Stress Detection Using Wearable Physiological and Sociometric Sensors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mozos, Oscar Martinez, Sandulescu, Virginia, Andrews, Sally, Ellis, David, Bellotto, Nicola, Dobrescu, Radu, Ferrandez, Jose Manuel
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915936679755776
author Mozos, Oscar Martinez
Sandulescu, Virginia
Andrews, Sally
Ellis, David
Bellotto, Nicola
Dobrescu, Radu
Ferrandez, Jose Manuel
author_facet Mozos, Oscar Martinez
Sandulescu, Virginia
Andrews, Sally
Ellis, David
Bellotto, Nicola
Dobrescu, Radu
Ferrandez, Jose Manuel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12746
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Stress Detection Using Wearable Physiological and Sociometric Sensors
Mozos, Oscar Martinez
Sandulescu, Virginia
Andrews, Sally
Ellis, David
Bellotto, Nicola
Dobrescu, Radu
Ferrandez, Jose Manuel
Machine Learning
Signal Processing
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.
title Stress Detection Using Wearable Physiological and Sociometric Sensors
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2604.12746