Mangalapalli Vamsikrishna
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
Mangalapalli Vamsikrishna has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- N. Lakshmidevi
Computer Science and Engineering, GMR Institute of Technology, Razam, India
2 shared publications - Praveen Mande
GITAM Deemed to be University
2 shared publications - S. S. Nayak
Department of Computer Science and Engineering, School of Engineering and Technology, Centurion University of Technology & Management, Paralakhemundi, India
2 shared publications - Sasmita Kumari Nayak
Department of Computer Science and Engineering, Centurion University of Technology and Management, Bhubaneswar, Odisha, India
2 shared publications - Abhishek Kumar Pandey
School of Computer Science Engineering and Technology, Bennett University, Greater Noida, India
1 shared publication - Bhagya Prasad Bugge
S.R.K.R Engineering College
1 shared publication
Latest Publications
- Open Access
- 13 February 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
A Modified Chaos-Driven Enhanced Cryptographic Framework for Lightweight and Robust IoT Security in Resource-Constrained Devices
- 13 February 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
Open AccessA Modified Chaos-Driven Enhanced Cryptographic Framework for Lightweight and Robust IoT Security in Resource-Constrained Devices
- Open Access
- 27 October 2025
- Published by Asian Research Association in International Research Journal of Multidisciplinary Technovation
- p. 82-98
A Multi-Label Toxic Comment Classification Framework using under Sampling and Deep Learning Models
Toxic online content poses significant challenges to digital communication platforms, necessitating accurate and balanced classification strategies. Unlike traditional binary classification approaches, this study focuses on multi-label toxic comment classification using the Jigsaw dataset, where each comment may exhibit multiple overlapping toxicity types. To address the severe class imbalance inherent in the dataset, three tailored undersampling strategies—One-vs-Rest Undersampling, Multilabel Random Undersampling (MLRU), and an Improved Threshold-Based Undersampling—are proposed to enhance the representation of minority labels such as threat and identity hate. These undersampled datasets are evaluated using a diverse set of ML and DL models, including Random Forest, XGBoost, CNN, RNN, LSTM, BiLSTM, BERT, and RoBERTa. Experimental results shown that this joint multi-label–specific under sampling combined with advanced classification architectures establish superior models, more evident in early detection of rare but relevant types of toxicity. This work demonstrates that multi-label learning frameworks can serve as an effective approach toward fair and full toxic comment detection.
- 27 October 2025
- Published by Asian Research Association in International Research Journal of Multidisciplinary Technovation
- p. 82-98
Open AccessA Multi-Label Toxic Comment Classification Framework using under Sampling and Deep Learning Models
Toxic online content poses significant challenges to digital communication platforms, necessitating accurate and balanced classification strategies. Unlike traditional binary classification approaches, this study focuses on multi-label toxic comment classification using the Jigsaw dataset, where each comment may exhibit multiple overlapping toxicity types. To address the severe class imbalance inherent in the dataset, three tailored undersampling strategies—One-vs-Rest Undersampling, Multilabel Random Undersampling (MLRU), and an Improved Threshold-Based Undersampling—are proposed to enhance the representation of minority labels such as threat and identity hate. These undersampled datasets are evaluated using a diverse set of ML and DL models, including Random Forest, XGBoost, CNN, RNN, LSTM, BiLSTM, BERT, and RoBERTa. Experimental results shown that this joint multi-label–specific under sampling combined with advanced classification architectures establish superior models, more evident in early detection of rare but relevant types of toxicity. This work demonstrates that multi-label learning frameworks can serve as an effective approach toward fair and full toxic comment detection.
- Open Access
- 1 June 2025
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 38 (3) , 1870-1879
Region based lossless compression for digital images using entropy coding
Image compression is a method for reducing video and image storage space. Moreover, enhancing the performance of the transmission and storage processes is important. The region based coding technique is important for compressing and sending medical images. In the medical field, lossless compression can help telemedicine applications achieve high efficiency. It affects image quality and takes a long time to encode. As a result, this study proposes region-based lossless compression for digital images using entropy coding. The best performance is achieved by segmenting these areas. In this case, an integer wavelet transform (IWT) is utilized after the ROI of the image was manually generated. The IWT compression method is helpful for reversibly reconstructing the original image to the required quality. For enhancing the quality of compression, entropy coding is utilized. By passing images of varying sizes and formats, various quantitative metrics can be determined. The simulation results demonstrate that the region based lossless compression technique utilizing range blocks and iterations resulted in reduced encoding time and improved quality.
- 1 June 2025
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 38 (3) , 1870-1879
Open AccessRegion based lossless compression for digital images using entropy coding
Image compression is a method for reducing video and image storage space. Moreover, enhancing the performance of the transmission and storage processes is important. The region based coding technique is important for compressing and sending medical images. In the medical field, lossless compression can help telemedicine applications achieve high efficiency. It affects image quality and takes a long time to encode. As a result, this study proposes region-based lossless compression for digital images using entropy coding. The best performance is achieved by segmenting these areas. In this case, an integer wavelet transform (IWT) is utilized after the ROI of the image was manually generated. The IWT compression method is helpful for reversibly reconstructing the original image to the required quality. For enhancing the quality of compression, entropy coding is utilized. By passing images of varying sizes and formats, various quantitative metrics can be determined. The simulation results demonstrate that the region based lossless compression technique utilizing range blocks and iterations resulted in reduced encoding time and improved quality.
- Open Access
- 1 April 2025
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 38 (1) , 689-698
An ensemble approach for detection of diabetes using SVM and DT
As diabetes affects the health of the entire population, it is a chronic disease that is still an important worldwide health issue. Diabetes increases the possibility of long-term complications, such as kidney failure and heart disease. If this disease is discovered early, people may live longer and in better health. In order to detect and prevent particular diseases, machine learning (ML) has become essential. An ensemble approach for detection of diabetes using support vector machine (SVM) and decision tree (DT) presents in this paper. In this case, to identify diabetes, two ML techniques are DT and SVM have been combined with an ensemble classifier. They obtain the information, they require from the Public Health Institute’s statistics area. There are 270 records, or instances, in the collection. This dataset includes the following attributes: age, a body mass index (BMI) glucose, and insulin. The development of a system that predictions a patient’s risk of diabetes is the goal of this analysis. Several performance metrics, including F1-score, recall, accuracy, and precision, were used to achieve this. From overall results, 96% of precision, 97% of accuracy, 96% of F1-score, and 97% of recall values are the results achieved for the ensemble model (SVM+DT) which is more effective than other individual ML models as DT and SVM.
- 1 April 2025
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 38 (1) , 689-698
Open AccessAn ensemble approach for detection of diabetes using SVM and DT
As diabetes affects the health of the entire population, it is a chronic disease that is still an important worldwide health issue. Diabetes increases the possibility of long-term complications, such as kidney failure and heart disease. If this disease is discovered early, people may live longer and in better health. In order to detect and prevent particular diseases, machine learning (ML) has become essential. An ensemble approach for detection of diabetes using support vector machine (SVM) and decision tree (DT) presents in this paper. In this case, to identify diabetes, two ML techniques are DT and SVM have been combined with an ensemble classifier. They obtain the information, they require from the Public Health Institute’s statistics area. There are 270 records, or instances, in the collection. This dataset includes the following attributes: age, a body mass index (BMI) glucose, and insulin. The development of a system that predictions a patient’s risk of diabetes is the goal of this analysis. Several performance metrics, including F1-score, recall, accuracy, and precision, were used to achieve this. From overall results, 96% of precision, 97% of accuracy, 96% of F1-score, and 97% of recall values are the results achieved for the ensemble model (SVM+DT) which is more effective than other individual ML models as DT and SVM.
- Open Access
- 21 March 2025
- Published by Asian Research Association in International Research Journal of Multidisciplinary Technovation
- p. 74-86
Insider Threat Detection Using Behavioural Analysis through Machine Learning and Deep Learning Techniques
Insider threats pose a significant security challenge to organizational assets and sensitive information. This paper presents a novel approach to insider threat detection by categorizing features into several behavioral types, including Time-related, User-related, Project and Role-related, Activity-related, Logon-related, USB-related, File-related, and Email-related features. Using a comprehensive dataset of 830 features, this paper addresses the challenge of class imbalance through the Synthetic Minority Over-sampling Technique (SMOTE), which improves the balance and preserves data patterns. Dividing features into distinct behavioral categories enhances the precision of threat detection by focusing on specific patterns and anomalies related to different behaviors. The evaluation of machine learning classifiers demonstrates high accuracy across various feature types: Random Forest achieved 76.4% for Time-related, 96.4% for User-related, 85.3% for Project and Role-related, 91.2% for Activity-related, 65.3% for Logon-related, 81.4% for USB-related, 92.5% for File-related, and 99.8% for email-related features. Artificial Neural Networks (ANN) showed good performance with 72% for Time-related, 85% for User-related, 87.6% for Project and Role-related, 75% for Activity-related, 65.5% for Logon-related, 89.7% for USB-related, 86.5% for File-related, and 90% for email-related features. This work underscores the effectiveness of feature categorization and the SMOTE technique in enhancing classifier performance and provides valuable insights for improving organizational security against insider threats.
- 21 March 2025
- Published by Asian Research Association in International Research Journal of Multidisciplinary Technovation
- p. 74-86
Open AccessInsider Threat Detection Using Behavioural Analysis through Machine Learning and Deep Learning Techniques
Insider threats pose a significant security challenge to organizational assets and sensitive information. This paper presents a novel approach to insider threat detection by categorizing features into several behavioral types, including Time-related, User-related, Project and Role-related, Activity-related, Logon-related, USB-related, File-related, and Email-related features. Using a comprehensive dataset of 830 features, this paper addresses the challenge of class imbalance through the Synthetic Minority Over-sampling Technique (SMOTE), which improves the balance and preserves data patterns. Dividing features into distinct behavioral categories enhances the precision of threat detection by focusing on specific patterns and anomalies related to different behaviors. The evaluation of machine learning classifiers demonstrates high accuracy across various feature types: Random Forest achieved 76.4% for Time-related, 96.4% for User-related, 85.3% for Project and Role-related, 91.2% for Activity-related, 65.3% for Logon-related, 81.4% for USB-related, 92.5% for File-related, and 99.8% for email-related features. Artificial Neural Networks (ANN) showed good performance with 72% for Time-related, 85% for User-related, 87.6% for Project and Role-related, 75% for Activity-related, 65.5% for Logon-related, 89.7% for USB-related, 86.5% for File-related, and 90% for email-related features. This work underscores the effectiveness of feature categorization and the SMOTE technique in enhancing classifier performance and provides valuable insights for improving organizational security against insider threats.
- Open Access
- 1 February 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 15 (1) , 1209-1217
Cloud computing environment based hierarchical anomaly intrusion detection system using artificial neural network
Nowadays, computer technology is essential to everyday life, including banking, education, entertainment, and communication. Network security is essential in the digital era, and detecting intrusion threats is the most difficult problem. As a result, the network is monitored for unusual activity using this hierarchical anomaly intrusion detection system, and when these actions are detected, an alert is generated. This hierarchical anomaly intrusion detection system, which uses artificial neural network (ANN) and is implemented on a cloud computing environment, analyzes data even in the high levels of traffic and protects computer networks and data from malicious activity. As a result, this system shows better detection, accuracy, and precision rates.
- 1 February 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 15 (1) , 1209-1217
Open AccessCloud computing environment based hierarchical anomaly intrusion detection system using artificial neural network
Nowadays, computer technology is essential to everyday life, including banking, education, entertainment, and communication. Network security is essential in the digital era, and detecting intrusion threats is the most difficult problem. As a result, the network is monitored for unusual activity using this hierarchical anomaly intrusion detection system, and when these actions are detected, an alert is generated. This hierarchical anomaly intrusion detection system, which uses artificial neural network (ANN) and is implemented on a cloud computing environment, analyzes data even in the high levels of traffic and protects computer networks and data from malicious activity. As a result, this system shows better detection, accuracy, and precision rates.
- Open Access
- 21 December 2022
- Published by Springer Nature in Wireless Personal Communications
- Vol. 128 (4) , 2981
Correction to: An Optimized Deep Neural Aspect Based Framework for Sentiment Classification
- 21 December 2022
- Published by Springer Nature in Wireless Personal Communications
- Vol. 128 (4) , 2981
Open AccessCorrection to: An Optimized Deep Neural Aspect Based Framework for Sentiment Classification
- 10 October 2022
- Published by Springer Nature in Wireless Personal Communications
- Vol. 128 (4) , 2953-2979
An Optimized Deep Neural Aspect Based Framework for Sentiment Classification
- 10 October 2022
- Published by Springer Nature in Wireless Personal Communications
- Vol. 128 (4) , 2953-2979
An Optimized Deep Neural Aspect Based Framework for Sentiment Classification
- 25 August 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 126 (3) , 2231-2247
Prioritized Energy Efficient Task Scheduling Algorithm in Cloud Computing Using Whale Optimization Algorithm
- 25 August 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 126 (3) , 2231-2247
Prioritized Energy Efficient Task Scheduling Algorithm in Cloud Computing Using Whale Optimization Algorithm