Screen Activity Monitoring Using Federated Learning

Madhavi Dorge; Anchal Kesare; Pranita Navale; Kalpana Thorat; Arpit Gupta

doi:10.1109/apsit63993.2025.11086241

May 23, 2025

Screen Activity Monitoring Using Federated Learning

View at Publisher

Ask AI

Bookmark

Share

Key Points

Develop and evaluate a privacy-preserving machine learning architecture using federated learning to detect and classify student computer usage during online study.
Trained and evaluated multiple pre-trained computer vision architectures within a decentralized federated learning framework.
Analyzed an experimental dataset of over 3,500 screenshots depicting diverse student interactions across distinct activity categories.
The FedInceptionV3 model achieved an overall image classification accuracy of 98.25% in categorizing student computer usage.
The decentralized architecture successfully distinguished academic tasks from entertainment distractions while protecting user data privacy.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Machine learning study demonstrates high-accuracy screen activity classification in online students, indicating effective privacy-preserving digital monitoring.

Abstract

No abstract yet. The journal hasn't published one we can show.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Dorge et al. (2025) studied this question.

synapsesocial.com/papers/6a193c57ac919e0a4888cda4 https://doi.org/10.1109/apsit63993.2025.11086241

View at Publisher

Ask AI

Bookmark

Share

Screen Activity Monitoring Using Federated Learning

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Screen Activity Monitoring Using Federated Learning

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading