Stress detection using wearable physiological and sociometric sensors

Martinez Mozos, Oscar and Sandulescu, Virginia and Andrews, Sally and Ellis, David and Bellotto, Nicola and Dobrescu, Radu and Manuel Ferrandez, Jose (2017) Stress detection using wearable physiological and sociometric sensors. International Journal of Neural Systems, 27 (2). p. 1650041. ISSN 0129-0657

Documents
23128mozos2015ijns.pdf

Request a copy
[img] PDF
23128mozos2015ijns.pdf - Whole Document
Restricted to Repository staff only until 25 December 2018.

743kB
Item Type:Article
Item Status:Live Archive

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.

Keywords:activity monitoring, assistive technologies, physiology, sensors, signal classi?cation, sociometric badges, stress, stress detection, wearable technology
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
C Biological Sciences > C800 Psychology
Divisions:College of Science > School of Computer Science
ID Code:23128
Deposited On:13 May 2016 08:59

Repository Staff Only: item control page