Stress Detection Using Wearable Physiological and Sociometric Sensors

TL;DR

This study develops a machine learning-based system that combines physiological and sociometric sensors to accurately detect stress in social situations, with potential for real-time application.

Contribution

It introduces a novel approach integrating two sensor modalities and evaluates their combined effectiveness for automatic stress detection.

Findings

Combining sensors improves stress detection accuracy.

Support vector machine achieved high classification performance.

Identified key features most indicative of stress.

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 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.