No Cover Image

Journal article 567 views

Classifying mental tasks based on features of higher-order statistics from EEG signals in brain–computer interface

Shang-ming Zhou Orcid Logo, John Q. Gan, Francisco Sepulveda

Information Sciences, Volume: 178, Issue: 6, Pages: 1629 - 1640

Swansea University Author: Shang-ming Zhou Orcid Logo

Full text not available from this repository: check for access using links below.

Abstract

This paper proposes a new feature extraction method to characterize the non-Gaussian information contained within the EEG signals using bispectrum. Moreover, the proposed method is applied to the classification of right and left motor imagery for developing EEG-based brain–computer interface systems...

Full description

Published in: Information Sciences
ISSN: 00200255
Published: INFORMATION SCIENCES 2008
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa10025
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: This paper proposes a new feature extraction method to characterize the non-Gaussian information contained within the EEG signals using bispectrum. Moreover, the proposed method is applied to the classification of right and left motor imagery for developing EEG-based brain–computer interface systems. The experimental results on the Graz BCI data set have shown that based on the proposed features, a LDA classifier, SVM classifier and NN classifier outperform the winner of the brain-computer interface (BCI) 2003 competition on the same data set in terms of either the mutual information, the competition criterion, or misclassification rate.
Keywords: Brain–computer interfaces, Classification, Electroencephalogram (EEG), Feature extraction, Higher-order statistics, Bispectrum
College: Swansea University Medical School
Issue: 6
Start Page: 1629
End Page: 1640