PROJECT TITLE :

Recognizing Emotions Induced by Affective Sounds through Heart Rate Variability

ABSTRACT:

This paper reports on how emotional states elicited by affective sounds will be effectively recognized by means that of estimates of Autonomic Nervous System (ANS) dynamics. Specifically, emotional states are modeled as a mix of arousal and valence dimensions according to the well-known circumplex model of affect, whereas the ANS dynamics is estimated through commonplace and nonlinear analysis of Heart rate variability (HRV) exclusively, that springs from the electrocardiogram (ECG). In addition, Lagged Poincaré Plots of the HRV series were additionally taken into account. The affective sounds were gathered from the International Affective Digitized Sound System and grouped into four totally different levels of arousal (intensity) and two levels of valence (unpleasant and pleasant). A cluster of 27 healthy volunteers were administered with these standardized stimuli whereas ECG signals were continuously recorded. Then, those HRV options showing important changes (p $<$ 0.05 from statistical tests) between the arousal and valence dimensions were used as input of an automatic classification system for the recognition of the four categories of arousal and two classes of valence. Experimental results demonstrated that a quadratic discriminant classifier, tested through Leave-One-Subject-Out procedure, was in a position to realize a recognition accuracy of 84.72 percent on the valence dimension, and 84.twenty six percent on the arousal dimension.