Balancing Between Privacy and Utility for Affect Recognition Using Multitask Learning in Differential Privacy–Added Federated Learning Settings: Quantitative Study
JMIR Mental Health · 2024
DOI: 10.2196/60003 ↗At a glance
Journal article in JMIR Mental Health, 2024. Written by Mohamed Benouis and 2 co-authors. Institution: Faculty of Applied Computer Science, Augsburg University, Augsburg, Germany. Major MEDLINE topics: Privacy, Machine Learning. Cited 15 times so far (Crossref); 40 references. The full text is freely available in PubMed Central.
Abstract (original language)
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.
Objective
This study aims to enhance the performance of emotion recognition using multitask learning (MTL), a technique extensively explored across various machine learning tasks, including affective computing. By leveraging the shared information among related tasks, we seek to augment the accuracy of emotion recognition while confronting the privacy threats inherent in the physiological data captured by these sensors.
Methods
To address the privacy concerns associated with the sensitive data collected by wearable sensors, we proposed a novel framework that integrates differential privacy and federated learning approaches with MTL. This framework was designed to efficiently identify mental stress while preserving private identity information. Through this approach, we aimed to enhance the performance of emotion recognition tasks while preserving user privacy.
Results
Comprehensive evaluations of our framework were conducted using 2 prominent public datasets. The results demonstrate a significant improvement in emotion recognition accuracy, achieving a rate of 90%. Furthermore, our approach effectively mitigates privacy risks, as evidenced by limiting reidentification accuracies to 47%.
Conclusions
This study presents a promising approach to advancing emotion recognition capabilities while addressing privacy concerns in the context of empathetic sensors. By integrating MTL with differential privacy and federated learning, we have demonstrated the potential to achieve high levels of accuracy in emotion recognition while ensuring the protection of user privacy. This research contributes to the ongoing efforts to use affective computing in a privacy-aware and ethical manner.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Faculty of Applied Computer Science, Augsburg University, Augsburg, Germany.
ORCID profiles: Mohamed Benouis, Elisabeth Andre, Yekta Said Can
Cite
APA
Benouis, M., Andre, E., & Can, Y. S. (2024). Balancing Between Privacy and Utility for Affect Recognition Using Multitask Learning in Differential Privacy–Added Federated Learning Settings: Quantitative Study. JMIR Mental Health. https://doi.org/10.2196/60003
Vancouver
Benouis M, Andre E, Can YS. Balancing Between Privacy and Utility for Affect Recognition Using Multitask Learning in Differential Privacy–Added Federated Learning Settings: Quantitative Study. JMIR Mental Health. 2024. doi:10.2196/60003
BibTeX
@article{Benouis2024,
author = {Benouis, Mohamed and Andre, Elisabeth and Can, Yekta Said},
title = {Balancing Between Privacy and Utility for Affect Recognition Using Multitask Learning in Differential Privacy–Added Federated Learning Settings: Quantitative Study},
journal = {JMIR Mental Health},
year = {2024},
doi = {10.2196/60003}
}
EUVIMED