N. S. Kalyan Chakravarthy
Research Subjects
N. S. Kalyan Chakravarthy has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Jafar Ali Ibrahim Syed Masood
Vellore Institute of Technology
3 shared publications - Arulmurugan Ramu
K. Zhubanov Aktobe Regional University, Kazakhstan
1 shared publication - Arun Nambi Pandian
High-Performance Computing Research Laboratory, QIS College of Engineering and Technology, Ongole, Andhra Pradesh, India
1 shared publication - D. Bujji Babu
Qis College of Engineering and Technology, India
1 shared publication - Dalia Abdulkareem Shafiq
School of Computer Science, Faculty of Innovation and Technology, Taylor’s University, Subang Jaya 47500, Malaysia
1 shared publication David Asirvatham
Faculty of Innovation and Technology, Taylors University, Subang Jaya, Malaysia
1 shared publication
Latest Publications
- 24 April 2025
- Published by IGI Global Scientific Publishing
- p. 109-134
A Security Scheme Based on Blockchain Technology With Modified Extreme Gradient Boosting Decision Tree-Based Trust Management System for Vehicular Net
VANETs are crucial for ITS, but their wireless nature poses security risks. Blockchain offers secure authentication and privacy. This chapter proposes a BC-based security system with a TMS using RSUs and CAs. The system identifies malicious nodes and forged messages using reputation and message metrics. A modified XGBoost and decision tree model calculate trust based on role, distance, and direct trust assessment. Experiments show BC-TMS is efficient, resilient, and ensures VANET security. Compared to existing centric trust models, the proposed paradigm is straightforward, trustworthy, and effective. In order to test BC-TMS in terms of safety, correctness, and reliability, a series of experiments are carried out, and the findings demonstrate that BC-TMS is not only efficient but also highly resilient, thereby establishing a trust model for VANETs that ensures the utmost security and protection.
- 24 April 2025
- Published by IGI Global Scientific Publishing
- p. 109-134
A Security Scheme Based on Blockchain Technology With Modified Extreme Gradient Boosting Decision Tree-Based Trust Management System for Vehicular Net
VANETs are crucial for ITS, but their wireless nature poses security risks. Blockchain offers secure authentication and privacy. This chapter proposes a BC-based security system with a TMS using RSUs and CAs. The system identifies malicious nodes and forged messages using reputation and message metrics. A modified XGBoost and decision tree model calculate trust based on role, distance, and direct trust assessment. Experiments show BC-TMS is efficient, resilient, and ensures VANET security. Compared to existing centric trust models, the proposed paradigm is straightforward, trustworthy, and effective. In order to test BC-TMS in terms of safety, correctness, and reliability, a series of experiments are carried out, and the findings demonstrate that BC-TMS is not only efficient but also highly resilient, thereby establishing a trust model for VANETs that ensures the utmost security and protection.
- Open Access
- 8 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 112-116
Optimizing Medical Imaging: High-Performance Hardware for Image Processing, Machine Learning
The demand for high-performance hardware solutions for machine learning tasks is growing as medical imaging evolves. In this paper, we will focus on the latest hardware advanced technologies: GPUs, TPUs and FPGAs that can be used for image processing optimization in medical imaging such as brain tumor segmentation or chest X-ray classification. We test these devices on the BraTS and ChestX-ray14 datasets to show how running models quicker increases diagnostic performance. The study offers a comprehensive performance and energy efficiency evaluation of all the considered hardware solutions when training deep learning models for medical imaging, providing clinical guidelines to choose appropriate new-generation accelerators before engaging in expensive leasing contracts.
- 8 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 112-116
Open AccessOptimizing Medical Imaging: High-Performance Hardware for Image Processing, Machine Learning
The demand for high-performance hardware solutions for machine learning tasks is growing as medical imaging evolves. In this paper, we will focus on the latest hardware advanced technologies: GPUs, TPUs and FPGAs that can be used for image processing optimization in medical imaging such as brain tumor segmentation or chest X-ray classification. We test these devices on the BraTS and ChestX-ray14 datasets to show how running models quicker increases diagnostic performance. The study offers a comprehensive performance and energy efficiency evaluation of all the considered hardware solutions when training deep learning models for medical imaging, providing clinical guidelines to choose appropriate new-generation accelerators before engaging in expensive leasing contracts.
- Open Access
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 103687-103703
A Hybrid Deep Learning Model to Predict High-Risk Students in Virtual Learning Environments
Online learning has accelerated with the development of the Internet and communication technology. The widely accessible open online courses are delivered using particular digital environments that allow students to participate at speed and location. Virtual learning environments (VLEs) have developed quickly in recent years, giving students access to high-quality digital resources. Online learning environments have numerous benefits but drawbacks, including poor engagement, high dropout rates, low engagement, and self-regulated behavior, making students define their aims. Forecasting failed students in a VLE can help organizations and teachers improve their pedagogical practices and make data-driven decisions. This work proposes a Hybrid Deep Learning (HDL) approach to predict students’ performance utilizing ECNN (Enhanced Convolution Neural Networks) Resnet model-based classification algorithms. The HDL approach is evaluated using the OULAD (Open University Learning Analytics Dataset), which provides a comprehensive and reliable assessment of the model’s performance. The hybrid DLT approaches, demonstrating superiority, exhibited greater prediction accuracy than the existing classifiers. Additionally, the models’ accuracy increases by about 95.67%, higher than other approaches are DFFNN model (93.9%) and MLP model (71.41%).
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 103687-103703
Open AccessA Hybrid Deep Learning Model to Predict High-Risk Students in Virtual Learning Environments
Online learning has accelerated with the development of the Internet and communication technology. The widely accessible open online courses are delivered using particular digital environments that allow students to participate at speed and location. Virtual learning environments (VLEs) have developed quickly in recent years, giving students access to high-quality digital resources. Online learning environments have numerous benefits but drawbacks, including poor engagement, high dropout rates, low engagement, and self-regulated behavior, making students define their aims. Forecasting failed students in a VLE can help organizations and teachers improve their pedagogical practices and make data-driven decisions. This work proposes a Hybrid Deep Learning (HDL) approach to predict students’ performance utilizing ECNN (Enhanced Convolution Neural Networks) Resnet model-based classification algorithms. The HDL approach is evaluated using the OULAD (Open University Learning Analytics Dataset), which provides a comprehensive and reliable assessment of the model’s performance. The hybrid DLT approaches, demonstrating superiority, exhibited greater prediction accuracy than the existing classifiers. Additionally, the models’ accuracy increases by about 95.67%, higher than other approaches are DFFNN model (93.9%) and MLP model (71.41%).
- 19 April 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 120 (2) , 1279-1289
Harmonic Inversion Based Posterirori Minimization in HPA for 5G Communication Framework
- 19 April 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 120 (2) , 1279-1289
Harmonic Inversion Based Posterirori Minimization in HPA for 5G Communication Framework