Continuous emotion recognition during music listening using EEG signals: A fuzzy parallel cascades model

A controversial issue in artificial intelligence is human emotion recognition. This paper presents a fuzzy parallel cascades (FPC) model for predicting the continuous subjective emotional appraisal of music by time-varying spectral content electroencephalogram (EEG) signals. The EEG, along with an 15 subjects, was recorded during listening to seven musical excerpts. appraisement valence and arousal axes as signal. FPC composed each cascade containing logic-based system. performance evaluated using linear regression (LR), support vector (SVR), Long–Short-Term-Memory recurrent neural network (LSTM-RNN) models 4 fold cross-validation. root mean square error (RMSE) lower than other estimation both all lowest obtained RMSE 0.082, which acquired model. analysis mutual information frontal EEG confirms role channels theta frequency band Considering dynamic variations features songs, employing modeling approach predict can be plausible substitute classification excerpts into predefined labels.