Classification of human emotions from EEG signals using statistical features and neural network

Chai , Tong Yuen and Woo , San San and Rizon, Mohamed and Tan , Ching Seong (2010) Classification of human emotions from EEG signals using statistical features and neural network. International , 1 (3). pp. 1-6. ISSN 1985-854X

[img]
Preview
PDF - Published Version
158Kb

Official URL: http://penerbit.uthm.edu.my/ejournal/

Abstract

A statistical based system for human emotions classification by using electroencephalogram (EEG) is proposed in this paper. The data used in this study is acquired using EEG and the emotions are elicited from six human subjects under the effect of emotion stimuli. This paper also proposed an emotion stimulation experiment using visual stimuli. From the EEG data, a total of six statistical features are computed and back-propagation neural network is applied for the classification of human emotions. In the experiment of classifying five types of emotions: Anger, Sad, Surprise, Happy, and Neutral. As result the overall classification rate as high as 95% is achieved.

Item Type:Article
Uncontrolled Keywords:EEG; human emotions; neural network; statistical features
Subjects:Q Science > QP Physiology
ID Code:511
Deposited By:Nurhafiza Hamzah
Deposited On:12 Dec 2011 14:56
Last Modified:12 Dec 2011 14:56

Repository Staff Only: item control page