H. L. Parashivamurthy
H. L. Parashivamurthy has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
G. Dakshayini
Department of Mathematics, Faculty of Engineering, Management, and Technology, Adichunchanagiri University, Mandya, India
1 shared publicationH. N. Shwetha
Department of Mathematics, Faculty of Engineering, Management, and Technology, Adichunchanagiri University, Mandya, India
1 shared publicationJaveriya Amreen N. A.
Department of Mathematics, Faculty of Engineering, Management, and Technology, Adichunchanagiri University, Mandya, India
1 shared publication- Kiran Puttegowda
Department of Electronics and Communication Engineering, Vidyavardhaka College of Engineering, Mysuru, Karnataka, India, Visvesvaraya Technological University, Belagavi, India
1 shared publication - M. Sudhakar
Department of Social Work, PSG College of Arts and Science, Coimbatore, India
1 shared publication - Ranjan Kumar H S
Department of Artificial Intelligence and Data Science, Shri Madhwa Vadhiraja Institute of Technology and Management: Udupi, Bantakal, India
1 shared publication
Latest Publications
- Open Access
- 10 March 2026
- Published by The ScienceIn Publishing in Journal of Integrated Science and Technology
- Vol. 14 (4)
Accurate Mammogram classification for Breast Cancer detection using Transfer Learning-based CNN models
Breast cancer is one of the leading causes of mortality among women worldwide, making early and accurate diagnosis essential for effective treatment and improved survival rates. Mammography is widely considered the standard screening technique for detecting early signs of breast cancer; however, manual interpretation of mammograms may lead to diagnostic errors, resulting in missed detections or unnecessary treatments. To address these challenges, this study proposes an enhanced machine learning–based framework for accurate breast cancer diagnosis using mammographic images. The proposed approach utilizes deep learning techniques, particularly Convolutional Neural Networks (CNNs), to automatically learn discriminative features from mammograms. Several state-of-the-art architectures, including VGG19, ResNet50, InceptionV3, DenseNet121, and MobileNetV2, are evaluated to analyze their effectiveness in breast cancer classification. The framework incorporates multiple optimization strategies such as transfer learning, class weighting to handle imbalanced datasets, and variations in input image sizes to improve model performance. Experimental evaluation is conducted using the CBIS-DDSM and mini-MIAS mammogram datasets. Among the tested models, the MobileNetV2 architecture combined with transfer learning from ImageNet and additional pre-trained weights demonstrates superior performance, achieving an accuracy of 87.08% on the CBIS-DDSM dataset. Furthermore, separating mammogram samples into masses and calcifications and applying class weights contribute to improved classification performance. The results are compared with existing approaches, demonstrating the effectiveness of the proposed enhanced machine learning framework for breast cancer detection in mammographic images.
- 10 March 2026
- Published by The ScienceIn Publishing in Journal of Integrated Science and Technology
- Vol. 14 (4)
Open AccessAccurate Mammogram classification for Breast Cancer detection using Transfer Learning-based CNN models
Breast cancer is one of the leading causes of mortality among women worldwide, making early and accurate diagnosis essential for effective treatment and improved survival rates. Mammography is widely considered the standard screening technique for detecting early signs of breast cancer; however, manual interpretation of mammograms may lead to diagnostic errors, resulting in missed detections or unnecessary treatments. To address these challenges, this study proposes an enhanced machine learning–based framework for accurate breast cancer diagnosis using mammographic images. The proposed approach utilizes deep learning techniques, particularly Convolutional Neural Networks (CNNs), to automatically learn discriminative features from mammograms. Several state-of-the-art architectures, including VGG19, ResNet50, InceptionV3, DenseNet121, and MobileNetV2, are evaluated to analyze their effectiveness in breast cancer classification. The framework incorporates multiple optimization strategies such as transfer learning, class weighting to handle imbalanced datasets, and variations in input image sizes to improve model performance. Experimental evaluation is conducted using the CBIS-DDSM and mini-MIAS mammogram datasets. Among the tested models, the MobileNetV2 architecture combined with transfer learning from ImageNet and additional pre-trained weights demonstrates superior performance, achieving an accuracy of 87.08% on the CBIS-DDSM dataset. Furthermore, separating mammogram samples into masses and calcifications and applying class weights contribute to improved classification performance. The results are compared with existing approaches, demonstrating the effectiveness of the proposed enhanced machine learning framework for breast cancer detection in mammographic images.
- 18 April 2025
- Published by IGI Global Scientific Publishing
- p. 259-282
Advanced Analysis and Comparison of Graph Energies
Different types of graph energies have been comprehensively explored throughout the chapter based on seminal work by I. Gutman. Attention was paid to Seidel energy, distance energy, Harary energy, maximum degree energy, Randić energy, and Laplacian energy. The objective was to discuss their properties systematically, their interrelations, and applications. In the chapter, a deep comparison across various graph structures is performed, showing how each of the mentioned energy functions is influencing graph theory and possible applications. Combining theoretical considerations with practical examples, this chapter allows for an improved understanding of graph energies and their implications in view of both pure and applied mathematics. The results provide interesting insights for both theorists and practitioners interested in using the properties of graph energies in different fields.
- 18 April 2025
- Published by IGI Global Scientific Publishing
- p. 259-282
Advanced Analysis and Comparison of Graph Energies
Different types of graph energies have been comprehensively explored throughout the chapter based on seminal work by I. Gutman. Attention was paid to Seidel energy, distance energy, Harary energy, maximum degree energy, Randić energy, and Laplacian energy. The objective was to discuss their properties systematically, their interrelations, and applications. In the chapter, a deep comparison across various graph structures is performed, showing how each of the mentioned energy functions is influencing graph theory and possible applications. Combining theoretical considerations with practical examples, this chapter allows for an improved understanding of graph energies and their implications in view of both pure and applied mathematics. The results provide interesting insights for both theorists and practitioners interested in using the properties of graph energies in different fields.
- 18 April 2025
- Published by IGI Global Scientific Publishing
- p. 283-308
Exponential P1-Distance Energy of Graphs
In this chapter, a new energy measure in graph theory has been introduced, namely, p1-distance energy, which has emerged from the incorporation of distances and matrices into the classical concept of the energy of graphs. The authors extend Gutman's pioneering work on this new energy measure, namely, p1-distance energy for some fundamental graph structures, such as crown graphs, cocktail party graphs, and complete bipartite graphs. In each class of graphs, they perform detailed computations to get their respective p1-distance energies and discuss special features, hence, possible trend exhibited by them. This work shows that the new measure of energy can provide deeper insights into graph characteristics, from theoretical research to practical applications in physics, chemistry, and network analysis. The work on given concrete graph structures opens an avenue for further studies on p1-distance energy of other complex networks, enriching a broader exploration of energy measures in graph theory.
- 18 April 2025
- Published by IGI Global Scientific Publishing
- p. 283-308
Exponential P1-Distance Energy of Graphs
In this chapter, a new energy measure in graph theory has been introduced, namely, p1-distance energy, which has emerged from the incorporation of distances and matrices into the classical concept of the energy of graphs. The authors extend Gutman's pioneering work on this new energy measure, namely, p1-distance energy for some fundamental graph structures, such as crown graphs, cocktail party graphs, and complete bipartite graphs. In each class of graphs, they perform detailed computations to get their respective p1-distance energies and discuss special features, hence, possible trend exhibited by them. This work shows that the new measure of energy can provide deeper insights into graph characteristics, from theoretical research to practical applications in physics, chemistry, and network analysis. The work on given concrete graph structures opens an avenue for further studies on p1-distance energy of other complex networks, enriching a broader exploration of energy measures in graph theory.