Recognizing an emotional context created using human bio-signals has gained traction in contemporary applications. The current emotional ontology however cannot handle probabilistic information in the emotion recognition process. The primary goal of this research is to utilize a Bayesian Network into the study of EEG-based emotion recognition to address the probabilistic context data. The work is based our previous emotion ontology prototype 'Emotiono'; the EEG dataset for evaluating its performance being extracted from 'DEAP' which an open multimodal database for emotion analysis. With 10-fold data in validation the average classification rate using the posited method reaches 86.8 % for Arousal and 85.9 % for Valence in the two dimensional emotion recognition processes. © 2012 Springer Science+Business Media.
CITATION STYLE
Zhang, X., Cao, D., Moore, P., Chen, J., Zhou, L., Zhou, Y., & Ma, X. (2012). A Bayesian Network (BN) based probabilistic solution to enhance emotional ontology. In Lecture Notes in Electrical Engineering (Vol. 182 LNEE, pp. 181–190). https://doi.org/10.1007/978-94-007-5086-9_24
Mendeley helps you to discover research relevant for your work.