Key result
Nonlinear dynamic techniques for feature extraction from physiological signals achieved >90% recognition accuracy for arousal and valence classes using a Quadratic Discriminant Classifier.
Why the study?
Does feature extraction using nonlinear dynamic techniques improve recognition accuracy of arousal and valence classes in volunteers compared to standard methods?
Population
35 volunteers
Comparison
Feature extraction using nonlinear dynamic… vs Feature extraction using standard methods
Authors
Loading...
Hypothesis-generating for nonlinear features in emotion detection; leaves open validation before clinical use.
Does feature extraction using nonlinear dynamic techniques improve recognition accuracy of arousal and valence classes in volunteers compared to standard methods?
Using nonlinear dynamic techniques for feature extraction from physiological signals significantly improves the accuracy of automatic emotion recognition (>90%).
Valenza et al. (2011) studied 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.
Synapse has enriched one closely related paper. Consider it for comparative context: