DETERMINATION OF EMOTIONAL STATUS FROM EEG TIME SERIES BY USING EMD BASED LOCAL BINARY PATTERN METHOD

Although determining emotional states from brain dynamics has been a subject that has been studied for a long time, the desired level has not been reached yet. In this study, Empirical mode decomposition (EMD) based Local Binary Pattern (LBP) method is proposed for emotional determination using (positive-neutral-negative) Electroencephalogram (EEG) signals. Thanks to this method, a hybrid structure was created in obtaining features from EEG signals. In the study, Seed EEG dataset containing 15 positive subjects and positive-neutral-negative emotional state is used. In the study, classification is utilized with the basis of individuals by using 27 EEG channels in the left hemisphere of each subject. Level 5 was separated by applying EMD to EEG segments containing three emotional states. Features were obtained from the Intrinsic mode function (IMF) using LBP method. These features are classified with k Nearest Neighbor (k-NN) and Artificial Neural Network (ANN). The average classification accuracy for 15 participants was 83.77% using the k-NN classifier and 84.50% with the ANN classifier. In addition, the highest classification performance was found to be 96.75% with the k-NN classifier. The results obtained in the study support similar studies in the literature.