Narasimha Swamy Lavudiya
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Narasimha Swamy Lavudiya has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- C. V. P. R. Prasad
Malla Reddy Engineering College for Women (UGC Autonomous)
1 shared publication - Chopparapu Srinivasa Rao1 shared publication
- Garlapati Narayana
Associate Professor, Department of CSE (AIML), Chaitanya Bharathi Institute of Technology, Gandipet, Hyderabad, Telangana, India
1 shared publication - Joel Josephson Pottipadu
Department of Electronics and Communication Engineering, Malla Reddy Engineering College, Hyderabad, India
1 shared publication - L. Bhagyalakshmi
Department of ECE, Rajalakshmi Engineering College, Chennai, India
1 shared publication - M. Vadivukarassi
Sree Dattha Institute of Engineering and Science
1 shared publication
Latest Publications
- Open Access
- 2 October 2024
- Published by Iskender AKKURT in International Journal of Computational and Experimental Science and Engineering
- Vol. 10 (4)
Enhancing Ophthalmological Diagnoses: An Adaptive Ensemble Learning Approach Using Fundus and OCT Imaging
This study presents an innovative Ensemble Disease Learning Algorithm (EDL) for the detection and classification of retinal diseases using fundus images. We enhance our method by incorporating deep learning techniques and multi-modal imaging data, including optical coherence tomography (OCT) images alongside fundus photographs, to provide a more comprehensive understanding of retinal pathology. The advanced EDL integrates Convolutional Neural Networks (CNNs) and attention mechanisms with Capsule Networks (CapsNet) and Support Vector Machine (SVM) classifiers for more nuanced feature extraction and classification. We introduce a novel ensemble adaptive weighting approach that dynamically adjusts classifier weights based on performance across disease types and severity levels, significantly improving the algorithm's handling of complex and rare cases. To enhance model interpretability, we implement an explainable AI component that provides visual heatmaps of the most significant regions for each diagnosis to clinicians. We evaluate the enhanced EDL on a large, diverse dataset encompassing multiple retinal diseases, including diabetic retinopathy, age-related macular degeneration, and glaucoma, across various ethnicities and age groups. Our results demonstrate superior accuracy, sensitivity, and specificity compared to our previous model and other state-of-the-art approaches. A prospective clinical validation study assesses the algorithm's real-world performance. This research advances automated retinal disease diagnosis by making it more robust, accurate, and clinically relevant, potentially improving patient outcomes and global eye care through early disease detection and treatment planning.
- 2 October 2024
- Published by Iskender AKKURT in International Journal of Computational and Experimental Science and Engineering
- Vol. 10 (4)
Open AccessEnhancing Ophthalmological Diagnoses: An Adaptive Ensemble Learning Approach Using Fundus and OCT Imaging
This study presents an innovative Ensemble Disease Learning Algorithm (EDL) for the detection and classification of retinal diseases using fundus images. We enhance our method by incorporating deep learning techniques and multi-modal imaging data, including optical coherence tomography (OCT) images alongside fundus photographs, to provide a more comprehensive understanding of retinal pathology. The advanced EDL integrates Convolutional Neural Networks (CNNs) and attention mechanisms with Capsule Networks (CapsNet) and Support Vector Machine (SVM) classifiers for more nuanced feature extraction and classification. We introduce a novel ensemble adaptive weighting approach that dynamically adjusts classifier weights based on performance across disease types and severity levels, significantly improving the algorithm's handling of complex and rare cases. To enhance model interpretability, we implement an explainable AI component that provides visual heatmaps of the most significant regions for each diagnosis to clinicians. We evaluate the enhanced EDL on a large, diverse dataset encompassing multiple retinal diseases, including diabetic retinopathy, age-related macular degeneration, and glaucoma, across various ethnicities and age groups. Our results demonstrate superior accuracy, sensitivity, and specificity compared to our previous model and other state-of-the-art approaches. A prospective clinical validation study assesses the algorithm's real-world performance. This research advances automated retinal disease diagnosis by making it more robust, accurate, and clinically relevant, potentially improving patient outcomes and global eye care through early disease detection and treatment planning.
- Open Access
- 2 October 2024
- Published by Iskender AKKURT in International Journal of Computational and Experimental Science and Engineering
- Vol. 10 (4)
Real-Time E-commerce Insights with Mean Shift Clustering: A Dynamic Approach to Customer Understanding
In the high-speed universe of internet business, understanding client conduct progressively is urgent for customized encounters and ideal business results. This paper investigates the utilization of Mean Shift bunching, a strong non-parametric thickness-based calculation, for continuous examination in online business. By utilizing Mean Shift's capacity to progressively distinguish bunches of erratic shapes, organizations can acquire important bits of knowledge into client conduct, even as it advances. We show the way that Mean Shift can fragment clients in view of their ongoing perusing movement, search questions, item associations, and buy designs, making dynamic client profiles that mirror their ebb and flow interests and inclinations. This empowers organizations to convey profoundly customized proposals, upgrade valuing techniques, and designer promoting efforts in light of constant client needs. Moreover, we investigate how Mean Shift can be utilized to foresee future client conduct, empowering organizations to expect needs and proactively tailor the shopping experience. The paper additionally addresses the difficulties of carrying out ongoing Mean Shift grouping, including information streaming and adaptability, computational intricacy, and information protection concerns. We finish up by illustrating future exploration headings for improving the viability of Mean Change continuously online business examination, underscoring its capability to reform the manner in which organizations draw in with clients in a dynamic and consistently changing internet based commercial center.
- 2 October 2024
- Published by Iskender AKKURT in International Journal of Computational and Experimental Science and Engineering
- Vol. 10 (4)
Open AccessReal-Time E-commerce Insights with Mean Shift Clustering: A Dynamic Approach to Customer Understanding
In the high-speed universe of internet business, understanding client conduct progressively is urgent for customized encounters and ideal business results. This paper investigates the utilization of Mean Shift bunching, a strong non-parametric thickness-based calculation, for continuous examination in online business. By utilizing Mean Shift's capacity to progressively distinguish bunches of erratic shapes, organizations can acquire important bits of knowledge into client conduct, even as it advances. We show the way that Mean Shift can fragment clients in view of their ongoing perusing movement, search questions, item associations, and buy designs, making dynamic client profiles that mirror their ebb and flow interests and inclinations. This empowers organizations to convey profoundly customized proposals, upgrade valuing techniques, and designer promoting efforts in light of constant client needs. Moreover, we investigate how Mean Shift can be utilized to foresee future client conduct, empowering organizations to expect needs and proactively tailor the shopping experience. The paper additionally addresses the difficulties of carrying out ongoing Mean Shift grouping, including information streaming and adaptability, computational intricacy, and information protection concerns. We finish up by illustrating future exploration headings for improving the viability of Mean Change continuously online business examination, underscoring its capability to reform the manner in which organizations draw in with clients in a dynamic and consistently changing internet based commercial center.
- 3 February 2024
- Published by Springer Nature in SN Computer Science
- Vol. 5 (2) , 1-8
Unveiling the Energy-Based Validation and Verification (EVV) Method for Perceiving and Averting Rank Inconsistency Attacks (RIA) for Guarding IoT Routing
- 3 February 2024
- Published by Springer Nature in SN Computer Science
- Vol. 5 (2) , 1-8
Unveiling the Energy-Based Validation and Verification (EVV) Method for Perceiving and Averting Rank Inconsistency Attacks (RIA) for Guarding IoT Routing