Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{187090,
        author = {Kunal Ashok Zende and Shravani Borude and Devyani Borse and Srushti Chavan and Dr. V.S. Wadne},
        title = {Privacy-Preserving On-Screen Activity Tracking and Classification in E-Learning Using Federated Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {4071-4076},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187090},
        abstract = {E-learning, a modern approach to education that leverages digital technologies such as computers, mobile devices, and the internet, has witnessed a rapid increase in adoption in recent years. Despite its global reach and potential, it also introduces challenges related to time management and resource utilization. Students often use the same device for both educational and entertainment purposes, making it difficult to remain focused and avoid distractions from social media and other online platforms. As online education continues to expand, monitoring student activity on screens becomes a critical yet underexplored research area—particularly when considering user privacy. To address this issue, this study proposes a privacy-preserving architecture that detects whether students are productively engaged or waste time on their computers while ensuring data confidentiality through federated learning. A dataset of over 4,000 screenshots depicting various student activities was used to train multiple pre-trained models. The proposed FedInceptionV3 model achieved state-of-the-art test accuracy of 99.75%, demonstrating its effectiveness in maintaining both accuracy and privacy in e-learning activity detection.},
        keywords = {e-learning, federated learning, privacy preservation, deep learning, inceptionv3.},
        month = {November},
        }