Artifactual component classification from MEG data using support vector machine

Author

Phothisonothai, Montri ; Fang Duan ; Tsubomi, H. ; Kondo, Atsushi ; Aihara, Kazuyuki ; Yoshimura, Yuki ; Kikuchi, Masashi ; Minabe, Yoshio ; Watanabe, K.

Author_Institution

Dept. of Electr. Eng. & Inf. Syst., Univ. of Tokyo, Tokyo, Japan

fYear

2012

fDate

5-7 Dec. 2012

Firstpage

1

Lastpage

5

Abstract

Recently, an independent component analysis (ICA) has been proven to be an effective method for removing artifacts and noise in multi-channel physiological measures. ICA can extract independent component (IC) which was directly regarded as artifacts. In this paper, we propose an automatic method for classifying physiological artifacts from magnetoencephalogram (MEG) data. The artifactual ICs were classified based on support vector machine (SVM) algorithm. The following parameters: kurtosis (K), probability density (PD), central moment of frequency (CMoF), spectral entropy (SpecEn), and fractal dimension (FD) were used as input vector of SVM. The proposed method showed the average classification rates of 99.18%, 92.33%, and 98.15% for cardiac (EKG), ocular (EOG), and high-amplitude changes (HAM), respectively.

Keywords

entropy; feature extraction; fractals; independent component analysis; magnetoencephalography; medical signal processing; signal classification; signal denoising; support vector machines; MEG data; SVM algorithm; SVM input vectors; artifact removal; artifactual ICs; artifactual component classification; average classification rates; central moment of frequency; fractal dimension; independent component analysis; independent component extraction; kurtosis; magnetoencephalogram; multichannel physiological measures; noise removal; physiological artifact classification; probability density; spectral entropy; support vector machine; Educational institutions; Electrocardiography; Electrooculography; Independent component analysis; Integrated circuits; Noise; Support vector machines; MEG; Magnetoencephalogram; artifacts; independent component analysis; support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering International Conference (BMEiCON), 2012

Conference_Location

Ubon Ratchathani

Print_ISBN

978-1-4673-4890-4

Type

conf

DOI

10.1109/BMEiCon.2012.6465462

Filename

6465462