Stress remains a significant social problem for individuals in modern societies. This paper presents a machine learning approach for the automatic detection of stress of people in a social situation by combining two sensor systems that capture physiological and social responses. We compare the performance using different classifiers including support vector machine, AdaBoost, and k-nearest neighbor. Our experimental results show that by combining the measurements from both sensor systems, we could accurately discriminate between stressful and neutral situations during a controlled Trier social stress test (TSST). Moreover, this paper assesses the discriminative ability of each sensor modality individually and considers their suitability for real-time stress detection. Finally, we present an study of the most discriminative features for stress detection.
@article{arxiv.2604.12746,
title = {Stress Detection Using Wearable Physiological and Sociometric Sensors},
author = {Oscar Martinez Mozos and Virginia Sandulescu and Sally Andrews and David Ellis and Nicola Bellotto and Radu Dobrescu and Jose Manuel Ferrandez},
journal= {arXiv preprint arXiv:2604.12746},
year = {2026}
}
Comments
This is the accepted manuscript of the article published in International Journal of Neural Systems, 27, 2, 2017. The Version of Record is available at DOI: 10.1142/S0129065716500416