Parthiban Krishnamoorthy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Parthiban Krishnamoorthy has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Ananya Ghosh
Vellore Institute of Technology
3 shared publications A. K. Saini
Department of Computer Science and Engineering
1 shared publication- Alazar Yeshitla
Department of Biotechnology, College of Biological and Chemical Engineering, Addis Ababa Science and Technology University, Addis Ababa, Ethiopia
1 shared publication - Arulkumar Varatharajan
Vellore Institute of Technology
1 shared publication - E Bhuvaneswari1 shared publication
- Hemant Palivela
Damac Properties, LLC, Dubai, United Arab Emirates
1 shared publication
Latest Publications
- Open Access
- 16 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 135040-135062
FedADC: Federated Average Knowledge Distilled Mutual Conditional Learning (FedADC) for Waste Classification
Federated learning presents a potent avenue for addressing challenges in waste classification, where diverse datasets are distributed across sources. This paper introduces the Federated Average Knowledge Distilled Mutual Conditional Learning (FedADC) algorithm, a novel framework tailored for efficient waste classification in federated settings. FedADC combines federated learning with knowledge distillation and mutual conditional learning, offering a sophisticated approach to model training and adaptation. The bidirectional learning process enables dynamic adjustments to local dataset nuances, enhancing model accuracy. A pivotal contribution of this work is the comparative analysis of hyperparameter tuning techniques, revealing the superiority of GridSearch for fine-tuning in federated learning. Additionally, the paper explores and compares data augmentation, denoising strategies, and cross-validation techniques, providing insights that amplify the adaptability of the proposed model. The FedADC algorithm, coupled with these nuanced contributions, advances the understanding and application of federated learning in waste classification. Through a hybrid learning paradigm, rigorous parameter exploration, and meticulous validation strategies, this research establishes a foundation for robust and effective waste management solutions in federated settings.
- 16 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 135040-135062
Open AccessFedADC: Federated Average Knowledge Distilled Mutual Conditional Learning (FedADC) for Waste Classification
Federated learning presents a potent avenue for addressing challenges in waste classification, where diverse datasets are distributed across sources. This paper introduces the Federated Average Knowledge Distilled Mutual Conditional Learning (FedADC) algorithm, a novel framework tailored for efficient waste classification in federated settings. FedADC combines federated learning with knowledge distillation and mutual conditional learning, offering a sophisticated approach to model training and adaptation. The bidirectional learning process enables dynamic adjustments to local dataset nuances, enhancing model accuracy. A pivotal contribution of this work is the comparative analysis of hyperparameter tuning techniques, revealing the superiority of GridSearch for fine-tuning in federated learning. Additionally, the paper explores and compares data augmentation, denoising strategies, and cross-validation techniques, providing insights that amplify the adaptability of the proposed model. The FedADC algorithm, coupled with these nuanced contributions, advances the understanding and application of federated learning in waste classification. Through a hybrid learning paradigm, rigorous parameter exploration, and meticulous validation strategies, this research establishes a foundation for robust and effective waste management solutions in federated settings.
- 16 April 2024
- Published by Taylor & Francis
- p. 82-100
Convergence of Modern Technologies for Data Architectures
The rapid growth of the Internet of Things (IoT) and smart gadgets has affected every industry. Services must be reliable, high-performing, scalable, and ubiquitous for the IoT and related devices. SDN, Cloud IoT, Cloudlet, Mobile Computing (MC), Transparent Computing (TC), and Dew Computing are novel paradigms that achieve these attributes (DC). Connectivity, latency, and bandwidth limit cloud-IoT integration. Fog and Edge Computational (EC), which has no storage or computing resources in the cloud but is closer to the data source, emerged from the need for cloud-IoT communication. The hierarchical cross-layer edge-fog-cloud (E-F-C) design optimizes solutions and computes and analyzes big data and AI. To comprehend modern reference designs, building blocks, applications, and computing standards, this chapter discusses several paradigms and details the hierarchical edge-fog cloud. We also examine privacy-preserving, decentralized, and communal analytics in edge, fog, and cloud computing communication (CC). Finally, the data fabric, open issues, and future directions are described.
- 16 April 2024
- Published by Taylor & Francis
- p. 82-100
Convergence of Modern Technologies for Data Architectures
The rapid growth of the Internet of Things (IoT) and smart gadgets has affected every industry. Services must be reliable, high-performing, scalable, and ubiquitous for the IoT and related devices. SDN, Cloud IoT, Cloudlet, Mobile Computing (MC), Transparent Computing (TC), and Dew Computing are novel paradigms that achieve these attributes (DC). Connectivity, latency, and bandwidth limit cloud-IoT integration. Fog and Edge Computational (EC), which has no storage or computing resources in the cloud but is closer to the data source, emerged from the need for cloud-IoT communication. The hierarchical cross-layer edge-fog-cloud (E-F-C) design optimizes solutions and computes and analyzes big data and AI. To comprehend modern reference designs, building blocks, applications, and computing standards, this chapter discusses several paradigms and details the hierarchical edge-fog cloud. We also examine privacy-preserving, decentralized, and communal analytics in edge, fog, and cloud computing communication (CC). Finally, the data fabric, open issues, and future directions are described.
- Open Access
- 29 August 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-7
Skin Diseases Classification Using Hybrid AI Based Localization Approach
One of the most prevalent diseases that can be initially identified by visual inspection and further identified with the use of dermoscopic examination and other testing is skin cancer. Since eye observation provides the earliest opportunity for artificial intelligence to intercept various skin images, some skin lesion classification algorithms based on deep learning and annotated skin photos display improved outcomes. The researcher used a variety of strategies and methods to identify and stop diseases earlier. All of them yield positive results for identifying and categorizing diseases, but proper disease categorization is still lacking. Computer-aided diagnosis is one of the most crucial methods for more accurate disease detection, although it is rarely used in dermatology. For Feature Extraction, we introduced Spectral Centroid Magnitude (SCM). The given dataset is classified using an enhanced convolutional neural network; the first stage of preprocessing uses a median filter, and the final stage compares the accuracy results to the current method.
- 29 August 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-7
Open AccessSkin Diseases Classification Using Hybrid AI Based Localization Approach
One of the most prevalent diseases that can be initially identified by visual inspection and further identified with the use of dermoscopic examination and other testing is skin cancer. Since eye observation provides the earliest opportunity for artificial intelligence to intercept various skin images, some skin lesion classification algorithms based on deep learning and annotated skin photos display improved outcomes. The researcher used a variety of strategies and methods to identify and stop diseases earlier. All of them yield positive results for identifying and categorizing diseases, but proper disease categorization is still lacking. Computer-aided diagnosis is one of the most crucial methods for more accurate disease detection, although it is rarely used in dermatology. For Feature Extraction, we introduced Spectral Centroid Magnitude (SCM). The given dataset is classified using an enhanced convolutional neural network; the first stage of preprocessing uses a median filter, and the final stage compares the accuracy results to the current method.