTM) with sequential dependencies, and an attention mechanism to weigh significant tokens in a context-sensitive fashion have been proposed. Moreover, the model uses a dual embedding approach that incorporates FastText and RoBERTa to provide a balance between a comprehensive comprehension of sub-word and an investigation of a context. The suggested model was tested on various datasets, such as IMDb, AG News, and Twitter Emotion, with the highest accuracy of 95.35 on AG News. Comparative studies against baseline and transformer designs prove the excellence of the hybrid design and its strength. It is also shown that the model generalizes well and performs exceptionally well as compared to the traditional and transformer-based methods in both precision and F1-score. These results indicate that an architectural diversity paired with the representational richness may result in a great architectural diversity with highly precise and context-aware text classification systems that can be implemented in the wild.
  • Ensemble Model for Stock Price Forecasting: MapReduce Framework for Big Data Handling: An Optimal Trained Hybrid Model for Classification
    R. Senthamil Selvi, V. Sankari, N. Ramya, M. Selvi
    Journal of Circuits Systems and Computers, 2024
    A number of authors have focused on this study to examine how huge data are perceived. A novel big data classification paradigm is introduced by the work’s preprocessing, feature extraction and classification techniques. Data normalization is carried out at the preprocessing stage. The MapReduce framework is then utilized to manage the massive data. Statistical features (mean, median, min/max and SD), higher-order statistical features (skewness, kurtosis and enhanced entropy), and correlation-based features are all extracted prior to classification. The Bi-LSTM and deep maxout hybrid classification model classifies the data during the reduction stage. To assure classification accuracy, training will also be deployed by the new Hybrid Butterfly Positioned Coot Optimization (HBPCO) algorithm. The proposed method’s accuracy of 97.45% beats the methods of NN (85.13%), CNN (83.78%), RNN (78.37%), Bi-LSTM (82.43%) and SVM (87.83%).
  • Deep Learning Algorithms for Skin Disease Classification
    Pradeepa R, Punitha V, Senthamil Selvi R
    Journal of Innovative Image Processing, 2024
    Skin diseases are a serious concern of public health worldwide, and successful treatment needs a correct and timely diagnosis. Traditional diagnostic methods mostly depend on dermatologist’s visual observation and this leads to subjective interpretations coupled with time-consuming processes. Deep learning algorithms have lately been known as powerful means for automated medical image analysis that present more accurate and quicker results at the same time. This study analyses the usage of state-of-the-art deep learning algorithms like YOLOv8, Deep CNN, and ResNet50 used for classification of skin diseases using dermatological images. Classifying the skin conditions relies heavily on the ability to identify and extract essential features. Different skin conditions were covered under large dataset thus providing a comprehensive foundation for training and validation aimed at ensuring that the models could generalize well across different diseases. Each algorithm also employs transfer learning techniques by utilizing pre-trained models based on large image datasets in order to improve adaptability and generalization over new data types. The use of deep learning algorithms in classifying skin diseases represents a significant method to achieve efficient and accurate diagnosis with benefits to both patients and healthcare professionals as is the trend in medical image analysis. The advanced deep learning models introduced in this paper excel at classifying complex skin diseases, outperforming the machine learning approaches in performance.
  • Geographical Information System-Aided Landmark Recognition System Using Machine Learning
    S. A. Sahaaya Arul Mary, Lakshmi Kanthan Narayanan, S. Mohana, R. Senthamil Selvi, R. Karthik, N. Ramya
    Lecture Notes on Data Engineering and Communications Technologies, 2023
  • Ensemble classifier based big data classification with hybrid optimal feature selection
    J.C. Miraclin Joyce Pamila, R. Senthamil Selvi, P. Santhi, T.M. Nithya
    Advances in Engineering Software, 2022
  • Improved meta-heuristic algorithm for selecting optimal features: A big data classification model
    Ramar Senthamil Selvi, Muniyappan Lakshapalam Valarmathi, Prathima Devadas
    Concurrency and Computation Practice and Experience, 2022
    Many fields function with large databases constitute a high number of features. Feature selection strategies seek to exclude the features that are distracting, repetitive, or unnecessary, as they can degrade the classification results. Existing approaches lack the scalability needed to handle the datasets with millions of instances and they do not obtain favorable results in a timely manner. This study uses a unique feature selection approach based on an upgraded optimization model and deep machine learning‐based data classification. “(a) Feature extraction, (b) optimal feature selection, and (c) classification” are the three stages of the proposed model. Initially, the extracted big‐datasets are efficiently handled by the parallel pool map‐reduce architecture. Several features from the input big‐data are extracted using feature extraction (FE) approaches such as the suggested Tri‐Kernel principal component analysis (TK‐PCA), linear discriminant analysis, and linear square regression. Furthermore, the data obtained characteristics may contain data that is irrelevant, out‐of‐date, or noisy. The computing cost rises due to the larger feature space. As a result, the best features are selected using a new optimization technique known as Levy Adapted SLnO (LA‐SLnO), which is a superior variant of the original SLnO algorithm. This selection of appropriate features improves the classification accuracy. For classification, Convolutional Neural Network is used in this work. Finally, a comparative evaluation is undergone to validate the efficiency of the proposed model.
  • Application of Machine Learning in Healthcare: An Analysis
    Suja Cherukullapurath Mana, G. Kalaiarasi, Yogitha R, L Suji Helen, R. Senthamil Selvi
    3rd International Conference on Electronics and Sustainable Communication Systems Icesc 2022 Proceedings, 2022
    Health care field is facing a lot of challenges due to the huge volume of people need medical support. The pandemic situation has created a lot of challenges to the healthcare field. This paper analyses how advancement in machine learning can be best utilized in improving health care services. Machine learning techniques are based on the idea of how systems can learn from the already existing data and can work with minimal human supervision. Thus machine learning has huge scope in healthcare. Machine learning algorithms can be effectively utilized for disease prediction, disease detection, providing personalized healthcare etc. These models can effectively predict the presence of diseases and also helps in detecting the diseases at earlier stage itself. Both supervised and unsupervised algorithms will be helpful in this field. Personalized healthcare applications aim to provide patient oriented healthcare services. Machine learning in combination with internet of things technologies made the personalized health care possible. The data collected from wearable devices and sensors can be effectively processed using machine learning algorithms and effective predictions can leads to quality of life improvements. In this chapter authors studies some of the existing applications of machine learning in healthcare field. Authors also propose a model that will add value to the existing applications.
  • Natural language processing based identification of Related Short Forum Posts through Knowledge Based Conceptualization
    J. C. Miraclin Joyce Pamila, Ajithkumar. A. K, R.Senthamil Selvi
    Proceedings International Conference on Artificial Intelligence and Smart Systems Icais 2021, 2021
    Online communities collaborate and users share their views using online forums. The experience and ideas shared by the users in the forum are rich but finding relevant forum posts is laborious and frustrating. This research is targeted towards comparing a post at hand to find forum posts related to it. The conventional methods for identifying text similarity are not as efficient as they do not conceptualize the short text and lead to poor performance in finding related content. This paper proposes a novel scheme for the identification of related short forum posts in discussion forums. Contrary to the use of fixed vocabulary sets in the existing schemes, the proposed method uses distinct words in the forum post pair to form a joint word set dynamically. The knowledge base is used for deriving a raw semantic vector for each forum post. Further, the two semantic vectors are used for the computation of semantic similarity. The proposed framework uses inverted indexing to improve the efficiency of retrieving relevant forum posts by reducing the search space with synonyms of the forum post at hand. It is proven to be efficient in finding related forum posts in discussion forums with a recall of 90% through a set of tests conducted. It is also observed that precision can be improved with the Named Entity Recognition method.
  • Enabling data security in data using vertical split with parallel feature selection using meta heuristic algorithms
    R. Senthamil Selvi, M.L. Valarmathi
    Concurrency and Computation Practice and Experience, 2021
    Big data is the emerging trend in modern science that deals with datasets larger and more complex that cannot be dealt by the traditional data processing techniques. This seems to be the core of current technology and business. In practice, many criteria should be considered in the implementation of this technique. The way of the search space for finding potential subsets of features and prediction performance of classifiers are major important issue. To solve this issue, feature selection methods are introduced in the recent work. In the feature selection algorithm, Non‐deterministic Polynomial (NP) Hard, and searching the space has been becomes more difficult task. To solve this problem, this work provides a new approach toward feature selection based on Vertical Split Group FireFly (VSGFF) algorithm. FF algorithm gets its inspiration from social aspects of real fireflies. At the same time, VSGFF is proposed with the principle of multiple clusters to avoid privacy problem. Finally, Naïve Bayes (NB), K Nearest Neighbor (KNN), and Multi‐Layer Perceptron Neural Network (MLPNN) classification algorithms are proposed for big data classification. Experimental outcomes depicts that proposed technique improves classification accuracy by 4% compared to traditional vertical split firefly algorithm.
  • Optimal Feature Selection for Big Data Classification: Firefly with Lion-Assisted Model
    Ramar Senthamil Selvi, Muniyappan Lakshapalam Valarmathi
    Big Data, 2020
  • An improved firefly heuristics for efficient feature selection and its application in big data
    Biomedical Research India, 2017

RECENT SCHOLAR PUBLICATIONS

  • Improved SVM‐Recursive Feature Elimination (ISVM‐RFE) Based Feature Selection for Bigdata Classification Under Map Reduce Framework
    JC Miraclin Joyce Pamila, RS Selvi
    Concurrency and Computation: Practice and Experience 37 (4-5), e70037 , 2025
    2025.0
    Citations: 1
  • Ensemble model for stock price forecasting: MapReduce framework for big data handling: an optimal trained hybrid model for classification
    R Senthamil Selvi, V Sankari, N Ramya, M Selvi
    Journal of Circuits, Systems and Computers 33 (11), 2450202 , 2024
    2024.0
    Citations: 3
  • Deep learning algorithms for skin disease classification
    R Pradeepa, V Punitha, R Senthamil Selvi
    J Innov Image Process 6 (2), 84-95 , 2024
    2024.0
    Citations: 3
  • FoodHarmony - Linking Lives Through Food, Integrating AI for Safe Distribution
    RS Selvi
    VDI-Z Integrierte Produktion 11 (10), 101-114 , 2024
    2024.0
  • Ensemble classifier based big data classification with hybrid optimal feature selection
    JCMJ Pamila, RS Selvi, P Santhi, TM Nithya
    Advances in Engineering Software 173, 103183 , 2022
    2022.0
    Citations: 19
  • Geographical Information System-Aided Landmark Recognition System Using Machine Learning
    SA Sahaaya Arul Mary, LK Narayanan, S Mohana, R Senthamil Selvi, ...
    Computer Networks and Inventive Communication Technologies: Proceedings of … , 2022
    2022.0
  • Geographical Information System-Aided Landmark Recognition System Using
    SASA Mary, LK Narayanan, S Mohana
    Computer Networks and Inventive Communication Technologies: Proceedings of … , 2022
    2022.0
  • Application of machine learning in healthcare: an analysis
    SC Mana, G Kalaiarasi, LS Helen, RS Selvi
    2022 3rd International Conference on Electronics and Sustainable … , 2022
    2022.0
    Citations: 21
  • Improved meta‐heuristic algorithm for selecting optimal features: A big data classification model
    R Senthamil Selvi, ML Valarmathi, P Devadas
    Concurrency and Computation: Practice and Experience 34 (17), e7000 , 2022
    2022.0
    Citations: 5
  • Crowdfunding Platform Using Blockchain Technology
    DRS Selvi, R SuryaPrakash, C Vishnu, AS Priyadharsan, ...
    International Journal Of Innovative Research In Technology 9 (1) , 2022
    2022.0
    Citations: 3
  • Natural language processing based identification of Related Short Forum Posts Through Knowledge Based Conceptualization
    JCMJ Pamila, RS Selvi
    2021 International Conference on Artificial Intelligence and Smart Systems … , 2021
    2021.0
  • Enabling data security in data using vertical split with parallel feature selection using meta heuristic algorithms
    R Senthamil Selvi, ML Valarmathi
    Concurrency and Computation: Practice and Experience 33 (3), e5248 , 2021
    2021.0
    Citations: 5
  • Detection of Unwanted Messages and Fraudulent User Identification on Social Network
    PLA Dr. R. Senthamil Selvi1, Dr. S. Mohana, Prof. S. Uma Maheswari, Dr. R ...
    Annals of the Romanian Society for Cell Biology 25 (2), 1041-1048 , 2021
    2021.0
    Citations: 1
  • Optimal feature selection for big data classification: firefly with lion-assisted model
    RS Selvi, ML Valarmathi
    Big data 8 (2), 125-146 , 2020
    2020.0
    Citations: 20
  • An improved firefly heuristics for efficient feature selection and its application in big data
    RS Selvi, ML Valarmathi
    Biomedical Research 28, S236-S241 , 2017
    2017.0
    Citations: 7
  • A survey on maintaining data privacy a different perspective
    RS Selvi, ML Valarmathi
    Advances in Natural and Applied Sciences 10 (4), 44-50 , 2016
    2016.0
  • A Survey on Privacy Preservation for Anonymzing Data
    M Saranya, RS Selvi
    International Journal of Emerging Engineering Research and Technology 3 (1) , 2015
    2015.0
    Citations: 1
  • A survey on leach-energy based routing protocol
    P Manimala, RS Selvi
    International Journal of Emerging Technology and Advanced Engineering … , 2013
    2013.0
    Citations: 23
  • Secure Big Data Storage To Guarantee Confidentiality In Cipher Text Multi sharing Control
    R Ilakkiya, RS Selvi
  • Firefly based feature selection algorithms for big data classification
    R Senthamil Selvi
    Chennai , 0

MOST CITED SCHOLAR PUBLICATIONS

  • A survey on leach-energy based routing protocol
    P Manimala, RS Selvi
    International Journal of Emerging Technology and Advanced Engineering … , 2013
    2013.0
    Citations: 23
  • Application of machine learning in healthcare: an analysis
    SC Mana, G Kalaiarasi, LS Helen, RS Selvi
    2022 3rd International Conference on Electronics and Sustainable … , 2022
    2022.0
    Citations: 21
  • Optimal feature selection for big data classification: firefly with lion-assisted model
    RS Selvi, ML Valarmathi
    Big data 8 (2), 125-146 , 2020
    2020.0
    Citations: 20
  • Ensemble classifier based big data classification with hybrid optimal feature selection
    JCMJ Pamila, RS Selvi, P Santhi, TM Nithya
    Advances in Engineering Software 173, 103183 , 2022
    2022.0
    Citations: 19
  • An improved firefly heuristics for efficient feature selection and its application in big data
    RS Selvi, ML Valarmathi
    Biomedical Research 28, S236-S241 , 2017
    2017.0
    Citations: 7
  • Improved meta‐heuristic algorithm for selecting optimal features: A big data classification model
    R Senthamil Selvi, ML Valarmathi, P Devadas
    Concurrency and Computation: Practice and Experience 34 (17), e7000 , 2022
    2022.0
    Citations: 5
  • Enabling data security in data using vertical split with parallel feature selection using meta heuristic algorithms
    R Senthamil Selvi, ML Valarmathi
    Concurrency and Computation: Practice and Experience 33 (3), e5248 , 2021
    2021.0
    Citations: 5
  • Ensemble model for stock price forecasting: MapReduce framework for big data handling: an optimal trained hybrid model for classification
    R Senthamil Selvi, V Sankari, N Ramya, M Selvi
    Journal of Circuits, Systems and Computers 33 (11), 2450202 , 2024
    2024.0
    Citations: 3
  • Deep learning algorithms for skin disease classification
    R Pradeepa, V Punitha, R Senthamil Selvi
    J Innov Image Process 6 (2), 84-95 , 2024
    2024.0
    Citations: 3
  • Crowdfunding Platform Using Blockchain Technology
    DRS Selvi, R SuryaPrakash, C Vishnu, AS Priyadharsan, ...
    International Journal Of Innovative Research In Technology 9 (1) , 2022
    2022.0
    Citations: 3
  • Improved SVM‐Recursive Feature Elimination (ISVM‐RFE) Based Feature Selection for Bigdata Classification Under Map Reduce Framework
    JC Miraclin Joyce Pamila, RS Selvi
    Concurrency and Computation: Practice and Experience 37 (4-5), e70037 , 2025
    2025.0
    Citations: 1
  • Detection of Unwanted Messages and Fraudulent User Identification on Social Network
    PLA Dr. R. Senthamil Selvi1, Dr. S. Mohana, Prof. S. Uma Maheswari, Dr. R ...
    Annals of the Romanian Society for Cell Biology 25 (2), 1041-1048 , 2021
    2021.0
    Citations: 1
  • A Survey on Privacy Preservation for Anonymzing Data
    M Saranya, RS Selvi
    International Journal of Emerging Engineering Research and Technology 3 (1) , 2015
    2015.0
    Citations: 1
  • FoodHarmony - Linking Lives Through Food, Integrating AI for Safe Distribution
    RS Selvi
    VDI-Z Integrierte Produktion 11 (10), 101-114 , 2024
    2024.0
  • Geographical Information System-Aided Landmark Recognition System Using Machine Learning
    SA Sahaaya Arul Mary, LK Narayanan, S Mohana, R Senthamil Selvi, ...
    Computer Networks and Inventive Communication Technologies: Proceedings of … , 2022
    2022.0
  • Geographical Information System-Aided Landmark Recognition System Using
    SASA Mary, LK Narayanan, S Mohana
    Computer Networks and Inventive Communication Technologies: Proceedings of … , 2022
    2022.0
  • Natural language processing based identification of Related Short Forum Posts Through Knowledge Based Conceptualization
    JCMJ Pamila, RS Selvi
    2021 International Conference on Artificial Intelligence and Smart Systems … , 2021
    2021.0
  • A survey on maintaining data privacy a different perspective
    RS Selvi, ML Valarmathi
    Advances in Natural and Applied Sciences 10 (4), 44-50 , 2016
    2016.0
  • Secure Big Data Storage To Guarantee Confidentiality In Cipher Text Multi sharing Control
    R Ilakkiya, RS Selvi
  • Firefly based feature selection algorithms for big data classification
    R Senthamil Selvi
    Chennai , 0