Comparison of Machine Learning Approaches to Emotion Recognition Based on DEAP Database Physiological Signals

Abstract

Recognizing and accurately classifying human emotion is a complex and challenging task. Recently, great attention has been paid to the emotion recognition methods using three different approaches: based on non-physiological signals (like speech and facial expression), based on physiological signals, or based on hybrid approaches. Nonphysiological signals are easily controlled by the individual, so these approaches have downsides in real world applications. In this paper, an approach based on physiological signals which cannot be willingly influenced (electroencephalogram, heartrate, respiration, galvanic skin response, electromyography, body temperature) is presented. A publicly available DEAP database was used for the binary classification (high vs low for various threshold values) considering four frequently used emotional parameters (arousal, valence, liking and dominance). We have extracted 1490 features from the dataset, analyzed their predictive value for each emotion parameter and compared three different classification approaches – Support Vector Machine, Boosting algorithms and Artificial Neural Networks.