S. Hemkiran
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
S. Hemkiran has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Sudha Sadasivam
Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, India
2 shared publications A. K. Anjhanna
PSG Institute of Technology and Applied Research
1 shared publicationA. Prasanna Rahavendra
PSG Institute of Technology and Applied Research
1 shared publication- G. Sathish Kumar
Department of Artificial Intelligence and Data Science, Sri Eshwar College of Engineering, Coimbatore, India
1 shared publication - G. Uma Maheshwari
Department of CSE (Artificial Intelligence and Machine Learning), Dr. Mahalingam College of Engineering and Technology, Coimbatore, India
1 shared publication - G. Vijaya
Department of Artificail Intelligence and Data Science, Karpagam College of Engineering, Coimbatore, India
1 shared publication
Latest Publications
- Open Access
- 4 February 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1)
An effective ECOLASSO with black widow optimization for feature selection and stagewise adaptive learning rate for disease prediction
Machine learning techniques are utilized for early detection of diseases, which can significantly enhance probabilities of positive treatment and existence. The traditional machine learning algorithms may be unable to predict outcomes with sufficient accuracy. In this work, an Effective ECOLASSO with Black Widow Optimization for Feature Selection and Stagewise Adaptive Learning Rate (ELBWOSALR) classifier is proposed for feature selection and prediction. The proposed work comprises two phases, in the first phase, Ecological similarity Least Absolute Shrinkage and Selection Operator (ECOLASSO) model is utilized to predict the best features from the dataset by removing the feature with smallest absolute regression coefficient from the feature set. A Black Widow Optimizer (BWO) is used to choose the subset of optimal features and to reduce local optima. In the second phase, Stagewise Adaptive Learning Rate (SALR) involves combining several weak learner classifiers into a strong ensemble classifier by adaptive learning rate. The key contribution of this work is the integration of ECOLASSO model with BWO for robust feature selection, combined with a SALR classifier. This hybridization addresses two critical challenges simultaneously: (i) ECOLASSO ensures sparsity and ecological similarity-driven selection of relevant features, while (ii) BWO prevents premature convergence and enhances global search efficiency. By coupling these with SALR, our model achieves superior accuracy and generalization compared to conventional classifiers. Lung cancer, breast cancer and heart disease datasets are used for experimentation. The ELBWOSALR classifier is compared with various classifier models such as Support Vector Classifier, Decision Tree Classifier, Random Forest Classifier, Logistic Regression, Extreme Gradient Boost Classifier, Gradient Boosting Classifier, K-Nearest Neighbors Classifier and CatBoost Classifier and the results are observed. The proposed ELBWOSALR classifier achieves accuracies of 98%, 97% and 91% with AUC values of 92%, 99% and 94% for lung cancer, breast cancer and heart disease datasets respectively.
- 4 February 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6 (1)
Open AccessAn effective ECOLASSO with black widow optimization for feature selection and stagewise adaptive learning rate for disease prediction
Machine learning techniques are utilized for early detection of diseases, which can significantly enhance probabilities of positive treatment and existence. The traditional machine learning algorithms may be unable to predict outcomes with sufficient accuracy. In this work, an Effective ECOLASSO with Black Widow Optimization for Feature Selection and Stagewise Adaptive Learning Rate (ELBWOSALR) classifier is proposed for feature selection and prediction. The proposed work comprises two phases, in the first phase, Ecological similarity Least Absolute Shrinkage and Selection Operator (ECOLASSO) model is utilized to predict the best features from the dataset by removing the feature with smallest absolute regression coefficient from the feature set. A Black Widow Optimizer (BWO) is used to choose the subset of optimal features and to reduce local optima. In the second phase, Stagewise Adaptive Learning Rate (SALR) involves combining several weak learner classifiers into a strong ensemble classifier by adaptive learning rate. The key contribution of this work is the integration of ECOLASSO model with BWO for robust feature selection, combined with a SALR classifier. This hybridization addresses two critical challenges simultaneously: (i) ECOLASSO ensures sparsity and ecological similarity-driven selection of relevant features, while (ii) BWO prevents premature convergence and enhances global search efficiency. By coupling these with SALR, our model achieves superior accuracy and generalization compared to conventional classifiers. Lung cancer, breast cancer and heart disease datasets are used for experimentation. The ELBWOSALR classifier is compared with various classifier models such as Support Vector Classifier, Decision Tree Classifier, Random Forest Classifier, Logistic Regression, Extreme Gradient Boost Classifier, Gradient Boosting Classifier, K-Nearest Neighbors Classifier and CatBoost Classifier and the results are observed. The proposed ELBWOSALR classifier achieves accuracies of 98%, 97% and 91% with AUC values of 92%, 99% and 94% for lung cancer, breast cancer and heart disease datasets respectively.
- 1 October 2022
- Published by Bentham Science Publishers Ltd. in Current Bioinformatics
- Vol. 17 (8) , 698-709
Prediction of Drug Bioactivity in Alzheimer’s Disease Using Machine Learning Techniques and Community Networks
Background: The design of novel drugs is vital to combat fatal diseases such as Alzheimer’s. With quantum advances in computational methods, artificial intelligence (AI) techniques have been widely utilized in drug discovery. Since drug design is a protracted and resource-intensive process, extensive research is necessary for building predictive in-silico models to discover new medications for Alzheimer’s. A thorough analysis of models is, therefore, required to expedite the discovery of new drugs. Objective: In this study, the performance of machine learning (ML) and deep learning (DL) models for predicting the bioactivity of compounds for Alzheimer’s inhibition is assessed. Additionally, an interaction network is constructed to visualize the clustered bioactivity networks. Methods: The dataset was initially prepared from a public repository of bioactive compounds and was curated. Exploratory data analysis was performed to get insights into the gathered data. A bioactivity interaction network was then constructed to detect communities and compute the network metrics. Next, ML and DL models were built, and their hyperparameters were tuned to improve model performance. Finally, the metrics of all the models were compared to identify the best-performing model for bioactivity prediction. Results: The bioactivity network revealed the formation of three communities. The ML models were ranked based on lower error scores, and the best five models were hybridized to create a blended regressor. Subsequently, two DL models, namely a deep neural network (DNN) and long short-term memory with recurrent neural network architecture (LSTM-RNN), were built. The analysis revealed that the LSTM-RNN outperformed all the models analysed in this study. Conclusion: In summary, this study illustrates a bioactivity network and proposes a DL technique to build robust models for in-silico prediction of drug bioactivity against Alzheimer's.
- 1 October 2022
- Published by Bentham Science Publishers Ltd. in Current Bioinformatics
- Vol. 17 (8) , 698-709
Prediction of Drug Bioactivity in Alzheimer’s Disease Using Machine Learning Techniques and Community Networks
Background: The design of novel drugs is vital to combat fatal diseases such as Alzheimer’s. With quantum advances in computational methods, artificial intelligence (AI) techniques have been widely utilized in drug discovery. Since drug design is a protracted and resource-intensive process, extensive research is necessary for building predictive in-silico models to discover new medications for Alzheimer’s. A thorough analysis of models is, therefore, required to expedite the discovery of new drugs. Objective: In this study, the performance of machine learning (ML) and deep learning (DL) models for predicting the bioactivity of compounds for Alzheimer’s inhibition is assessed. Additionally, an interaction network is constructed to visualize the clustered bioactivity networks. Methods: The dataset was initially prepared from a public repository of bioactive compounds and was curated. Exploratory data analysis was performed to get insights into the gathered data. A bioactivity interaction network was then constructed to detect communities and compute the network metrics. Next, ML and DL models were built, and their hyperparameters were tuned to improve model performance. Finally, the metrics of all the models were compared to identify the best-performing model for bioactivity prediction. Results: The bioactivity network revealed the formation of three communities. The ML models were ranked based on lower error scores, and the best five models were hybridized to create a blended regressor. Subsequently, two DL models, namely a deep neural network (DNN) and long short-term memory with recurrent neural network architecture (LSTM-RNN), were built. The analysis revealed that the LSTM-RNN outperformed all the models analysed in this study. Conclusion: In summary, this study illustrates a bioactivity network and proposes a DL technique to build robust models for in-silico prediction of drug bioactivity against Alzheimer's.
- 17 December 2021
- Published by Springer Nature
- p. 1-9
Design of Automatic Credit Card Approval System Using Machine Learning
- 17 December 2021
- Published by Springer Nature
- p. 1-9
Design of Automatic Credit Card Approval System Using Machine Learning