Research on emotion recognition based on physiological signal and AuBT

摘要

Emotions play a significant role in human perception and decision making. Recent studies on emotion recognition are the subject of attention by researchers from different fields. By focusing in the four emotional states: happiness, anger, sadness and a neutral state which can be always found in daily life, this dissertation studies the Physiological signal based on emotion recognition technique. This paper uses a biological signal toolbox Augsburg (AuBT) analysis of physiological signals for emotion recognition. Augsburg Biosignal Toolbox (AuBT) is a toolbox for analyzing physiological signals written in Matlab. The result of experiment show that application of Augsburg biological signal toolbox gets the overall recognition rate of 87.5%, indicating that the Augsburg Biosignal Toolbox emotion recognition is feasible.