M. Therasa
M. Therasa has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- A. Padmashree
Department of Artificial Intelligence and Machine Learning, Bannari Amman Institute of Technology, Sathyamangalam, India
1 shared publication - Gokula Krishnan Vasudevan
Professor, Department of Computer Science and Engineering, Easwari Engineering College, Chennai, Tamil Nadu, India
1 shared publication - J. Deepa
Computer Science and Design, Easwari Engineering College, Chennai, India
1 shared publication - Juli Amala Rani Jeeva
Department of Mathematics, Panimalar Engineering College, Chennai, India
1 shared publication - K. Hema Priya
CSE Department, Easwari Engineering College, Chennai, Tamil Nadu, India
1 shared publication - M Vivekanandan
Assistant Professor, Department of Artificial Intelligence and Data Science, Rajalakshmi Institute of Technology, Chennai, Tamil Nadu, India
1 shared publication
Latest Publications
- 28 September 2025
- Published by Springer Nature in Biomedical Materials & Devices
- Vol. 4 (4) , 1-21
Brain Tumor Classification Using Dynamic Path-Controllable Deep Unfolding Network Optimized Using Duck Swarm Algorithm
- 28 September 2025
- Published by Springer Nature in Biomedical Materials & Devices
- Vol. 4 (4) , 1-21
Brain Tumor Classification Using Dynamic Path-Controllable Deep Unfolding Network Optimized Using Duck Swarm Algorithm
- Open Access
- 14 September 2024
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 8 (6) , 694-706
Explainable deep learning for glaucoma detection: Efficient dense net with quantum-based Dwarf Mongoose optimization
Glaucoma, a progressive eye disease, leads to irreversible vision loss due to optic nerve damage. This study aims to develop a more explainable and interpretable deep learning-based model for the detection and classification of glaucoma, addressing the current limitations in the field. The proposed approach utilizes a modified DenseNet-201 architecture, incorporating an additional transition layer for enhanced glaucoma classification. A pre-trained Efficient DenseNet is applied, and a reweighted cross-entropy loss function is used to handle the class imbalance in the training data. Quantum-based Dwarf Mongoose Optimization (QDMOA) is employed to fine-tune the model’s parameters, minimizing over fitting and improving generalization on small datasets. Experimental results demonstrate that the proposed method effectively detects and classifies two types of glaucoma. The use of dense connections with regularization significantly reduces over fitting, and the reweighted loss function improves model performance on imbalanced data. The developed deep learning model offers improved accuracy in glaucoma detection and classification while addressing the need for more interpretable and reliable models in medical applications. This research provides a practical tool for automated glaucoma screening, which could support ophthalmologists in early diagnosis and treatment, reducing the risk of irreversible vision loss.
- 14 September 2024
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 8 (6) , 694-706
Open AccessExplainable deep learning for glaucoma detection: Efficient dense net with quantum-based Dwarf Mongoose optimization
Glaucoma, a progressive eye disease, leads to irreversible vision loss due to optic nerve damage. This study aims to develop a more explainable and interpretable deep learning-based model for the detection and classification of glaucoma, addressing the current limitations in the field. The proposed approach utilizes a modified DenseNet-201 architecture, incorporating an additional transition layer for enhanced glaucoma classification. A pre-trained Efficient DenseNet is applied, and a reweighted cross-entropy loss function is used to handle the class imbalance in the training data. Quantum-based Dwarf Mongoose Optimization (QDMOA) is employed to fine-tune the model’s parameters, minimizing over fitting and improving generalization on small datasets. Experimental results demonstrate that the proposed method effectively detects and classifies two types of glaucoma. The use of dense connections with regularization significantly reduces over fitting, and the reweighted loss function improves model performance on imbalanced data. The developed deep learning model offers improved accuracy in glaucoma detection and classification while addressing the need for more interpretable and reliable models in medical applications. This research provides a practical tool for automated glaucoma screening, which could support ophthalmologists in early diagnosis and treatment, reducing the risk of irreversible vision loss.
- Open Access
- 23 September 2023
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 11 (3) , 808-813
Deep Learning Method of Predicting MANET Lifetime Using Graph Adversarial Network Routing
The prominence of mobile ad-hoc networks (MANETs) is on the rise. Within the domain of machine learning, a specialized subset known as deep learning (DL) employs diverse methodologies, each providing unique interpretations of the data it processes. In existing system the vulnerabilities of MANETs to security threats stem from factors such as node mobility, the potential for MANETs to provide economical solutions to real-world communication challenges, decentralized management, and constrained bandwidth. The efficacy of encryption and authentication methods in safeguarding MANETs encounters limitations. Intelligence will be the future development direction of network adaptive optimization technology in response to the increasingly complex mobile communication network. Data from mobile communication is a crucial part of the future information society. This paper propose adaptive optimization scheme , employs a machine learning algorithm that is capable of realizing the optimal parameter configuration and coordinating various optimization objectives in response to changes in state and environment. The coordination and advancement of social, versatile and area administrations make the customary informal organization easily change to portable correspondence organization. Creation of a system that can learn some rules from data and apply them to subsequent data processing is the research objective. This paper examines the machine learning-based algorithm for big data analysis and effectively addresses the issue of communication network data using graph theory and the experimental result shows higher lifetime prediction accuracy compare to previous system.
- 23 September 2023
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 11 (3) , 808-813
Open AccessDeep Learning Method of Predicting MANET Lifetime Using Graph Adversarial Network Routing
The prominence of mobile ad-hoc networks (MANETs) is on the rise. Within the domain of machine learning, a specialized subset known as deep learning (DL) employs diverse methodologies, each providing unique interpretations of the data it processes. In existing system the vulnerabilities of MANETs to security threats stem from factors such as node mobility, the potential for MANETs to provide economical solutions to real-world communication challenges, decentralized management, and constrained bandwidth. The efficacy of encryption and authentication methods in safeguarding MANETs encounters limitations. Intelligence will be the future development direction of network adaptive optimization technology in response to the increasingly complex mobile communication network. Data from mobile communication is a crucial part of the future information society. This paper propose adaptive optimization scheme , employs a machine learning algorithm that is capable of realizing the optimal parameter configuration and coordinating various optimization objectives in response to changes in state and environment. The coordination and advancement of social, versatile and area administrations make the customary informal organization easily change to portable correspondence organization. Creation of a system that can learn some rules from data and apply them to subsequent data processing is the research objective. This paper examines the machine learning-based algorithm for big data analysis and effectively addresses the issue of communication network data using graph theory and the experimental result shows higher lifetime prediction accuracy compare to previous system.