Time Domain Analysis for Emotional EEG Signals of Stroke Patient and Normal Subject

This paper aims to analyze the emotional Electroencephalogram (EEG) signals of different time windows. The time window of the signals is one of the variables that affect the efficiency of the EEG signal analysis. In this research, a total of 30 subjects are analyzed from three different groups namely 10 left brain damage (LBD), 10 right brain damage (RBD), and 10 normal control (NC) for six different emotional states. The 14-Channel Wireless Emotiv EPOC device with a sampling frequency of 128 Hz is used to extract EEG signal from the subjects. The 6th Order Butterworth Bandpass filter is used to extract the EEG signals with the frequency band of 8-49 Hz, which are alpha to gamma waves. The EEG signals are segmented in 2s, 4s, 6s, and 8s time windows for all frequency bands. In addition, the K-Nearest Neighbor (KNN) and Probabilistic Neural Network (PNN) classifiers are used to classify the six emotions in LBD, RBD and NC. The beta and gamma bands are the best performing EEG frequency band for emotion classification. In the investigation, 6s time windows have the highest classification accuracy for KNN with 81.90% and 8s time window for PNN classifier with 82.15%.