Early Detection of Chronic Stress Using Wearable Devices: A Machine Learning Approach with the WESAD Database

Amaia Calvo, Julen Martin, Cristina Martin, Cristina Martin, Cristina Martin

2025

Abstract

Stress disorders have experienced a significant increase in recent years, impacting individual health. This study explores the feasibility of detecting this mental condition through the analysis of physiological signals captured by wearable devices using machine learning algorithms. An exhaustive review of relevant public databases was conducted and WESAD database was identified as the most suitable one. A detailed examination was conducted using two different configurations for building AI models: in one approach, a single model was created using data from all participants, while in the other, personalized models were developed for each individual participant. This approach evaluated the effectiveness of different preprocessing methods and AI algorithms, as well as identified the physiological signals most informative about stress. Convolutional Neural Networks (CNN) achieved the highest accuracy in stress detection, with an overall accuracy of 99.8% for the single model configuration and 99.6% for personalized models. The analysis also highlighted electrocardiogram (ECG) and electrodermal activity (EDA) as the most informative signals for predicting stress.

Paper Citation

in Harvard Style

Calvo A., Martin J. and Martin C. (2025). Early Detection of Chronic Stress Using Wearable Devices: A Machine Learning Approach with the WESAD Database. In Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health - Volume 1: ICT4AWE; ISBN 978-989-758-743-6, SciTePress, pages 189-196. DOI: 10.5220/0013209700003938

in Bibtex Style

@conference{ict4awe25,
author={Amaia Calvo and Julen Martin and Cristina Martin},
title={Early Detection of Chronic Stress Using Wearable Devices: A Machine Learning Approach with the WESAD Database},
booktitle={Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health - Volume 1: ICT4AWE},
year={2025},
pages={189-196},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013209700003938},
isbn={978-989-758-743-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health - Volume 1: ICT4AWE
TI - Early Detection of Chronic Stress Using Wearable Devices: A Machine Learning Approach with the WESAD Database
SN - 978-989-758-743-6
AU - Calvo A.
AU - Martin J.
AU - Martin C.
PY - 2025
SP - 189
EP - 196
DO - 10.5220/0013209700003938
PB - SciTePress