Nonlinear dynamic techniques for feature extraction from physiological signals achieved >90% recognition accuracy for arousal and valence classes using a Quadratic Discriminant Classifier.
This paper reports on a new methodology for the automatic assessment of emotional responses. More specifically, emotions are elicited in agreement with a bidimensional spatial localization of affective states, that is, arousal and valence dimensions. A dedicated experimental protocol was designed and realized where specific affective states are suitably induced while three peripheral physiological signals, i.e., ElectroCardioGram (ECG), ElectroDermal Response (EDR), and ReSPiration activity (RSP), are simultaneously acquired. A group of 35 volunteers was presented with sets of images gathered from the International Affective Picture System (IAPS) having five levels of arousal and five levels of valence, including a neutral reference level in both. Standard methods as well as nonlinear dynamic techniques were used to extract sets of features from the collected signals. The goal of this paper is to implement an automatic multiclass arousal/valence classifier comparing performance when extracted features from nonlinear methods are used as an alternative to standard features. Results show that, when nonlinearly extracted features are used, the percentages of successful recognition dramatically increase. A good recognition accuracy (>;90 percent) after 40-fold cross-validation steps for both arousal and valence classes was achieved by using the Quadratic Discriminant Classifier (QDC).
Valenza et al. (Mon,) conducted a other in Affective valence and arousal recognition (n=35). Nonlinear dynamic techniques for feature extraction vs. Standard feature extraction methods was evaluated on Recognition accuracy for arousal and valence classes. Nonlinear dynamic techniques for feature extraction from physiological signals achieved >90% recognition accuracy for arousal and valence classes using a Quadratic Discriminant Classifier.