Vellingiri Jayagopal
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
Vellingiri Jayagopal has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Abolfazl Mehbodniya
Department of Electronics and Communication Engineering, Kuwait College of Science and Technology, Kuwait City, Kuwait
2 shared publications C. Bala Subramanian
Department of Computer Science Engineering, Kalasalingam Academy of Research and Education, Krishnankoil, India
2 shared publications- D. Stalin David
Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College
2 shared publications - Gobinath C
School of Computer Science and Engineering, REVA University, Bengaluru, India
2 shared publications - Julian L. Webber
Kuwait College of Science and Technology, Safat, Kuwait
2 shared publications Kalaivanan K
School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore-632014, India
2 shared publications
Latest Publications
- 22 September 2026
- Published by Springer Nature in Evolving Systems
- Vol. 17 (4) , 116
Adaptive and attentive-based recurrent MobileNet for brain tumour segmentation and classification
- 22 September 2026
- Published by Springer Nature in Evolving Systems
- Vol. 17 (4) , 116
Adaptive and attentive-based recurrent MobileNet for brain tumour segmentation and classification
- Open Access
- 11 September 2026
- Published by Frontiers Media SA in Frontiers in Oncology
- Vol. 16, 1907746
An explainable dual-branch transformer–ConvNeXt framework for robust lung histopathology classification
Introduction: Accurate histopathological discrimination of lung adenocarcinoma (ACA) and squamous cell carcinoma (SCC) from benign tissue is a clinically demanding task in which the two malignant subtypes are frequently confused even by trained pathologists. Methods: We present a dual-branch deep learning framework that couples a hierarchical shifted-window vision transformer (SwinV2-CR-Tiny) with a fully-convolutional masked-autoencoder-pretrained convolutional network (ConvNeXtV2-Tiny) to capture complementary global-contextual and local-textural representations of haematoxylin-and-eosin (H&E) stained tissue. The two branches are integrated through a learnable cross-feature gating module, refined by feature-space gated-modulation heads, and compressed by an Electric-Eel-Foraging-Optimizer (EEFO)-driven feature-selection stage. A Crested-Porcupine-Optimizer (CPO) calibrates class weighting and a Fennec-Fox-Optimizer (FFO) tunes per-class decision thresholds, while training combines Macenko stain normalization, CLAHE, MixUp/CutMix augmentation, a focal loss with label smoothing, Sharpness-Aware Minimization (SAM) and Stochastic Weight Averaging (SWA). Predictive uncertainty is quantified by Monte-Carlo (MC) dropout and model decisions are explained with Grad-CAM++ and Integrated Gradients. The model was evaluated on a stratified 70/15/15 partition of the LC25000 lung cohort (15,000 images; 5,000 per class). Results: The proposed model attains a test accuracy of 94.04%, macro-F1 of 0.9404, macro one-vs-rest AUC of 0.9886 and Cohen's κ of 0.9107, with near-perfect benign separation (sensitivity 0.999) and the residual error concentrated in the clinically expected ACA↔SCC confusion. Contrary to our prior expectation, MC-dropout predictive uncertainty did not separate misclassified from correctly classified cases on this cohort (mean across-pass standard deviation 0.0261 for errors versus 0.0269 for correct predictions). We additionally report a negative calibration finding: the model is systematically under-confident and naive temperature scaling increased the expected calibration error. Discussion: The negative uncertainty result is attributed to the same confidence-suppressing training objective and is reported rather than omitted. We further discuss the data-provenance characteristics of LC25000 that constrain the interpretation of absolute accuracy. The framework offers an interpret-able, transparently-evaluated decision-support pipeline whose error profile aligns with established lung-cancer histomorphology.
- 11 September 2026
- Published by Frontiers Media SA in Frontiers in Oncology
- Vol. 16, 1907746
Open AccessAn explainable dual-branch transformer–ConvNeXt framework for robust lung histopathology classification
Introduction: Accurate histopathological discrimination of lung adenocarcinoma (ACA) and squamous cell carcinoma (SCC) from benign tissue is a clinically demanding task in which the two malignant subtypes are frequently confused even by trained pathologists. Methods: We present a dual-branch deep learning framework that couples a hierarchical shifted-window vision transformer (SwinV2-CR-Tiny) with a fully-convolutional masked-autoencoder-pretrained convolutional network (ConvNeXtV2-Tiny) to capture complementary global-contextual and local-textural representations of haematoxylin-and-eosin (H&E) stained tissue. The two branches are integrated through a learnable cross-feature gating module, refined by feature-space gated-modulation heads, and compressed by an Electric-Eel-Foraging-Optimizer (EEFO)-driven feature-selection stage. A Crested-Porcupine-Optimizer (CPO) calibrates class weighting and a Fennec-Fox-Optimizer (FFO) tunes per-class decision thresholds, while training combines Macenko stain normalization, CLAHE, MixUp/CutMix augmentation, a focal loss with label smoothing, Sharpness-Aware Minimization (SAM) and Stochastic Weight Averaging (SWA). Predictive uncertainty is quantified by Monte-Carlo (MC) dropout and model decisions are explained with Grad-CAM++ and Integrated Gradients. The model was evaluated on a stratified 70/15/15 partition of the LC25000 lung cohort (15,000 images; 5,000 per class). Results: The proposed model attains a test accuracy of 94.04%, macro-F1 of 0.9404, macro one-vs-rest AUC of 0.9886 and Cohen's κ of 0.9107, with near-perfect benign separation (sensitivity 0.999) and the residual error concentrated in the clinically expected ACA↔SCC confusion. Contrary to our prior expectation, MC-dropout predictive uncertainty did not separate misclassified from correctly classified cases on this cohort (mean across-pass standard deviation 0.0261 for errors versus 0.0269 for correct predictions). We additionally report a negative calibration finding: the model is systematically under-confident and naive temperature scaling increased the expected calibration error. Discussion: The negative uncertainty result is attributed to the same confidence-suppressing training objective and is reported rather than omitted. We further discuss the data-provenance characteristics of LC25000 that constrain the interpretation of absolute accuracy. The framework offers an interpret-able, transparently-evaluated decision-support pipeline whose error profile aligns with established lung-cancer histomorphology.
- 29 August 2025
- Published by Springer Nature
- p. 241-253
Gesture Assist: A Companion for Elderly with Gesture and Emotion Recognition
- 29 August 2025
- Published by Springer Nature
- p. 241-253
Gesture Assist: A Companion for Elderly with Gesture and Emotion Recognition
- 26 June 2025
- Published by Wiley in International Journal of Communication Systems
- Vol. 38 (12)
Enhanced VANET Communication: Fractional Order Water Flow Optimization and Secure Communication via Spatial Bayesian Neural Network
The strategic aim of vehicular ad hoc networks (VANETs) is to ensure efficient service delivery in urban environments, relying on seamless integration and communication among vehicles, sensors, and fixed roadside components. VANET exhibit unique characteristics such as rapid node mobility, self‐organization, dispersed networks, and dynamic topologies. Significant advancements have been made in strengthening security, focusing on improving data integrity, enhancing user privacy, and effectively detecting Sybil attacks, where a single node impersonates multiple entities advancing privacy preservation measures. Existing solutions often fall short in addressing these concerns comprehensively. To tackle these challenges, Enhanced VANET Communication: Fractional Order Water Flow Optimizer and Secure encryption–based Communication through Spatial Bayesian Neural Network (VANET‐SC‐SBNN) is proposed. Initially, the input data are gathered from VeReMi dataset. It uses Localized Sparse Incomplete Multiview Clustering (LSIMC) to group vehicles and identify cluster centres. The Humboldt Squid Optimization Algorithm (HSOA) is employed for selecting cluster heads. The Spatial Bayesian Neural Network (SBNN) is used to identify malicious Cluster Heads (CHs) by extracting useful information from them. Fractional Order Water Flow Optimizer (FOWFO) is used for optimizing the SBNN parameters. The Polymorphic Advanced Encryption Standard (PAES) is adopted to securely transmit data from CHs to the cloud. The proposed VANET‐SC‐SBNN is implemented in Python, and the performance is evaluated under performance metrics such as accuracy, precision, recall, F‐measure, security, and encryption time. The proposed VANET‐SC‐SBNN method achieves 17.17%, 19.52%, and 19.25% higher accuracy; 17.45%, 18.62%, and 24.11% higher precision; and 19.45%, 17.72%, and 18.19% higher F‐measure. The performance of the proposed approach is compared with existing techniques: Floyd‐Warshall algorithm and modified advanced encryption standard for secured communication in VANET (FWA‐SC‐VANET), an effective and physically safe privacy‐preserving key‐agreement protocol for vehicular ad hoc network (PSP‐PKP‐VANET), provably secure conditional‐privacy access control protocol for intelligent customers‐centric communication in vanet (SC‐PCC‐VANET) methods, respectively.
- 26 June 2025
- Published by Wiley in International Journal of Communication Systems
- Vol. 38 (12)
Enhanced VANET Communication: Fractional Order Water Flow Optimization and Secure Communication via Spatial Bayesian Neural Network
The strategic aim of vehicular ad hoc networks (VANETs) is to ensure efficient service delivery in urban environments, relying on seamless integration and communication among vehicles, sensors, and fixed roadside components. VANET exhibit unique characteristics such as rapid node mobility, self‐organization, dispersed networks, and dynamic topologies. Significant advancements have been made in strengthening security, focusing on improving data integrity, enhancing user privacy, and effectively detecting Sybil attacks, where a single node impersonates multiple entities advancing privacy preservation measures. Existing solutions often fall short in addressing these concerns comprehensively. To tackle these challenges, Enhanced VANET Communication: Fractional Order Water Flow Optimizer and Secure encryption–based Communication through Spatial Bayesian Neural Network (VANET‐SC‐SBNN) is proposed. Initially, the input data are gathered from VeReMi dataset. It uses Localized Sparse Incomplete Multiview Clustering (LSIMC) to group vehicles and identify cluster centres. The Humboldt Squid Optimization Algorithm (HSOA) is employed for selecting cluster heads. The Spatial Bayesian Neural Network (SBNN) is used to identify malicious Cluster Heads (CHs) by extracting useful information from them. Fractional Order Water Flow Optimizer (FOWFO) is used for optimizing the SBNN parameters. The Polymorphic Advanced Encryption Standard (PAES) is adopted to securely transmit data from CHs to the cloud. The proposed VANET‐SC‐SBNN is implemented in Python, and the performance is evaluated under performance metrics such as accuracy, precision, recall, F‐measure, security, and encryption time. The proposed VANET‐SC‐SBNN method achieves 17.17%, 19.52%, and 19.25% higher accuracy; 17.45%, 18.62%, and 24.11% higher precision; and 19.45%, 17.72%, and 18.19% higher F‐measure. The performance of the proposed approach is compared with existing techniques: Floyd‐Warshall algorithm and modified advanced encryption standard for secured communication in VANET (FWA‐SC‐VANET), an effective and physically safe privacy‐preserving key‐agreement protocol for vehicular ad hoc network (PSP‐PKP‐VANET), provably secure conditional‐privacy access control protocol for intelligent customers‐centric communication in vanet (SC‐PCC‐VANET) methods, respectively.
- 17 April 2025
- Published by Springer Nature in Earth Science Informatics
- Vol. 18 (2) , 1-28
EADCN-BCSR: A novel framework for accurate and real-time waste detection and classification
- 17 April 2025
- Published by Springer Nature in Earth Science Informatics
- Vol. 18 (2) , 1-28
EADCN-BCSR: A novel framework for accurate and real-time waste detection and classification
- Open Access
- 16 December 2024
- Published by Springer Nature in Journal of Plant Diseases and Protection
- Vol. 132 (1) , 1-12
EnConv: enhanced CNN for leaf disease classification
Detecting leaf diseases in plants is essential to maintain crop yield and market value. Machine learning has shown promise in detecting these diseases as it can group data into predetermined categories after examining it from various angles. However, machine learning models require a thorough knowledge of plant diseases, and processing time can be lengthy. This study proposes an enhanced convolutional neural network that utilizes depthwise separable convolution and inverted residual blocks to detect leaf diseases in plants. The model considers the morphological properties and characteristics of the plant leaves, including color, intensity, and size, to categorize the data. The proposed model outperforms traditional machine learning approaches and deep learning models, achieving an accuracy of 99.87% for 39 classes of different plants such as tomato, corn, apple, potato, and more. To further improve the model, global average pooling was used in place of the flatten layer. Overall, this study presents a promising approach to detect leaf diseases in plants using an enhanced convolutional neural network with depthwise separable convolution and inverted residual blocks. The results show the potential benefits of using this model in agriculture to improve the early detection of plant diseases and maintain crop yield and market value.
- 16 December 2024
- Published by Springer Nature in Journal of Plant Diseases and Protection
- Vol. 132 (1) , 1-12
Open AccessEnConv: enhanced CNN for leaf disease classification
Detecting leaf diseases in plants is essential to maintain crop yield and market value. Machine learning has shown promise in detecting these diseases as it can group data into predetermined categories after examining it from various angles. However, machine learning models require a thorough knowledge of plant diseases, and processing time can be lengthy. This study proposes an enhanced convolutional neural network that utilizes depthwise separable convolution and inverted residual blocks to detect leaf diseases in plants. The model considers the morphological properties and characteristics of the plant leaves, including color, intensity, and size, to categorize the data. The proposed model outperforms traditional machine learning approaches and deep learning models, achieving an accuracy of 99.87% for 39 classes of different plants such as tomato, corn, apple, potato, and more. To further improve the model, global average pooling was used in place of the flatten layer. Overall, this study presents a promising approach to detect leaf diseases in plants using an enhanced convolutional neural network with depthwise separable convolution and inverted residual blocks. The results show the potential benefits of using this model in agriculture to improve the early detection of plant diseases and maintain crop yield and market value.
- Open Access
- 25 October 2024
- Published by Springer Nature in Peer-to-Peer Networking and Applications
- Vol. 17 (6) , 4396
Correction to: Fuzzy logic and CPSO-optimized key management for secure communication in decentralized IoT networks: A lightweight solution
- 25 October 2024
- Published by Springer Nature in Peer-to-Peer Networking and Applications
- Vol. 17 (6) , 4396
Open AccessCorrection to: Fuzzy logic and CPSO-optimized key management for secure communication in decentralized IoT networks: A lightweight solution
- Open Access
- 28 June 2024
- Published by The Korean Society of Economic and Environmental Geology in Economic and Environmental Geology
- Vol. 57 (3) , 329-342
A Grey Wolf Optimized- Stacked Ensemble Approach for Nitrate Contamination Prediction in Cauvery Delta
Kalaivanan K, Vellingiri J. Econ. Environ. Geol. 2024;57:329-42. https://doi.org/10.9719/EEG.2024.57.3.329
- 28 June 2024
- Published by The Korean Society of Economic and Environmental Geology in Economic and Environmental Geology
- Vol. 57 (3) , 329-342
Open AccessA Grey Wolf Optimized- Stacked Ensemble Approach for Nitrate Contamination Prediction in Cauvery Delta
Kalaivanan K, Vellingiri J. Econ. Environ. Geol. 2024;57:329-42. https://doi.org/10.9719/EEG.2024.57.3.329
- 8 June 2024
- Published by Springer Nature in Peer-to-Peer Networking and Applications
- Vol. 17 (5) , 2979-2997
Fuzzy logic and CPSO-optimized key management for secure communication in decentralized IoT networks: A lightweight solution
- 8 June 2024
- Published by Springer Nature in Peer-to-Peer Networking and Applications
- Vol. 17 (5) , 2979-2997
Fuzzy logic and CPSO-optimized key management for secure communication in decentralized IoT networks: A lightweight solution
- 17 June 2023
- Published by Springer Nature in SN Computer Science
- Vol. 4 (5) , 1-7
Intrusion Detection System in Industrial Cyber-Physical System Using Clustered Federated Learning
- 17 June 2023
- Published by Springer Nature in SN Computer Science
- Vol. 4 (5) , 1-7
Intrusion Detection System in Industrial Cyber-Physical System Using Clustered Federated Learning