M. Renugadevi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
M. Renugadevi has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Nagrajan Raju
School of Electrical & Electronics Engineering, SASTRA Deemed University, Thanjavur, India
2 shared publications - Bhoomi Shah
Department of Computer Science and Engineering, School of Technology, GSFC University, Vadodara, India
1 shared publication - Deepak Parashar
Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India.
1 shared publication - Govindarajan Venkat Babu
School of Electrical and Electronics Engineering, SASTRA Deemed University, Thanjavur 613401, India
1 shared publication - Ihssan S. Masad
Department of Electrical and Computer Engineering, Gulf University for Science and Technology, Hawally 32093, Kuwait
1 shared publication - K. Narasimhan
SASTRA Deemed University
1 shared publication
Latest Publications
- 2 August 2026
- Published by Springer Nature
- p. 17-31
Enhanced Reinforcement Learning Framework for Glioma Prognosis in Data-Constrained MRI Cohorts
- 2 August 2026
- Published by Springer Nature
- p. 17-31
Enhanced Reinforcement Learning Framework for Glioma Prognosis in Data-Constrained MRI Cohorts
- Open Access
- 11 September 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (18) , 2304
GlioSurvQNet: A DuelContextAttn DQN Framework for Brain Tumor Prognosis with Metaheuristic Optimization
Background/Objectives: Accurate classification of brain tumors and reliable prediction of patient survival are essential in neuro-oncology, guiding clinical decisions and enabling precision treatment planning. However, conventional machine learning and deep learning methods often struggle with challenges such as data scarcity, class imbalance, limited model interpretability, and poor generalization across diverse clinical settings. This study presents GlioSurvQNet, a novel reinforcement learning-based framework designed to address these limitations for both glioma grading and survival prediction. Methods: GlioSurvQNet is built upon a DuelContextAttn Deep Q-Network (DQN) architecture, tailored for binary classification of low-grade vs. high-grade gliomas and multi-class survival prediction (short-, medium-, and long-term categories). Radiomics features were extracted from multimodal MRI scans, including FLAIR, T1CE, and T2 sequences. Feature optimization was performed using a hybrid ensemble of metaheuristic algorithms, including Harris Hawks Optimization (HHO), Modified Gorilla Troops Optimization (mGTO), and Zebra Optimization Algorithm (ZOA). Subsequently, SHAP-based feature selection was applied to enhance model interpretability and robustness. Results: The classification module achieved the highest accuracy of 99.27% using the FLAIR + T1CE modality pair, while the survival prediction model attained an accuracy of 93.82% with the FLAIR + T2 + T1CE fusion. Comparative evaluations against established machine learning and deep learning models demonstrated that GlioSurvQNet consistently outperformed existing approaches in both tasks. Conclusions: GlioSurvQNet offers a powerful and interpretable AI-driven solution for brain tumor analysis. Its high accuracy and robustness make it a promising tool for clinical decision support in glioma diagnosis and prognosis.
- 11 September 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (18) , 2304
Open AccessGlioSurvQNet: A DuelContextAttn DQN Framework for Brain Tumor Prognosis with Metaheuristic Optimization
Background/Objectives: Accurate classification of brain tumors and reliable prediction of patient survival are essential in neuro-oncology, guiding clinical decisions and enabling precision treatment planning. However, conventional machine learning and deep learning methods often struggle with challenges such as data scarcity, class imbalance, limited model interpretability, and poor generalization across diverse clinical settings. This study presents GlioSurvQNet, a novel reinforcement learning-based framework designed to address these limitations for both glioma grading and survival prediction. Methods: GlioSurvQNet is built upon a DuelContextAttn Deep Q-Network (DQN) architecture, tailored for binary classification of low-grade vs. high-grade gliomas and multi-class survival prediction (short-, medium-, and long-term categories). Radiomics features were extracted from multimodal MRI scans, including FLAIR, T1CE, and T2 sequences. Feature optimization was performed using a hybrid ensemble of metaheuristic algorithms, including Harris Hawks Optimization (HHO), Modified Gorilla Troops Optimization (mGTO), and Zebra Optimization Algorithm (ZOA). Subsequently, SHAP-based feature selection was applied to enhance model interpretability and robustness. Results: The classification module achieved the highest accuracy of 99.27% using the FLAIR + T1CE modality pair, while the survival prediction model attained an accuracy of 93.82% with the FLAIR + T2 + T1CE fusion. Comparative evaluations against established machine learning and deep learning models demonstrated that GlioSurvQNet consistently outperformed existing approaches in both tasks. Conclusions: GlioSurvQNet offers a powerful and interpretable AI-driven solution for brain tumor analysis. Its high accuracy and robustness make it a promising tool for clinical decision support in glioma diagnosis and prognosis.
- Open Access
- 26 August 2025
- Published by Springer Nature in Discover Applied Sciences
- Vol. 7 (9) , 1-20
SVR machine learning and SARIMA-based air quality index classification and forecasting system
The prediction and classification of the air quality index (AQI) are a primary concern. Still, due to the involvement of many parameters affecting AQI pre- dictions, it becomes time-consuming and monotonous work. The prediction and classification of the AQI with utmost accuracy is a pivotal tool for evaluating and monitoring the level of air pollution in a given area, facilitating public awareness and policy making in safeguarding human health and the surroundings. In this study, to improve the performance of air quality index classification and prediction, machine learning techniques based on support vector regression, and for prediction, the classic time-series analysis based on seasonal autoregressive integrated moving average (SARIMA) was employed. The forecasted AQI value for the next 25 days lies in a 97.3% confidence interval zone. The experimental results of the proposed method are evaluated and validated for performance and quality analysis on AQI data based on accuracy, precision, recall, and F1 score. The experimental results achieved 97% accuracy, compared to 94.1% with the Auto-regressive integrated moving average (ARIMA)-based technique, 91% precision, 94% recall, and 92% F1 score, demonstrating the effectiveness of the proposed technique for classifying and predicting the air quality index.
- 26 August 2025
- Published by Springer Nature in Discover Applied Sciences
- Vol. 7 (9) , 1-20
Open AccessSVR machine learning and SARIMA-based air quality index classification and forecasting system
The prediction and classification of the air quality index (AQI) are a primary concern. Still, due to the involvement of many parameters affecting AQI pre- dictions, it becomes time-consuming and monotonous work. The prediction and classification of the AQI with utmost accuracy is a pivotal tool for evaluating and monitoring the level of air pollution in a given area, facilitating public awareness and policy making in safeguarding human health and the surroundings. In this study, to improve the performance of air quality index classification and prediction, machine learning techniques based on support vector regression, and for prediction, the classic time-series analysis based on seasonal autoregressive integrated moving average (SARIMA) was employed. The forecasted AQI value for the next 25 days lies in a 97.3% confidence interval zone. The experimental results of the proposed method are evaluated and validated for performance and quality analysis on AQI data based on accuracy, precision, recall, and F1 score. The experimental results achieved 97% accuracy, compared to 94.1% with the Auto-regressive integrated moving average (ARIMA)-based technique, 91% precision, 94% recall, and 92% F1 score, demonstrating the effectiveness of the proposed technique for classifying and predicting the air quality index.