Vinodhini Kanakaraj
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Vinodhini Kanakaraj has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- S. P. Santhoshkumar
Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, India
7 shared publications - A. Kaliappan
School of Computing, SRM Institute of Science and Technology, Tiruchirappalli, India
3 shared publications S. Bindhu
Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology
3 shared publications- Gajalakshmi S
Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, India
2 shared publications Kawsalya S
Nehru Arts and Science College
2 shared publicationsPreethi M
Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College
2 shared publications
Latest Publications
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1139-1145
FruitNetSH: An Efficient Deep Learning Model for Precision Pomegranate Disease Diagnosis
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1139-1145
FruitNetSH: An Efficient Deep Learning Model for Precision Pomegranate Disease Diagnosis
- 8 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1915-1920
Explainable Multimodal Deep Learning for Early Detection of Neurodegenerative Disorders
Neurodegenerative disorders have a heterogeneous clinical presentation and the conventional diagnostic tools are not very sensitive thus making early detection of these disorders difficult. In this paper, an explainable multimodal deep learning model is proposed to identify and classify neurodegenerative diseases through early prediction and analysis of heterogeneous data, such as neuroimaging, speech signals, motor patterns, physiological biomarkers, genomic data and clinical metadata. Deep networks that are modality-specific are used in the extraction of robust features and advanced fusion mechanisms using attention to model cross-modal interactions and heterogeneity of features are addressed. The explainability-aware inference strategy offers clear understanding of the modality contributions and features relevance, which increases the clinical interpretability and trust. Substantial benchmark results indicate that the suggested framework has an excellent diagnostic accuracy, strong generalization, and better earlystage detection in comparison with the state-of-the-art methods. Findings make explainable multimodal deep learning a promising and scalable and reliable solution to early neurodegenerative disease detection and clinical decision support.
- 8 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1915-1920
Explainable Multimodal Deep Learning for Early Detection of Neurodegenerative Disorders
Neurodegenerative disorders have a heterogeneous clinical presentation and the conventional diagnostic tools are not very sensitive thus making early detection of these disorders difficult. In this paper, an explainable multimodal deep learning model is proposed to identify and classify neurodegenerative diseases through early prediction and analysis of heterogeneous data, such as neuroimaging, speech signals, motor patterns, physiological biomarkers, genomic data and clinical metadata. Deep networks that are modality-specific are used in the extraction of robust features and advanced fusion mechanisms using attention to model cross-modal interactions and heterogeneity of features are addressed. The explainability-aware inference strategy offers clear understanding of the modality contributions and features relevance, which increases the clinical interpretability and trust. Substantial benchmark results indicate that the suggested framework has an excellent diagnostic accuracy, strong generalization, and better earlystage detection in comparison with the state-of-the-art methods. Findings make explainable multimodal deep learning a promising and scalable and reliable solution to early neurodegenerative disease detection and clinical decision support.
- Open Access
- 20 March 2026
- Published by Oriental Scientific Publishing Company in Biomedical and Pharmacology Journal
- Vol. 1 (19) , 386-397
Scorpi-XStack: Improving Type 2 Diabetes Prediction via Feature Optimization and Stacking
Early detection of Type 2 Diabetes (T2D) is perilous for remediating patient consequences and dropping long-term complications. This study proposes Scorpi-XStack, a diagnostic framework that integrates a novel bio-inspired optimization algorithm, ScorpiOpt, with stacked ensemble learning to enhance predictive accuracy. ScorpiOpt identifies the most discriminative clinical features by reducing redundancy and improving feature robustness. These selected features are used to train a weighted collaborative classifier containing Random Forest and XGBoost as ignoble learners, for which Logistic Regression is the master learner. The framework was validated on three benchmark datasets—Pima Indian Diabetes (Kaggle), clinical records from Medical City Hospital, Iraq (Mendeley Data), and the Frankfurt Diabetes dataset (GitHub/ResearchGate)—after applying ETL processing, mean/mode imputation for missing values, and z-score normalization. Classical recital remained assessed via stratiform 5-fold cross-validation, springy an accurateness of 98.54%, F1-score of 98.50%, balanced accuracy of 98.52% and AUROC of 99.86%. Compared with existing methods (85–95% accuracy range), Scorpi-XStack demonstrated consistent improvements across multiple performance metrics. While results are promising, limitations such as dataset heterogeneity, potential overfitting, and computational overhead should be noted. Further validation on larger, independent, and multi-center cohorts is necessary to confirm clinical applicability and generalizability.
- 20 March 2026
- Published by Oriental Scientific Publishing Company in Biomedical and Pharmacology Journal
- Vol. 1 (19) , 386-397
Open AccessScorpi-XStack: Improving Type 2 Diabetes Prediction via Feature Optimization and Stacking
Early detection of Type 2 Diabetes (T2D) is perilous for remediating patient consequences and dropping long-term complications. This study proposes Scorpi-XStack, a diagnostic framework that integrates a novel bio-inspired optimization algorithm, ScorpiOpt, with stacked ensemble learning to enhance predictive accuracy. ScorpiOpt identifies the most discriminative clinical features by reducing redundancy and improving feature robustness. These selected features are used to train a weighted collaborative classifier containing Random Forest and XGBoost as ignoble learners, for which Logistic Regression is the master learner. The framework was validated on three benchmark datasets—Pima Indian Diabetes (Kaggle), clinical records from Medical City Hospital, Iraq (Mendeley Data), and the Frankfurt Diabetes dataset (GitHub/ResearchGate)—after applying ETL processing, mean/mode imputation for missing values, and z-score normalization. Classical recital remained assessed via stratiform 5-fold cross-validation, springy an accurateness of 98.54%, F1-score of 98.50%, balanced accuracy of 98.52% and AUROC of 99.86%. Compared with existing methods (85–95% accuracy range), Scorpi-XStack demonstrated consistent improvements across multiple performance metrics. While results are promising, limitations such as dataset heterogeneity, potential overfitting, and computational overhead should be noted. Further validation on larger, independent, and multi-center cohorts is necessary to confirm clinical applicability and generalizability.