Emotion Recognition via Galvanic Skin Response: Comparison of Machine Learning Algorithms and Feature Extraction Methods

Abstract

Emotionsplay a significant and powerful role in everyday life of human beings.Developing algorithms for computers to recognize emotional expression is widelystudied area. In this study, emotion recognition from  Galvanic Skin Response signals was performedusing time domain, wavelet and empirical mode decomposition based features.Valence and arousal have been categorized and relationship between physiologicalsignals and arousal and valence has been studied using k-Nearest Neighbors,Decision Tree, Random Forest and Support Vector Machine algorithms. We haveachieved 81.81% and 89.29% accuracy rate for arousal and valence respectively.