Selvakanmani Sethuramalingam
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
Selvakanmani Sethuramalingam has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Aditi Sharma
Department of Computer Science & Engineering, Quantum University, Roorkee, India
2 shared publications - S. Markkandan
School of Electronics Engineering, Vellore Institute of Technology
2 shared publications - Simar Preet Singh
Bennett University
2 shared publications - Surendra Pal Singh
Surveying Engineering Department, Wollega University, Nekemte City, Ethiopia
2 shared publications - Vikas Solanki
Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India
2 shared publications - Bhavani Ravi
Department of Computer Science and Engineering, Rajalakshmi Institute of Technology, Chennai 600010, India
1 shared publication
Latest Publications
- 29 February 2024
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 37 (4) , 1488-1504
Privacy-Preserving Breast Cancer Classification: A Federated Transfer Learning Approach
Breast cancer is deadly cancer causing a considerable number of fatalities among women in worldwide. To enhance patient outcomes as well as survival rates, early and accurate detection is crucial. Machine learning techniques, particularly deep learning, have demonstrated impressive success in various image recognition tasks, including breast cancer classification. However, the reliance on large labeled datasets poses challenges in the medical domain due to privacy issues and data silos. This study proposes a novel transfer learning approach integrated into a federated learning framework to solve the limitations of limited labeled data and data privacy in collaborative healthcare settings. For breast cancer classification, the mammography and MRO images were gathered from three different medical centers. Federated learning, an emerging privacy-preserving paradigm, empowers multiple medical institutions to jointly train the global model while maintaining data decentralization. Our proposed methodology capitalizes on the power of pre-trained ResNet, a deep neural network architecture, as a feature extractor. By fine-tuning the higher layers of ResNet using breast cancer datasets from diverse medical centers, we enable the model to learn specialized features relevant to different domains while leveraging the comprehensive image representations acquired from large-scale datasets like ImageNet. To overcome domain shift challenges caused by variations in data distributions across medical centers, we introduce domain adversarial training. The model learns to minimize the domain discrepancy while maximizing classification accuracy, facilitating the acquisition of domain-invariant features. We conducted extensive experiments on diverse breast cancer datasets obtained from multiple medical centers. Comparative analysis was performed to evaluate the proposed approach against traditional standalone training and federated learning without domain adaptation. When compared with traditional models, our proposed model showed a classification accuracy of 98.8% and a computational time of 12.22 s. The results showcase promising enhancements in classification accuracy and model generalization, underscoring the potential of our method in improving breast cancer classification performance while upholding data privacy in a federated healthcare environment.
- 29 February 2024
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 37 (4) , 1488-1504
Privacy-Preserving Breast Cancer Classification: A Federated Transfer Learning Approach
Breast cancer is deadly cancer causing a considerable number of fatalities among women in worldwide. To enhance patient outcomes as well as survival rates, early and accurate detection is crucial. Machine learning techniques, particularly deep learning, have demonstrated impressive success in various image recognition tasks, including breast cancer classification. However, the reliance on large labeled datasets poses challenges in the medical domain due to privacy issues and data silos. This study proposes a novel transfer learning approach integrated into a federated learning framework to solve the limitations of limited labeled data and data privacy in collaborative healthcare settings. For breast cancer classification, the mammography and MRO images were gathered from three different medical centers. Federated learning, an emerging privacy-preserving paradigm, empowers multiple medical institutions to jointly train the global model while maintaining data decentralization. Our proposed methodology capitalizes on the power of pre-trained ResNet, a deep neural network architecture, as a feature extractor. By fine-tuning the higher layers of ResNet using breast cancer datasets from diverse medical centers, we enable the model to learn specialized features relevant to different domains while leveraging the comprehensive image representations acquired from large-scale datasets like ImageNet. To overcome domain shift challenges caused by variations in data distributions across medical centers, we introduce domain adversarial training. The model learns to minimize the domain discrepancy while maximizing classification accuracy, facilitating the acquisition of domain-invariant features. We conducted extensive experiments on diverse breast cancer datasets obtained from multiple medical centers. Comparative analysis was performed to evaluate the proposed approach against traditional standalone training and federated learning without domain adaptation. When compared with traditional models, our proposed model showed a classification accuracy of 98.8% and a computational time of 12.22 s. The results showcase promising enhancements in classification accuracy and model generalization, underscoring the potential of our method in improving breast cancer classification performance while upholding data privacy in a federated healthcare environment.
- 1 January 2024
- Published by American Scientific Publishing Group (ASPG) LLC
- Vol. 13 (1) , 122-134
Strategic Improved K-Means Clustering in Mining Blood Donor Data Analysis and IoT-based Allocation
This manuscript proposes Strategic Improved K-Means Clustering to simplify blood donor data analysis and distribution. The technique optimizes blood donor system resources via K-Means++ initialization, hierarchical clustering, and smart data dissemination. The paper begins with a comprehensive overview of clustering techniques and their healthcare applications. It illustrates the need for contemporary blood donor data analysis methods for cluster quality and resource allocation. Cluster purity, silhouette coefficient, Davies-Bould in the index, and other performance indicators are used to rigorously compare the recommended technique to 10 established clustering methods. The approach routinely fulfils these conditions, proving that it creates accurate, well-fitting groupings. Ablation tests how much-enhanced initialization, hierarchical clustering, and strategic data placement improve the entire. The study found that these make the procedure dependable and successful for numerous sorts of data. The study shows that the approach may be applied to other data besides blood donor data. Hierarchical clustering provides important information about the dataset's hierarchical patterns, making clustering findings easier to grasp. Resources are better distributed with strategic data dissemination. The recommended strategy is effective in emergencies and areas with changing blood needs. To conclude, Strategic Improved K-Means Clustering evaluates and distributes blood donor data comprehensively. Its flexibility, adaptability, and speed make it excellent for managing healthcare resources and making collective choices …
- 1 January 2024
- Published by American Scientific Publishing Group (ASPG) LLC
- Vol. 13 (1) , 122-134
Strategic Improved K-Means Clustering in Mining Blood Donor Data Analysis and IoT-based Allocation
This manuscript proposes Strategic Improved K-Means Clustering to simplify blood donor data analysis and distribution. The technique optimizes blood donor system resources via K-Means++ initialization, hierarchical clustering, and smart data dissemination. The paper begins with a comprehensive overview of clustering techniques and their healthcare applications. It illustrates the need for contemporary blood donor data analysis methods for cluster quality and resource allocation. Cluster purity, silhouette coefficient, Davies-Bould in the index, and other performance indicators are used to rigorously compare the recommended technique to 10 established clustering methods. The approach routinely fulfils these conditions, proving that it creates accurate, well-fitting groupings. Ablation tests how much-enhanced initialization, hierarchical clustering, and strategic data placement improve the entire. The study found that these make the procedure dependable and successful for numerous sorts of data. The study shows that the approach may be applied to other data besides blood donor data. Hierarchical clustering provides important information about the dataset's hierarchical patterns, making clustering findings easier to grasp. Resources are better distributed with strategic data dissemination. The recommended strategy is effective in emergencies and areas with changing blood needs. To conclude, Strategic Improved K-Means Clustering evaluates and distributes blood donor data comprehensively. Its flexibility, adaptability, and speed make it excellent for managing healthcare resources and making collective choices …
- RetractionOpen Access
- 13 October 2023
- Published by Springer Nature in Arabian Journal of Geosciences
- Vol. 16 (11) , 1
Retraction Note: SVM-based compliance discrepancies detection using remote sensing for organic farms
- 13 October 2023
- Published by Springer Nature in Arabian Journal of Geosciences
- Vol. 16 (11) , 1
RetractionOpen AccessRetraction Note: SVM-based compliance discrepancies detection using remote sensing for organic farms
- Retracted
- 6 July 2021
- Published by Springer Nature in Arabian Journal of Geosciences
- Vol. 14 (14) , 1-10
RETRACTED ARTICLE: SVM-based compliance discrepancies detection using remote sensing for organic farms
- 6 July 2021
- Published by Springer Nature in Arabian Journal of Geosciences
- Vol. 14 (14) , 1-10
RetractedRETRACTED ARTICLE: SVM-based compliance discrepancies detection using remote sensing for organic farms
- Open Access
A Review of routing protocols for mobile cognitive radio ad hoc networks
Ad hoc network is a collection of wireless mobile nodes that dynamically form a temporary network without the use of any existing network infrastructure or centralized administration. A cognitive radio is a radio that can change its transmitter parameters based on interaction with the environment in which it operates. The basic idea of cognitive radio networks is that the unlicensed devices (cognitive radio users or secondary users) need to vacate the spectrum band once the licensed device (primary user) is detected. Cognitive capability and reconfigurability are the key characteristics of cognitive radio. Routing is an important issue in Mobile Cognitive Radio Ad Hoc Networks (MCRAHNs). In this paper, a survey of routing protocols for mobile cognitive radio ad networks is discussed.
Open AccessA Review of routing protocols for mobile cognitive radio ad hoc networks
Ad hoc network is a collection of wireless mobile nodes that dynamically form a temporary network without the use of any existing network infrastructure or centralized administration. A cognitive radio is a radio that can change its transmitter parameters based on interaction with the environment in which it operates. The basic idea of cognitive radio networks is that the unlicensed devices (cognitive radio users or secondary users) need to vacate the spectrum band once the licensed device (primary user) is detected. Cognitive capability and reconfigurability are the key characteristics of cognitive radio. Routing is an important issue in Mobile Cognitive Radio Ad Hoc Networks (MCRAHNs). In this paper, a survey of routing protocols for mobile cognitive radio ad networks is discussed.