Subba Rao Polamuri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Subba Rao Polamuri has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Pravin Ramdas Kshirsagar
Department of Electronics Telecommunication Engineering, JD College of Engineering and Management, Nagpur, India
6 shared publications - Kudipudi Srinivas
VR Siddhartha Engineering College
4 shared publications - Kuan Tak Tan
Department of Engineering Cluster, Singapore Institute of Technology, Singapore
3 shared publications - A. Krishna Mohan
Department of CSE, University College of Engineering Kakinada, JNTUK, Kakinada, India
2 shared publications - Aneesh Somwanshi
Department of Mechanical Engineering, MATS University, Raipur, India
2 shared publications - T. Prabhakara Rao
Associate Professor, Department of Computer Science and Engineering, Aditya University, Surampalem, AP, India
2 shared publications
Latest Publications
- 30 April 2026
- Published by Rajarambapu Institute of Technology in Journal of Engineering Education Transformations
- Vol. 39 (S2) , 114-132
Unifying Data Refinement and Fusion Strategies: A Cutting-Edge Methodology for E-Learning Performance Optimization
The surge in the e-learning market has compelled the need for intelligent predictive models to minimize the gap between performance analysis and personalized learning systems to improve student performance. With the wide growth of the e-learning market, there is a great demand for intelligent predictive models to bridge the gap between performance analysis and personalized learning systems to boost student performance. Yet, traditional prediction methods are not effective due to issues like class imbalance, outliers, irrelevant features, and limited model interpretability. This research introduces an advanced framework to predict student academic performance based on an educational data mining dataset, Students' Academic Performance Dataset (xAPI-Edu-Data), comprising 480 instances, 16 attributes, and multi-variate integer and categorical features of the e-learning environment and educational data mining. The proposed framework involves class imbalance handling using Synthetic Minority Oversampling Technique (SMOTE), outlier removal using Interquartile Range (IQR), feature scaling and data standardization using Z-score normalization. A novel hybrid feature selection method TRIFEX is proposed to select the most influencing features to the student performance by combining ANOVA F-statistics, Recursive Feature Elimination (RFE) and Lasso regularization. The Logistic Regression, Decision Tree, and K-Nearest Neighbor (KNN) classifiers are used in the study. The hyperparameter optimization is done using Randomized Search CV, Grid Search CV, and Optuna to increase the efficiency and generalization power of the model. In addition, a voting, based ensemble model is created to fuse the virtues of individual classifiers for good prediction. Experimental results have shown that the proposed ensemble model is more accurate with 98.99% accuracy, 99.00% F1-score and 0.1005 RMSE as compared to the conventional predictive models. The results suggest that the suggested method has substantial potential to increase the accuracy of prediction, explainability of features and individualized learning support in contemporary e-learning environments.
- 30 April 2026
- Published by Rajarambapu Institute of Technology in Journal of Engineering Education Transformations
- Vol. 39 (S2) , 114-132
Unifying Data Refinement and Fusion Strategies: A Cutting-Edge Methodology for E-Learning Performance Optimization
The surge in the e-learning market has compelled the need for intelligent predictive models to minimize the gap between performance analysis and personalized learning systems to improve student performance. With the wide growth of the e-learning market, there is a great demand for intelligent predictive models to bridge the gap between performance analysis and personalized learning systems to boost student performance. Yet, traditional prediction methods are not effective due to issues like class imbalance, outliers, irrelevant features, and limited model interpretability. This research introduces an advanced framework to predict student academic performance based on an educational data mining dataset, Students' Academic Performance Dataset (xAPI-Edu-Data), comprising 480 instances, 16 attributes, and multi-variate integer and categorical features of the e-learning environment and educational data mining. The proposed framework involves class imbalance handling using Synthetic Minority Oversampling Technique (SMOTE), outlier removal using Interquartile Range (IQR), feature scaling and data standardization using Z-score normalization. A novel hybrid feature selection method TRIFEX is proposed to select the most influencing features to the student performance by combining ANOVA F-statistics, Recursive Feature Elimination (RFE) and Lasso regularization. The Logistic Regression, Decision Tree, and K-Nearest Neighbor (KNN) classifiers are used in the study. The hyperparameter optimization is done using Randomized Search CV, Grid Search CV, and Optuna to increase the efficiency and generalization power of the model. In addition, a voting, based ensemble model is created to fuse the virtues of individual classifiers for good prediction. Experimental results have shown that the proposed ensemble model is more accurate with 98.99% accuracy, 99.00% F1-score and 0.1005 RMSE as compared to the conventional predictive models. The results suggest that the suggested method has substantial potential to increase the accuracy of prediction, explainability of features and individualized learning support in contemporary e-learning environments.
- 12 January 2026
- Published by Springer Nature in Cluster Computing
- Vol. 29 (2) , 112
Establishing an efficient security model using learning and optimization approaches
- 12 January 2026
- Published by Springer Nature in Cluster Computing
- Vol. 29 (2) , 112
Establishing an efficient security model using learning and optimization approaches
- 15 October 2025
- Published by Springer Nature
- p. 307-318
Machine Learning and Internet of Things Devices for Waste Segregation
- 15 October 2025
- Published by Springer Nature
- p. 307-318
Machine Learning and Internet of Things Devices for Waste Segregation
- 15 October 2025
- Published by Springer Nature
- p. 331-341
Improved Disease Detection Using CNN and Machine Learning Models
- 15 October 2025
- Published by Springer Nature
- p. 331-341
Improved Disease Detection Using CNN and Machine Learning Models
- 18 August 2025
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 35 (03)
Energy-Efficient Chaos Encryption Scheme and Image Processing in Wireless Multimedia Sensor Networks Using Swin Transformer-Aided YOLOv8 Model
Wireless media sensor networks (WMSNs) are widely used for real-time data collection, monitoring and flexible deployment, yet challenges remain regarding security, efficiency and energy consumption due to open communication, large data volumes and resource limitations. This paper presents an energy-efficient encryption and image processing scheme for WMSNs using deep learning. Raw images from the DOTA-v2 dataset undergo preprocessing steps such as resizing and denoising, where the K_TF technique enhances image quality. The SwinT-YOLOv8 model is employed for dynamic object detection, followed by a chaos-based lightweight image encryption (CLIE) scheme that ensures secure image encryption. This multi-stage encryption uses random values from Henon’s chaotic map, Brownian motion and Chen’s chaotic system to reduce pixel correlation and enhance security. The integrated approach facilitates secure communication and image exchange among network nodes. Implemented in MATLAB, the proposed system achieves 99.25% accuracy, a detection time of 60 s, a network lifetime of 60% and energy efficiency of 80.37%, along with improved performance across various key parameters.
- 18 August 2025
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 35 (03)
Energy-Efficient Chaos Encryption Scheme and Image Processing in Wireless Multimedia Sensor Networks Using Swin Transformer-Aided YOLOv8 Model
Wireless media sensor networks (WMSNs) are widely used for real-time data collection, monitoring and flexible deployment, yet challenges remain regarding security, efficiency and energy consumption due to open communication, large data volumes and resource limitations. This paper presents an energy-efficient encryption and image processing scheme for WMSNs using deep learning. Raw images from the DOTA-v2 dataset undergo preprocessing steps such as resizing and denoising, where the K_TF technique enhances image quality. The SwinT-YOLOv8 model is employed for dynamic object detection, followed by a chaos-based lightweight image encryption (CLIE) scheme that ensures secure image encryption. This multi-stage encryption uses random values from Henon’s chaotic map, Brownian motion and Chen’s chaotic system to reduce pixel correlation and enhance security. The integrated approach facilitates secure communication and image exchange among network nodes. Implemented in MATLAB, the proposed system achieves 99.25% accuracy, a detection time of 60 s, a network lifetime of 60% and energy efficiency of 80.37%, along with improved performance across various key parameters.
- Open Access
- 12 August 2025
- Published by UK Zhende Publishing Limited Company in Lex localis - Journal of Local Self-Government
- Vol. 23 (S5) , 719-737
EXPLORING DEEP LEARNING AND GAN MODELS FOR LEVERAGING STOCK PRICES PREDICTION: A NOVEL ADVERSARIAL FRAMEWORK FOR FINANCIAL TIME SERIES FORECASTING
Predicting stock prices is one of the hardest things to do in finance analytics since financial markets are naturally volatile, non-linear, and highly interdependent. Conventional machine learning algorithms often fail to recognise the latent patterns and temporal correlations present in stock market data. This research presents an innovative deep learning system that employs Generative Adversarial Networks (GANs) specifically tailored for stock price prediction by integrating adversarial training with advanced feature engineering methodologies. Our suggested model, the Financial Adversarial Prediction Network (FAPN), has two generators. One is for short-term price changes and the other is for long-term trend prediction. The discriminator network is augmented with an attention mechanism to improve the differentiation between authentic and synthetic price series. To help make more accurate predictions, technical indicators, news sentiment analysis, and macroeconomic data are all given as multi-modal inputs. The model has another loss function that combines adversarial loss with finance-specific indicators like risk-adjusted returns and directional correctness. Over the course of ten years, extensive testing involving five prominent stock indices (S&P 500, NASDAQ, Dow Jones, FTSE 100, and Nikkei 225) demonstrates that the new strategy significantly outperforms the previous one. Our FAPN model can predict the average direction of movement with 78.4% accuracy, which is better than the best methods available today, like LSTM (65.2%), ARIMA (58.7%), and traditional GAN approaches (71.3%). The model also does better on the Mean Absolute Percentage Error (MAPE), with an average of 2.34% compared to 4.12% for LSTM and 5.67% for classical statistical methods. Risk-adjusted performance measurements show a 34% increase in the Sharpe ratio compared to previous approaches. The proposed framework enhances the current standards in financial forecasting and elucidates the application of adversarial learning in compound time series forecasting jobs. We have made progress in the areas of novel architectural innovations, strong evaluation procedures, and useful applications for algorithmic trading systems. The tests demonstrate that GANs, when meticulously designed for financial applications, can significantly enhance predictive performance while sacrificing computing efficiency suitable for real-time trading operations.
- 12 August 2025
- Published by UK Zhende Publishing Limited Company in Lex localis - Journal of Local Self-Government
- Vol. 23 (S5) , 719-737
Open AccessEXPLORING DEEP LEARNING AND GAN MODELS FOR LEVERAGING STOCK PRICES PREDICTION: A NOVEL ADVERSARIAL FRAMEWORK FOR FINANCIAL TIME SERIES FORECASTING
Predicting stock prices is one of the hardest things to do in finance analytics since financial markets are naturally volatile, non-linear, and highly interdependent. Conventional machine learning algorithms often fail to recognise the latent patterns and temporal correlations present in stock market data. This research presents an innovative deep learning system that employs Generative Adversarial Networks (GANs) specifically tailored for stock price prediction by integrating adversarial training with advanced feature engineering methodologies. Our suggested model, the Financial Adversarial Prediction Network (FAPN), has two generators. One is for short-term price changes and the other is for long-term trend prediction. The discriminator network is augmented with an attention mechanism to improve the differentiation between authentic and synthetic price series. To help make more accurate predictions, technical indicators, news sentiment analysis, and macroeconomic data are all given as multi-modal inputs. The model has another loss function that combines adversarial loss with finance-specific indicators like risk-adjusted returns and directional correctness. Over the course of ten years, extensive testing involving five prominent stock indices (S&P 500, NASDAQ, Dow Jones, FTSE 100, and Nikkei 225) demonstrates that the new strategy significantly outperforms the previous one. Our FAPN model can predict the average direction of movement with 78.4% accuracy, which is better than the best methods available today, like LSTM (65.2%), ARIMA (58.7%), and traditional GAN approaches (71.3%). The model also does better on the Mean Absolute Percentage Error (MAPE), with an average of 2.34% compared to 4.12% for LSTM and 5.67% for classical statistical methods. Risk-adjusted performance measurements show a 34% increase in the Sharpe ratio compared to previous approaches. The proposed framework enhances the current standards in financial forecasting and elucidates the application of adversarial learning in compound time series forecasting jobs. We have made progress in the areas of novel architectural innovations, strong evaluation procedures, and useful applications for algorithmic trading systems. The tests demonstrate that GANs, when meticulously designed for financial applications, can significantly enhance predictive performance while sacrificing computing efficiency suitable for real-time trading operations.
- Open Access
- 7 November 2024
- Published by National Environmentalists Association in The Bioscan
- Vol. 19 (Special -1) , 653-660
Predicting Cardiovascular Disease by Integrating the Dataset and DNN with Asynchronous Learning Technique
Predicting cardiovascular illness via the integration of datasets and deep neural networks using an asynchronous learning methodology. Healthcare experts see the prediction of cardiac disease as a critical endeavour, while deep learning has shown considerable potential in accomplishing this objective. This research study presents a unique methodology termed the Asynchronous Federated Deep Learning Approach aimed at Cardiac Predictions (AFLCP), which integrates a heart disease dataset along with DNN through an asynchronous learning strategy. Suggested method utilises an asynchronous parameter update mechanism for deep neural networks and integrates a temporally weighted aggregate strategy to improve the convergence and accuracy of core model. The efficacy of the proposed AFLCP technique is assessed using two datasets across several DNN architectures, revealing that proposed AFLCP method surpasses baseline technique for communication expenses and model correctness.
- 7 November 2024
- Published by National Environmentalists Association in The Bioscan
- Vol. 19 (Special -1) , 653-660
Open AccessPredicting Cardiovascular Disease by Integrating the Dataset and DNN with Asynchronous Learning Technique
Predicting cardiovascular illness via the integration of datasets and deep neural networks using an asynchronous learning methodology. Healthcare experts see the prediction of cardiac disease as a critical endeavour, while deep learning has shown considerable potential in accomplishing this objective. This research study presents a unique methodology termed the Asynchronous Federated Deep Learning Approach aimed at Cardiac Predictions (AFLCP), which integrates a heart disease dataset along with DNN through an asynchronous learning strategy. Suggested method utilises an asynchronous parameter update mechanism for deep neural networks and integrates a temporally weighted aggregate strategy to improve the convergence and accuracy of core model. The efficacy of the proposed AFLCP technique is assessed using two datasets across several DNN architectures, revealing that proposed AFLCP method surpasses baseline technique for communication expenses and model correctness.