Balancing Between Privacy and Utility for Affect Recognition Using Multitask Learning in Differential Privacy-Added Federated Learning Settings: Quantitative Study.

Journal: JMIR mental health
PMID:

Abstract

BACKGROUND: The rise of wearable sensors marks a significant development in the era of affective computing. Their popularity is continuously increasing, and they have the potential to improve our understanding of human stress. A fundamental aspect within this domain is the ability to recognize perceived stress through these unobtrusive devices.

Authors

  • Mohamed Benouis
    Faculty of Applied Computer Science, Augsburg University, Augsburg, Germany.
  • Elisabeth André
    Faculty of Applied Computer Science, Institute of Computer Science, Universität Augsburg, Augsburg, Germany.
  • Yekta Said Can
    Faculty of Applied Computer Science, Institute of Computer Science, Universität Augsburg, Augsburg, Germany.