The aim of this study is to enhance image classification using Federated Learning (FL) applied to the CIFAR100 dataset. We created a decentralized FL environment with multiple clients, leveraging the Flower framework and Ray for distributed computing. The methodology involved federated averaging for parameter updates, client-specific data handling, and performance evaluation using various metrics. Our results demonstrate a significant improvement in model performance, with loss decreasing from 0.060846 to 0.038253 and accuracy increasing from 41.64% to 57.96% over five training rounds. This study concludes that FL is effective in improving image classification while preserving data privacy and decentralization.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Enhancing Image Classification with Federated Learning through a Flower Simulation Study on the CIFAR100 Dataset


    Beteiligte:
    Akilandeswari, A. (Autor:in) / Ramamoorthy, M (Autor:in) / Akila, D. (Autor:in) / Hajira, A B. (Autor:in) / Radhika, S. (Autor:in) / Chandramohan, S. (Autor:in)


    Erscheinungsdatum :

    06.11.2024


    Format / Umfang :

    559654 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Enhancing Traffic Light Detection and Classification through Federated Learning

    Vondikakis, Ioannis V. / Panagiotopoulos, Ilias E. / Dimitrakopoulos, George J. | IEEE | 2024


    Collaborative Learning in Shared Production Environment Using Federated Image Classification

    Hegiste, Vinit / Legler, Tatjana / Ruskowski, Martin | Springer Verlag | 2025

    Freier Zugriff

    Flower image classification based on visual transformer

    Lu, Lang / Ying, Hong / Mou, Honglin et al. | British Library Conference Proceedings | 2022


    Enhancing WiFi Multiple Access Performance with Federated Deep Reinforcement Learning

    Zhang, Lyutianyang / Yin, Hao / Zhou, Zhanke et al. | IEEE | 2020