Mood recognition system using EEG signal of song induced activities

Abstract

Music is referred to as language of emotions. Music induces emotion in the brain. These emotions are subject not only types of music, but also the sensitivity of the person subjected to music. Dissimilar cases of songs as relax, patriotism, happiness, romantic or sadness will induce different types of brain activities generating different EEG signals. EEG signal is applied to measure electrical activity of the brain. These EEG signal contain precious information of the different moods of subject. In this work, we proposed a mood recognition system using EEG signal of Song Induced activity. The main purpose is to analyze alpha rhythmof EEG signal related to the left hemisphere, and right hemisphere regions of the brain. We have selected 10 male subjects in the age group of 20–25. The electrodes placed on the scalp of the subject as per the International 10–20 standard. Each test was conducted for 25 min, with eye closed and each subject was asked to concentrate on the given tasks. In this study, we have created EEG dataset containing data offive mental tasks of ten different subjects. We determine the alpha rhythms in the left hemisphere are more predominant over the right hemisphere for emotions. Thuswe conclude that the left region of the brain gives more response to the emotions rather than the right region. Here we reduce the EEG database from brain region to left hemisphere. Further we reduce it to single electrode as F7 which reside in left region. The database generated in our study may be used to interface the brain with computer to mood recognition system. This will have wide varieties of applications in the future. For example, the entertainment industries may use it for composition of songs as per their effect on the brain. This study also shows that alpha power frequency carries useful information related to mood recognition. These features are separated using Linear Discriminate Analysis.