Bispectrum analysis of EEG for motor imagery classification

Author

Kotoky, Nayantara ; Hazarika, S.M.

fYear

2014

fDate

20-21 Feb. 2014

Firstpage

581

Lastpage

586

Abstract

Effective motor imagery (MI) classification based on electroencephalogram (EEG) signals for Brain Computer Interface (BCI) is an active area of research. Classification is largely dependent on the feature vector and the type of classifier. This paper reports a study on the use of bispectrum for classifying left and right hand MI based on surface EEG from electrode positions C3 and C4. EEG signals from publicly available dataset has been taken. Derived as well as statistical features of the bispectrum are explored. A Least Square Support Vector Machine (LS-SVM) classifier is used. Experimental results support the idea of using bispectrum for left and right hand MI classification.

Keywords

brain-computer interfaces; electroencephalography; image classification; least squares approximations; medical image processing; support vector machines; vectors; BCI; EEG; LS-SVM classifier; MI classification; bispectrum analysis; brain computer interface; electroencephalogram signals; feature vector; least square support vector machine; motor imagery classification; statistical features; Accuracy; Educational institutions; Electroencephalography; Feature extraction; Support vector machine classification; Training; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Integrated Networks (SPIN), 2014 International Conference on

Conference_Location

Noida

Print_ISBN

978-1-4799-2865-1

Type

conf

DOI

10.1109/SPIN.2014.6777021

Filename

6777021