EEG-Based Brain Computer Interface for Emotion Recognition

Abstract

Emotion recognition using electroencephalography (EEG) signal could be a current focus in brain-computer interface research, that is convenient and a reliable technique. EEG-based emotion detection studies are employed in a very spread of fields, including defence, aerospace, and medicine, among others. The purpose of this study is to discover the relationship between EEG signals and human emotions. EEG signals are commonly used to categorise emotions into three groups: positive, negative, and neutral. We first extracted features from the EEG signals in order to classify emotions and used a deep learning classifier: recurrent neural network (RNN) and gated recurrent unit (GRU). Second, a Muse EEG headband with four electrodes (TP9, AF7, AF8, TP10) is used to record brain activity. Positive and negative emotional states are elicited with lucid valence film clips, and neutral resting data with no stimuli is also recorded for one minute per session. EEG data was collected for 3 minutes per state from two people (one male and one female) (positive, neutral, and negative) [5]. This study helps to spot human emotions supported by EEG signals within the brain-computer interface and helps to know the emotion of the mind.