Stress detection in computer users based on digital signal processing of noninvasive physiological variables.

A stress detection system is developed based on the physiological signals monitored by non-invasive and non-intrusive sensors. The development of this emotion recognition system involved three stages: experiment setup for physiological sensing, signal preprocessing for the extraction of affective features and affective recognition using a learning system. Four signals: galvanic skin response (GSR), blood volume pulse (BVP), pupil diameter (PD) and skin temperature (ST) are monitored and analyzed to differentiate affective states in a computer user. A support vector machine is used to perform the supervised classification of affective states between "stress" and "relaxed". Results indicate that the physiological signals monitored do, in fact, have a strong correlation with the changes in emotional state of our experimental subjects when stress stimuli are applied to the interaction environment. It was also found that the pupil diameter was the most significant affective state indicator, compared to the other three physiological signals monitored.