Stress detection using wearable physiological and sociometric sensors

Mozos, OM, Sandulescu, V, Andrews, S ORCID: https://orcid.org/0000-0002-9916-9433, Ellis, D, Bellotto, N, Dobrescu, R and Ferrandez, JM, 2017. Stress detection using wearable physiological and sociometric sensors. International Journal of Neural Systems, 27 (2), 1650041-1-1650041-16. ISSN 0129-0657

Preview

Text 5466_Andrews.pdf - Post-print Download (759kB) | Preview

Abstract

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 neighbour. 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.

Item Type:	Journal article
Publication Title:	International Journal of Neural Systems
Creators:	Mozos, O.M., Sandulescu, V., Andrews, S., Ellis, D., Bellotto, N., Dobrescu, R. and Ferrandez, J.M.
Publisher:	World Scientific
Date:	2017
Volume:	27
Number:	2
ISSN:	0129-0657
Identifiers:	Number Type 10.1142/S0129065716500416 DOI
Divisions:	Schools > School of Social Sciences
Record created by:	Jonathan Gallacher
Date Added:	02 Jun 2016 08:20
Last Modified:	19 Oct 2017 09:49
URI:	https://irep.ntu.ac.uk/id/eprint/27918

Actions (login required)

Edit View

Statistics

Views

Downloads