M. Gomathy Nayagam
M. Gomathy Nayagam has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
K. Ramar
2 shared publicationsP. Sobiya
Department of computer science, Einstein College of Engineering, Tirunelveli
2 shared publicationsB. Jegajohi
Sri Venkateswara College of Engineering, Sriperumbudur, Chennai, Tamil Nadu, India
1 shared publication- Dhinakaran Damodaran
Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, India
1 shared publication - Erana Veerappa Dinesh Subramaniam
Ramco Institute of Technology, Anna University
1 shared publication - J. Jeno Jasmine
Department of Computer Science and Engineering (AIML) Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai India
1 shared publication
Latest Publications
- 13 November 2026
- Published by Wiley in Security and Privacy
- Vol. 9 (6)
Enterprise‐Oriented Blockchain‐Anchored Cryptographic Framework With Policy‐Driven Security for IoMT Data and Model Protection
While the Internet of Medical Things (IoMT) has enhanced intelligent clinical services in enterprise healthcare systems, it also has raised significant challenges for patient data confidentiality, cryptographic key management, secure resource sharing of AI models, and secure access control in the distributed healthcare domain. The objective of this study is to create an enterprise‐oriented blockchain secured cryptographic solution with scalable and verifiable security for IoMT data and AI models throughout their lifecycle. It is designed to combine four complementary phases: Hierarchical Attested Key Bootstrap (HAKB) for distributed key generation, Privacy‐Hardened Encrypted Recordkeeping (PHER) for policy‐aware encryption and secure storage, Attested Verifiable Inference (AVI) for trusted AI inference, and Consensus‐Driven Trust and Key Recovery (CTKR) for threshold‐based key reconstruction and resilient recovery, all supported by blockchain for immutable auditability, distributed trust, and secure model governance. Experimental evaluation on the MIMIC‐IV and Healthcare IoT datasets demonstrates that the proposed framework achieves 32% higher throughput, 35% lower communication overhead, and 28% lower energy consumption compared with the state‐of‐the‐art frameworks QRCF, MQKD, OSGD, CPDPM, and AFCP. Additionally, it achieves a key recovery success rate of 99% in case of multiple custodian node failures, highlighting its superior fault‐tolerance and resilience capabilities. The experimental results demonstrate that the proposed framework provides effective protection for IoMT data and AI models while improving scalability, fault tolerance, and operational efficiency under the evaluated enterprise healthcare environment.
- 13 November 2026
- Published by Wiley in Security and Privacy
- Vol. 9 (6)
Enterprise‐Oriented Blockchain‐Anchored Cryptographic Framework With Policy‐Driven Security for IoMT Data and Model Protection
While the Internet of Medical Things (IoMT) has enhanced intelligent clinical services in enterprise healthcare systems, it also has raised significant challenges for patient data confidentiality, cryptographic key management, secure resource sharing of AI models, and secure access control in the distributed healthcare domain. The objective of this study is to create an enterprise‐oriented blockchain secured cryptographic solution with scalable and verifiable security for IoMT data and AI models throughout their lifecycle. It is designed to combine four complementary phases: Hierarchical Attested Key Bootstrap (HAKB) for distributed key generation, Privacy‐Hardened Encrypted Recordkeeping (PHER) for policy‐aware encryption and secure storage, Attested Verifiable Inference (AVI) for trusted AI inference, and Consensus‐Driven Trust and Key Recovery (CTKR) for threshold‐based key reconstruction and resilient recovery, all supported by blockchain for immutable auditability, distributed trust, and secure model governance. Experimental evaluation on the MIMIC‐IV and Healthcare IoT datasets demonstrates that the proposed framework achieves 32% higher throughput, 35% lower communication overhead, and 28% lower energy consumption compared with the state‐of‐the‐art frameworks QRCF, MQKD, OSGD, CPDPM, and AFCP. Additionally, it achieves a key recovery success rate of 99% in case of multiple custodian node failures, highlighting its superior fault‐tolerance and resilience capabilities. The experimental results demonstrate that the proposed framework provides effective protection for IoMT data and AI models while improving scalability, fault tolerance, and operational efficiency under the evaluated enterprise healthcare environment.
- 10 June 2026
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 72 (8-9) , 1-11
A Three-level Dilated DeepLab V3+ for Accurate Kidney Cancer Classification Using Computed Tomography Images
- 10 June 2026
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 72 (8-9) , 1-11
A Three-level Dilated DeepLab V3+ for Accurate Kidney Cancer Classification Using Computed Tomography Images
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3082 (1) , 100002
A comprehensive survey of machine learning based mobile data traffic prediction models for 5G cellular networks
The advanced progression of mobile technology leads to a dramatic expansion in cellular data traffic (DT). Especially, the development of precise time series mo
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3082 (1) , 100002
A comprehensive survey of machine learning based mobile data traffic prediction models for 5G cellular networks
The advanced progression of mobile technology leads to a dramatic expansion in cellular data traffic (DT). Especially, the development of precise time series mo
- Open Access
- 1 January 2022
- Published by Tech Science Press in Intelligent Automation and Soft Computing
- Vol. 33 (3) , 1485-1499
Moving Object Detection and Tracking Algorithm Using Hybrid Decomposition Parallel Processing
Moving object detection, classification and tracking are more crucial and challenging task in most of the computer vision and machine vision applications such as robot navigation, human behavior analysis, traffic flow analysis and etc. However, most of object detection and tracking algorithms are not suitable for real time processing and causes slower processing speed due to the processing and analyzing of high resolution video from high-end multiple cameras. It requires more computation and storage. To address the aforementioned problem, this paper proposes a way of parallel processing of temporal frame differencing algorithm for object detection and contour tracking using the mixture of functional and domain decomposition parallel processing techniques. It has two main contributions. First, steps of frame differencing are parallelized using functional decomposition technique. Second, the processing of frames in each steps of frame differencing is again parallelized using domain decomposition technique. Finally, the performance is evaluated in Aneka Private Cloud platform and which yields to detect and track the object very swiftly and accurately.
- 1 January 2022
- Published by Tech Science Press in Intelligent Automation and Soft Computing
- Vol. 33 (3) , 1485-1499
Open AccessMoving Object Detection and Tracking Algorithm Using Hybrid Decomposition Parallel Processing
Moving object detection, classification and tracking are more crucial and challenging task in most of the computer vision and machine vision applications such as robot navigation, human behavior analysis, traffic flow analysis and etc. However, most of object detection and tracking algorithms are not suitable for real time processing and causes slower processing speed due to the processing and analyzing of high resolution video from high-end multiple cameras. It requires more computation and storage. To address the aforementioned problem, this paper proposes a way of parallel processing of temporal frame differencing algorithm for object detection and contour tracking using the mixture of functional and domain decomposition parallel processing techniques. It has two main contributions. First, steps of frame differencing are parallelized using functional decomposition technique. Second, the processing of frames in each steps of frame differencing is again parallelized using domain decomposition technique. Finally, the performance is evaluated in Aneka Private Cloud platform and which yields to detect and track the object very swiftly and accurately.
- 25 October 2019
- Published by Elsevier in Computer Communications
- Vol. 149, 343-349
Reliable object recognition system for cloud video data based on LDP features
- 25 October 2019
- Published by Elsevier in Computer Communications
- Vol. 149, 343-349
Reliable object recognition system for cloud video data based on LDP features
- 1 March 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Dominating set based content cloud architecture for video distribution services
Cloud computing is a new infrastructure environment that delivers on the promise of supporting on-demand services in a flexible manner by scheduling bandwidth, storage and compute resources on the fly. Content delivery networks (CDN) based systems are considered as the potential solutions to deliver User-generated content (UGC). But none of the existing CDN based solutions can support all the required features in UGC delivery. In this paper we analyses the various mechanism for deploying video in geographically distributed cloud server and optimal utilization of bandwidth, storage and other computing resources. Optimal Deployment can be done by using Dominating Set Algorithm.
- 1 March 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Dominating set based content cloud architecture for video distribution services
Cloud computing is a new infrastructure environment that delivers on the promise of supporting on-demand services in a flexible manner by scheduling bandwidth, storage and compute resources on the fly. Content delivery networks (CDN) based systems are considered as the potential solutions to deliver User-generated content (UGC). But none of the existing CDN based solutions can support all the required features in UGC delivery. In this paper we analyses the various mechanism for deploying video in geographically distributed cloud server and optimal utilization of bandwidth, storage and other computing resources. Optimal Deployment can be done by using Dominating Set Algorithm.
- 1 February 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
A survey on video distribution services in cloud computing
Cloud computing is a new infrastructure environment that delivers on the promise of supporting on-demand services in a flexible manner by scheduling bandwidth, storage and compute resources on the fly. Content delivery networks (CDN) based systems are considered as the potential solutions to deliver User-generated content (UGC). But none of the existing CDN based solutions can support all the required features in UGC delivery. In this paper we analyses the various mechanism for deploying video in geographically distributed cloud server and optimal utilization of bandwidth, storage and other computing resources. Optimal Deployment can be done by using Nash Bargaining solutions, Greedy algorithm, Convex optimization and Lagrange Duality methods are used.
- 1 February 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
A survey on video distribution services in cloud computing
Cloud computing is a new infrastructure environment that delivers on the promise of supporting on-demand services in a flexible manner by scheduling bandwidth, storage and compute resources on the fly. Content delivery networks (CDN) based systems are considered as the potential solutions to deliver User-generated content (UGC). But none of the existing CDN based solutions can support all the required features in UGC delivery. In this paper we analyses the various mechanism for deploying video in geographically distributed cloud server and optimal utilization of bandwidth, storage and other computing resources. Optimal Deployment can be done by using Nash Bargaining solutions, Greedy algorithm, Convex optimization and Lagrange Duality methods are used.
- 1 March 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 365-368
Efficient Resource Scheduler for Parallel Implementation of MSA Algorithm on Computational Grid
Multiple sequence alignment is the most common task in computational biology. This multiple sequence alignment is computationally difficult and classified as a NP-Hard problem; so approximate algorithm(s) are generally required for most multiple alignment tasks. The Molecular Biologist may require the alignment of thousands of sequences that each can be of many hundreds of amino acids or even several millions of nucleotides. The approximation algorithm requires a long processing period of time to compute near optimal alignment. Thus, one step to reduce the processing time is to parallelize the algorithm. In order to have solution over parallelism method, we can either use expensive multiprocessor programming or cheaper cluster/Grid programming. Multiprocessor systems are specialized expensive hardware and are not commonly available. An alternative cheapest way is to use either a computer cluster or a Computing Grid. A cluster can be used for amino acid sequences and will be very slow for multiple sequence alignment of DNA molecule. So, the computing grid is the only cheapest alternative for performing multiple sequence alignment of DNA molecules. We have designed an efficient grid scheduler to perform the parallel tasks in grid that minimizes the communication cost and time complexity and also implemented parallel algorithm on computing grid. The experimental results show enhanced speedup.
- 1 March 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 365-368
Efficient Resource Scheduler for Parallel Implementation of MSA Algorithm on Computational Grid
Multiple sequence alignment is the most common task in computational biology. This multiple sequence alignment is computationally difficult and classified as a NP-Hard problem; so approximate algorithm(s) are generally required for most multiple alignment tasks. The Molecular Biologist may require the alignment of thousands of sequences that each can be of many hundreds of amino acids or even several millions of nucleotides. The approximation algorithm requires a long processing period of time to compute near optimal alignment. Thus, one step to reduce the processing time is to parallelize the algorithm. In order to have solution over parallelism method, we can either use expensive multiprocessor programming or cheaper cluster/Grid programming. Multiprocessor systems are specialized expensive hardware and are not commonly available. An alternative cheapest way is to use either a computer cluster or a Computing Grid. A cluster can be used for amino acid sequences and will be very slow for multiple sequence alignment of DNA molecule. So, the computing grid is the only cheapest alternative for performing multiple sequence alignment of DNA molecules. We have designed an efficient grid scheduler to perform the parallel tasks in grid that minimizes the communication cost and time complexity and also implemented parallel algorithm on computing grid. The experimental results show enhanced speedup.