Artifactual component classification from MEG data using support vector machine

Montri Phothisonothai, Fang Duan, Hiroyuki Tsubomi, Aki Kondo, Kazuyuki Aihara, Yuko Yoshimura, Mitsuru Kikuchi, Yoshio Minabe, Katsumi Watanabe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

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.

Original languageEnglish
Title of host publication5th 2012 Biomedical Engineering International Conference, BMEiCON 2012
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event5th 2012 Biomedical Engineering International Conference, BMEiCON 2012 - Muang, Ubon Ratchathani, Thailand
Duration: 2012 Dec 52012 Dec 7

Other

Other5th 2012 Biomedical Engineering International Conference, BMEiCON 2012
CountryThailand
CityMuang, Ubon Ratchathani
Period12/12/512/12/7

Fingerprint

Independent component analysis
Support vector machines
Fractal dimension
Electrocardiography
Entropy

Keywords

  • Artifacts
  • Independent component analysis
  • Magnetoencephalogram
  • MEG
  • Support vector machine

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Phothisonothai, M., Duan, F., Tsubomi, H., Kondo, A., Aihara, K., Yoshimura, Y., ... Watanabe, K. (2012). Artifactual component classification from MEG data using support vector machine. In 5th 2012 Biomedical Engineering International Conference, BMEiCON 2012 [6465462] https://doi.org/10.1109/BMEiCon.2012.6465462

Artifactual component classification from MEG data using support vector machine. / Phothisonothai, Montri; Duan, Fang; Tsubomi, Hiroyuki; Kondo, Aki; Aihara, Kazuyuki; Yoshimura, Yuko; Kikuchi, Mitsuru; Minabe, Yoshio; Watanabe, Katsumi.

5th 2012 Biomedical Engineering International Conference, BMEiCON 2012. 2012. 6465462.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Phothisonothai, M, Duan, F, Tsubomi, H, Kondo, A, Aihara, K, Yoshimura, Y, Kikuchi, M, Minabe, Y & Watanabe, K 2012, Artifactual component classification from MEG data using support vector machine. in 5th 2012 Biomedical Engineering International Conference, BMEiCON 2012., 6465462, 5th 2012 Biomedical Engineering International Conference, BMEiCON 2012, Muang, Ubon Ratchathani, Thailand, 12/12/5. https://doi.org/10.1109/BMEiCon.2012.6465462
Phothisonothai M, Duan F, Tsubomi H, Kondo A, Aihara K, Yoshimura Y et al. Artifactual component classification from MEG data using support vector machine. In 5th 2012 Biomedical Engineering International Conference, BMEiCON 2012. 2012. 6465462 https://doi.org/10.1109/BMEiCon.2012.6465462
Phothisonothai, Montri ; Duan, Fang ; Tsubomi, Hiroyuki ; Kondo, Aki ; Aihara, Kazuyuki ; Yoshimura, Yuko ; Kikuchi, Mitsuru ; Minabe, Yoshio ; Watanabe, Katsumi. / Artifactual component classification from MEG data using support vector machine. 5th 2012 Biomedical Engineering International Conference, BMEiCON 2012. 2012.
@inproceedings{05ffb7409ccb49678ebe3a7537cd6c9a,
title = "Artifactual component classification from MEG data using support vector machine",
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 = "Artifacts, Independent component analysis, Magnetoencephalogram, MEG, Support vector machine",
author = "Montri Phothisonothai and Fang Duan and Hiroyuki Tsubomi and Aki Kondo and Kazuyuki Aihara and Yuko Yoshimura and Mitsuru Kikuchi and Yoshio Minabe and Katsumi Watanabe",
year = "2012",
doi = "10.1109/BMEiCon.2012.6465462",
language = "English",
isbn = "9781467348928",
booktitle = "5th 2012 Biomedical Engineering International Conference, BMEiCON 2012",

}

TY - GEN

T1 - Artifactual component classification from MEG data using support vector machine

AU - Phothisonothai, Montri

AU - Duan, Fang

AU - Tsubomi, Hiroyuki

AU - Kondo, Aki

AU - Aihara, Kazuyuki

AU - Yoshimura, Yuko

AU - Kikuchi, Mitsuru

AU - Minabe, Yoshio

AU - Watanabe, Katsumi

PY - 2012

Y1 - 2012

N2 - 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.

AB - 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.

KW - Artifacts

KW - Independent component analysis

KW - Magnetoencephalogram

KW - MEG

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84875092421&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875092421&partnerID=8YFLogxK

U2 - 10.1109/BMEiCon.2012.6465462

DO - 10.1109/BMEiCon.2012.6465462

M3 - Conference contribution

SN - 9781467348928

BT - 5th 2012 Biomedical Engineering International Conference, BMEiCON 2012

ER -