Kavitha Maruthai
Kavitha Maruthai has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Sridevi Rajalingam
Department of Electronics and Communication Engineering, K. Ramakrishnan College of Technology , Samayapuram , Trichy , Tamil Nadu India
2 shared publications Albert Alexander Stonier
Associate Professor, Department of Electrical and Electronics Engineering, Kongu Engineering College, Perundurai, Tamilnadu, India
1 shared publication- Babu Munirathinam
Department of Information Technology, Rajalakshmi Engineering College, Thandalam, Chennai, 602 105, Tamil Nadu, India
1 shared publication - Moorthy Sujatha
Koneru Lakshmaiah Education Foundation, India
1 shared publication - Priya Velusamy
Department of Civil Engineering, GMR Institute of Technology, Rajam, India
1 shared publication R Sarath Kumar
Assistant Professor, Department of Electronics and Communication Engineering, Sri Krishna College of Engineering and Technology, Coimbatore. Tamilnadu, India
1 shared publication
Latest Publications
- 20 January 2026
- Published by Springer Nature in Wireless Networks
- Vol. 32 (2) , 863-880
Performance analysis of multiport hilbert curve fractal antenna in mid-band applications
- 20 January 2026
- Published by Springer Nature in Wireless Networks
- Vol. 32 (2) , 863-880
Performance analysis of multiport hilbert curve fractal antenna in mid-band applications
- Open Access
- 13 November 2025
- Published by Walter de Gruyter GmbH in Measurement Science Review
- Vol. 25 (6) , 327-337
TRI-BCC: Tri-Level Breast Cancer Classification via Transfer Learning Networks with Histopathological Images
Breast cancer (BC) is the second most common hereditary cancer in women and is most likely to affect women. The high cost of treating BC has made its prevention an important health issue. However, early detection of BC is a time-consuming and difficult task when using mammogram images. This work introduces a novel TRI-BCC model for BC detection using transfer learning-based tri-level classification with histopathological images. Initially, input images undergo a denoising phase using the Adaptive Brightness Contrast Dynamic Histogram Equalization (ABCDE) technique, which removes noisy artifacts to enhance overall image quality. Following this pre-processing step, a data augmentation phase is employed to synthetically expand the training dataset, thereby improving model generalization and robustness against overfitting. The augmented and pre-processed images are subsequently provided as input to the hybrid Golden Eagle-Whale Optimization (GWO) algorithm, for the segmentation of lesions. In the tri-level classification, transfer learning (TL) models: CapsuleNet, EfficientNet, ShuffleNet, GoogleNet, MobileNet and ResNet are employed to categorize images as benign or malignant (Level-I). Benign cases (Level-II) include Adenosis (AS), Phyllodes tumor (PT), Tubular adenoma (TA) and Fibroadenoma (FA), while malignant cases (Level-II) include Papillary (PC), Mucinous (MC), Lobular (LC), and Ductal (DC) carcinoma. Malignant images are processed using a Randomized Decision Tree (RDT) to classify them into different cancer stages (Level-III) for precise diagnosis. Based on experimental analysis, the TRI-BCC model achieves an overall accuracy of 99.06 % for the categorization of BC. The proposed TRI-BCC model improves overall accuracy by 6.11 %, 0.78 %, 2.66 %, and 13.18 % compared to UNet+YOLO, fine-tuned networks, hybrid deep neural network, and Pa-DBN-BC, respectively.
- 13 November 2025
- Published by Walter de Gruyter GmbH in Measurement Science Review
- Vol. 25 (6) , 327-337
Open AccessTRI-BCC: Tri-Level Breast Cancer Classification via Transfer Learning Networks with Histopathological Images
Breast cancer (BC) is the second most common hereditary cancer in women and is most likely to affect women. The high cost of treating BC has made its prevention an important health issue. However, early detection of BC is a time-consuming and difficult task when using mammogram images. This work introduces a novel TRI-BCC model for BC detection using transfer learning-based tri-level classification with histopathological images. Initially, input images undergo a denoising phase using the Adaptive Brightness Contrast Dynamic Histogram Equalization (ABCDE) technique, which removes noisy artifacts to enhance overall image quality. Following this pre-processing step, a data augmentation phase is employed to synthetically expand the training dataset, thereby improving model generalization and robustness against overfitting. The augmented and pre-processed images are subsequently provided as input to the hybrid Golden Eagle-Whale Optimization (GWO) algorithm, for the segmentation of lesions. In the tri-level classification, transfer learning (TL) models: CapsuleNet, EfficientNet, ShuffleNet, GoogleNet, MobileNet and ResNet are employed to categorize images as benign or malignant (Level-I). Benign cases (Level-II) include Adenosis (AS), Phyllodes tumor (PT), Tubular adenoma (TA) and Fibroadenoma (FA), while malignant cases (Level-II) include Papillary (PC), Mucinous (MC), Lobular (LC), and Ductal (DC) carcinoma. Malignant images are processed using a Randomized Decision Tree (RDT) to classify them into different cancer stages (Level-III) for precise diagnosis. Based on experimental analysis, the TRI-BCC model achieves an overall accuracy of 99.06 % for the categorization of BC. The proposed TRI-BCC model improves overall accuracy by 6.11 %, 0.78 %, 2.66 %, and 13.18 % compared to UNet+YOLO, fine-tuned networks, hybrid deep neural network, and Pa-DBN-BC, respectively.
- Open Access
- 13 November 2025
- Published by Walter de Gruyter GmbH in Measurement Science Review
- Vol. 25 (6) , 327-337
TRI-BCC: Tri-Level Breast Cancer Classification via Transfer Learning Networks with Histopathological Images
Breast cancer (BC) is the second most common hereditary cancer in women and is most likely to affect women. The high cost of treating BC has made its prevention an important health issue. However, early detection of BC is a time-consuming and difficult task when using mammogram images. This work introduces a novel TRI-BCC model for BC detection using transfer learning-based tri-level classification with histopathological images. Initially, input images undergo a denoising phase using the Adaptive Brightness Contrast Dynamic Histogram Equalization (ABCDE) technique, which removes noisy artifacts to enhance overall image quality. Following this pre-processing step, a data augmentation phase is employed to synthetically expand the training dataset, thereby improving model generalization and robustness against overfitting. The augmented and pre-processed images are subsequently provided as input to the hybrid Golden Eagle-Whale Optimization (GWO) algorithm, for the segmentation of lesions. In the tri-level classification, transfer learning (TL) models: CapsuleNet, EfficientNet, ShuffleNet, GoogleNet, MobileNet and ResNet are employed to categorize images as benign or malignant (Level-I). Benign cases (Level-II) include Adenosis (AS), Phyllodes tumor (PT), Tubular adenoma (TA) and Fibroadenoma (FA), while malignant cases (Level-II) include Papillary (PC), Mucinous (MC), Lobular (LC), and Ductal (DC) carcinoma. Malignant images are processed using a Randomized Decision Tree (RDT) to classify them into different cancer stages (Level-III) for precise diagnosis. Based on experimental analysis, the TRI-BCC model achieves an overall accuracy of 99.06 % for the categorization of BC. The proposed TRI-BCC model improves overall accuracy by 6.11 %, 0.78 %, 2.66 %, and 13.18 % compared to UNet+YOLO, fine-tuned networks, hybrid deep neural network, and Pa-DBN-BC, respectively.
- 13 November 2025
- Published by Walter de Gruyter GmbH in Measurement Science Review
- Vol. 25 (6) , 327-337
Open AccessTRI-BCC: Tri-Level Breast Cancer Classification via Transfer Learning Networks with Histopathological Images
Breast cancer (BC) is the second most common hereditary cancer in women and is most likely to affect women. The high cost of treating BC has made its prevention an important health issue. However, early detection of BC is a time-consuming and difficult task when using mammogram images. This work introduces a novel TRI-BCC model for BC detection using transfer learning-based tri-level classification with histopathological images. Initially, input images undergo a denoising phase using the Adaptive Brightness Contrast Dynamic Histogram Equalization (ABCDE) technique, which removes noisy artifacts to enhance overall image quality. Following this pre-processing step, a data augmentation phase is employed to synthetically expand the training dataset, thereby improving model generalization and robustness against overfitting. The augmented and pre-processed images are subsequently provided as input to the hybrid Golden Eagle-Whale Optimization (GWO) algorithm, for the segmentation of lesions. In the tri-level classification, transfer learning (TL) models: CapsuleNet, EfficientNet, ShuffleNet, GoogleNet, MobileNet and ResNet are employed to categorize images as benign or malignant (Level-I). Benign cases (Level-II) include Adenosis (AS), Phyllodes tumor (PT), Tubular adenoma (TA) and Fibroadenoma (FA), while malignant cases (Level-II) include Papillary (PC), Mucinous (MC), Lobular (LC), and Ductal (DC) carcinoma. Malignant images are processed using a Randomized Decision Tree (RDT) to classify them into different cancer stages (Level-III) for precise diagnosis. Based on experimental analysis, the TRI-BCC model achieves an overall accuracy of 99.06 % for the categorization of BC. The proposed TRI-BCC model improves overall accuracy by 6.11 %, 0.78 %, 2.66 %, and 13.18 % compared to UNet+YOLO, fine-tuned networks, hybrid deep neural network, and Pa-DBN-BC, respectively.
- 29 December 2023
- Published by Elsevier in Environmental Research
- Vol. 246, 118089
Assessment of cyclone risk and case study of Gaja cyclone using GIS techniques and machine learning algorithms in coastal zone of Tamil Nadu, India
- 29 December 2023
- Published by Elsevier in Environmental Research
- Vol. 246, 118089
Assessment of cyclone risk and case study of Gaja cyclone using GIS techniques and machine learning algorithms in coastal zone of Tamil Nadu, India
- Open Access
- 1 February 2021
- Published by IOP Publishing in IOP Conference Series: Materials Science and Engineering
- Vol. 1055 (1) , 012126
Enhanced Algorithm for Bio Metric Based Secret Data Hiding
Distributed illustration is used for compression method. For a replacement given fingerprint pictures, represent its patches in line with the wordbook by computing l0-minimization then quantize and cipher the illustration. Experiments additionally illustrates that the algorithmic program is robust to extract trivia. This algorithmic program is economical compared with JPEG, JPEG 2000 and WSQ. All previous strategies have ompressed fingerprint pictures. then compressed pictures 2 finger combination primarily based new finger print produce for prime secure privacy protection. a very distinctive system for shielding fingerprint privacy by combining 2 totally different fingerprints into a replacement identity for authentication. And additionally to classify the coaching samples ought to embrace fingerprints with totally different.
- 1 February 2021
- Published by IOP Publishing in IOP Conference Series: Materials Science and Engineering
- Vol. 1055 (1) , 012126
Open AccessEnhanced Algorithm for Bio Metric Based Secret Data Hiding
Distributed illustration is used for compression method. For a replacement given fingerprint pictures, represent its patches in line with the wordbook by computing l0-minimization then quantize and cipher the illustration. Experiments additionally illustrates that the algorithmic program is robust to extract trivia. This algorithmic program is economical compared with JPEG, JPEG 2000 and WSQ. All previous strategies have ompressed fingerprint pictures. then compressed pictures 2 finger combination primarily based new finger print produce for prime secure privacy protection. a very distinctive system for shielding fingerprint privacy by combining 2 totally different fingerprints into a replacement identity for authentication. And additionally to classify the coaching samples ought to embrace fingerprints with totally different.