EEG-based human emotion recognition using k-NN machine learning

Abstract

Mental health issue is growing rapidly in these recent years. Teenagers and young adult aged of 16-30 years old are the most common victims. Mental health is a really serious issue concerning emotional health. One of the causes on emotional health issues is a lack of self-awareness, which is the key cornerstone on maintaining emotional state. In this study, EEG Neurostyle of 24 channels was used to obtain brain electrical signals. The mental emotions of the subjects were obtained from their reactions due to a set of audio-visual stimuli of approximately 5 minutes, the subject consists of 6 subjects aged 18-22 years old. The expressions of the subjects were recorded EEG signals separately to ensure their emotion according to the source (i.e. sad clips resulting sad emotion). The signals were processed using DFT and PSD to extract their features. The features were used to classify the emotions into 4 classes: happy, sad, scared, and disgust. In this study, the k-NN as classifier was used and obtained training and testing accuracy for all the features were greater than 52 % and 30 % for 4 classes.