Arousal Detection Using EEG Signal

Abstract

Emotion has an important role in interaction and communication between people. Emotion can be expressed either verbally through emotional vocabulary, or by expressing non-verbal cues such as intonation of voice, facial expressions and gestures. In recent years, estimation of human emotions from Electroencephalogram (EEG) signals plays a vital role in developing intellectual Brain Computer Interface (BCI) devices. In this work, we have analyzed the EEG signals of the 4 different participants from the dataset. The Data set is provided on the enterface06 site, But this data is raw EEG data. The work describes how to extract data in text form from this raw form. EEGLAB. This extracted data is then decomposed in subands with the help of the wavelet transform in MATLAB. Features useful for emotion classification are then extracted. An ANN based classification system for human emotion by using Electroencephalogram (EEG) is used. Total three statistical features are computed and feed-forward back-propagation neural network is applied for the classification of human emotion. In the experiment we classify emotion in two classes, high arousal (HA) and low arousal (LA).