A high-wearable EEG-based system using a 12-band Filter Bank and Common Spatial Pattern algorithm achieved an intra-individual average accuracy of 96.2% and an inter-individual accuracy of 80.3% in detecting emotional valence.
Does an automated feature extraction pipeline using a 12-band Filter Bank and Common Spatial Pattern algorithm improve emotional valence detection accuracy in healthy volunteers using a highly wearable 8-channel EEG system?
A highly wearable 8-channel EEG system using automated feature extraction achieved up to 96.2% intra-individual accuracy in detecting emotional valence.
Abstract An emotional-valence detection method for a very–high wearable EEG-based system is proposed. Valence detection occurs along the interval scale theorized by the circumplex model of emotions. The binary choice, positive valence vs negative valence, represents a first step towards the adoption of a metric scale with a finer resolution. Wearability is guaranteed by a wireless cap with conductive-rubber dry electrodes and 8 data acquisition channels. Experimental validation was realized on 25 volunteers without depressive disorders. The metrological reference was built by combining the rating of a standardized set of pictures from dataset Oasis and results from the Self Assessment Manikin questionnaire. Two different strategies for feature extraction were compared: (i) based on a-priory knowledge (i.e. Hemispheric Asymmetry Theories) and (ii) automated. A pipeline of a custom 12-band Filter Bank and Common Spatial Pattern algorithm is the method proposed for automated feature extraction. Four machine learning classifiers were tested for validating the proposed method in discriminating two classes (high or low emotional valence). An intra-individual average accuracy, 96.2 %, was obtained by a shallow artificial neural network, while K-Nearest Neighbors allowed obtaining 80.3 % of inter-individual accuracy. Considering the wearability, and the well-founded metrological reference, results are the state of the art in emotional valence detection.
Apicella et al. (Sun,) conducted a other in Healthy volunteers (n=25). 12-band Filter Bank and Common Spatial Pattern (CSP) algorithm vs. Traditional EEG bands and a-priori spatial knowledge was evaluated on Accuracy of emotional valence detection (positive vs negative). A high-wearable EEG-based system using a 12-band Filter Bank and Common Spatial Pattern algorithm achieved an intra-individual average accuracy of 96.2% and an inter-individual accuracy of 80.3% in detecting emotional valence.