Automatic Stress Classification With Pupil Diameter Analysis

is an open access repository that collects the work of Arts et Métiers ParisTech researchers and makes it freely available over the web where possible. This article proposes a method based on wavelet transform and neural networks for relating pupillary behavior to psychological stress. The proposed method was tested by recording pupil diameter and electrodermal activity during a simulated driving task. Self-report measures were also collected. Participants performed a baseline run with the driving task only, followed by three stress runs where they were required to perform the driving task along with sound alerts, the presence of two human evaluators, and both. Self-reports and pupil diameter successfully indexed stress manipulation, and significant correlations were found between these measures. However, electrodermal activity did not vary accordingly. After training, the four-way parallel neu-ral network classifier could guess whether a given unknown pupil diameter signal came from one of the four experimental trials with 79.2% precision. The present study shows that pupil diameter signal has good discriminating power for stress detection. 1. INTRODUCTION Stress detection and measurement are important issues in several human–computer interaction domains such as Affective Computing, Adaptive Automation, and Ambient Intelligence. In general, researchers and system designers seek to estimate the psychological state of operators in order to adapt or redesign the working environment accordingly (Sauter, 1991). The primary goal of such adaptation is to enhance overall system performance, trying to reduce workers' psychophysi-cal detriment (e. One key aspect of stress measurement concerns the recording of physiological parameters, which are known to be modulated by the autonomic nervous system (ANS). However, despite