Personalization of AI Models Based on Federated Learning for Driver Stress Monitoring
Abstract
To improve the comfort of car occupants or to develop control laws for autonomous vehicles or Advanced Driver-Assistance Systems, it is essential to monitor drivers’ internal state and automatically detect stressful situations. In this paper, we propose a driver’s stress monitoring system based on the analysis of physiological signals. To consider the individual differences between drivers, we propose a training strategy based on federated learning that favors examples in training set from drivers with the same profile as the driver we want to monitor. This approach allows us to personalize the prediction model for a target-driver and significantly improves performance compared to the classical paradigm that maximizes the average performance for all the users in a given dataset. This paper shows that this personalization strategy improves the performance of the stress estimation on the public database AffectiveROAD [ 1 ].
Cite
Text
Rafi et al. "Personalization of AI Models Based on Federated Learning for Driver Stress Monitoring." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25075-0_39Markdown
[Rafi et al. "Personalization of AI Models Based on Federated Learning for Driver Stress Monitoring." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/rafi2022eccvw-personalization/) doi:10.1007/978-3-031-25075-0_39BibTeX
@inproceedings{rafi2022eccvw-personalization,
title = {{Personalization of AI Models Based on Federated Learning for Driver Stress Monitoring}},
author = {Rafi, Houda and Benezeth, Yannick and Reynaud, Philippe and Arnoux, Emmanuel and Yang, Fan and Demonceaux, Cédric},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {575-585},
doi = {10.1007/978-3-031-25075-0_39},
url = {https://mlanthology.org/eccvw/2022/rafi2022eccvw-personalization/}
}