Brain Computer Interface for Emotion Recognition Based on EEG Signal

This paper presents an emotion recognition system based on electroencephalography (EEG) signals. helps medical practitioners to analyse the mental health of individual. Eight healthy volunteers/ subjects had participated in this experiment. A specific feeling is evoked using particular songs and videos that are collected present before subjects. Total 6 emotions namely neutral, happy, sad, disgust, fear motivate captured analysed. Data classified eighteen statistical features. The sampling rate 1200Hz. Signals filtered pre-processing techniques. Frequency, time timefrequency domain features extracted. An array 10 classifiers used including Decision Tree, Random Forest, Optimised Logistic regression, Support Vector Machine (SVM) Polynomial, SVM Sigmoid, RBF, K-Nearest Neighbours, Gaussian NB, Gradient Boosting Classifier. Accuracy, recall, precision, F1 score employed as performance metrics. accuracy obtained for classifier was 79.34%.