Abstract
Early mental stress detection can prevent many stress related health problems. This study aimed at using a wearable sensor system to measure physiological signals and detect mental stress. Three different stress conditions were presented to a healthy subject group. During the procedure, ECG, respiration, skin conductance, and EMG of the trapezius muscles were recorded. In total, 19 physiological features were calculated from these signals. After normalization of the feature values and analysis of correlations among these features, a subset of 9 features was selected for further analysis. Principal component analysis reduced these 9 features to 7 principal components (PCs). Using these PCs and different classifiers, a consistent classification accuracy between stress and non stress conditions of almost 80% was found. This suggests that a promising feature subset was found for future development of a personalized stress monitor.
I. INTRODUCTION
The second most frequently occurring type of workrelated health problems in the European population is ‘stress, depression or anxiety’ [1]. Of the sickness absence for one month or more, 25% was caused by stress, depression or anxiety. These figures indicate that stress is a major financial and social problem in European society. Chronic mental stress can cause health problems which include for example hypertension [2], cardiovascular diseases [3], increased likelihood of infections [2] and depression [4]. If mental stress could be detected in an early stage, stress relatedhealth problems couldbe prevented.
V. CONCLUSIONS
A subset of 9 physiological features was found that can be used for mental stress detection. The features were extracted from ECG, respiration, SC, and EMG signals. PCA indicated that the feature subset could be expressed as 7 PCs. These PCs were used for classification of cases into rest or stress conditions. A classification accuracy of almost 80% was found. This promising result indicates that this feature subset can be used for stress detection in the future. The high classification accuracy also indicates that the features are suitable for individual stress detection.
