• Mr.E.Ramesh Reddy
• A.V.Bharadwaj

In the realm of digital education, the utilization of e-learning platforms has become increasingly prevalent, offering flexible and accessible learning avenues. However, the gathering and analysis of user activity data on these platforms raise substantial privacy concerns. To mitigate these challenges, we present a novel approach that employs federated learning to track and classify on-screen activities while safeguarding user privacy. Our framework harnesses federated learning to train machine learning models across decentralized devices, ensuring that raw user data remains exclusively on users' devices and is never transmitted to a central server. On- screen activities, including mouse movements, keystrokes, and interactions with learning materials, are locally tracked and anonymized before contributing to the training of a global activity classification model

Privacy-preserving, On-screen activity tracking, Classification, E-learning Federated learning, User privacy

"Privacy-Preserving on screen activity tracking and classification in E-Learning using Federated Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.435-440, June-2024, Available :http://www.jetir.org/papers/JETIRGL06073.pdf

"Privacy-Preserving on screen activity tracking and classification in E-Learning using Federated Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. pp435-440, June-2024, Available at : http://www.jetir.org/papers/JETIRGL06073.pdf