Boosting specificity of MEG artifact removal by weighted support vector machine

Fang Duan, Montri Phothisonothai, Mitsuru Kikuchi, Yuko Yoshimura, Yoshio Minabe, Katsumi Watanabe, Kazuyuki Aihara

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

3 Citations (Scopus)

Abstract

An automatic artifact removal method of magnetoencephalogram (MEG) was presented in this paper. The method proposed is based on independent components analysis (ICA) and support vector machine (SVM). However, different from the previous studies, in this paper we consider two factors which would influence the performance. First, the imbalance factor of independent components (ICs) of MEG is handled by weighted SVM. Second, instead of simply setting a fixed weight to each class, a re-weighting scheme is used for the preservation of useful MEG ICs. Experimental results on manually marked MEG dataset showed that the method proposed could correctly distinguish the artifacts from the MEG ICs. Meanwhile, 99.72%±0.67 of MEG ICs were preserved. The classification accuracy was 97.91%±1.39. In addition, it was found that this method was not sensitive to individual differences. The cross validation (leave-one-subject-out) results showed an averaged accuracy of 97.41%±2.14.

Original languageEnglish
Title of host publicationProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Pages6039-6042
Number of pages4
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013 - Osaka, Japan
Duration: 2013 Jul 32013 Jul 7

Other

Other2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
CountryJapan
CityOsaka
Period13/7/313/7/7

Fingerprint

Artifacts
Support vector machines
Independent component analysis
Individuality
Weights and Measures
Support Vector Machine

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Duan, F., Phothisonothai, M., Kikuchi, M., Yoshimura, Y., Minabe, Y., Watanabe, K., & Aihara, K. (2013). Boosting specificity of MEG artifact removal by weighted support vector machine. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS (pp. 6039-6042). [6610929] https://doi.org/10.1109/EMBC.2013.6610929

Boosting specificity of MEG artifact removal by weighted support vector machine. / Duan, Fang; Phothisonothai, Montri; Kikuchi, Mitsuru; Yoshimura, Yuko; Minabe, Yoshio; Watanabe, Katsumi; Aihara, Kazuyuki.

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. p. 6039-6042 6610929.

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

Duan, F, Phothisonothai, M, Kikuchi, M, Yoshimura, Y, Minabe, Y, Watanabe, K & Aihara, K 2013, Boosting specificity of MEG artifact removal by weighted support vector machine. in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS., 6610929, pp. 6039-6042, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013, Osaka, Japan, 13/7/3. https://doi.org/10.1109/EMBC.2013.6610929
Duan F, Phothisonothai M, Kikuchi M, Yoshimura Y, Minabe Y, Watanabe K et al. Boosting specificity of MEG artifact removal by weighted support vector machine. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. p. 6039-6042. 6610929 https://doi.org/10.1109/EMBC.2013.6610929
Duan, Fang ; Phothisonothai, Montri ; Kikuchi, Mitsuru ; Yoshimura, Yuko ; Minabe, Yoshio ; Watanabe, Katsumi ; Aihara, Kazuyuki. / Boosting specificity of MEG artifact removal by weighted support vector machine. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. pp. 6039-6042
@inproceedings{46c4cda80dc64bf4be5642a55cdbdbdd,
title = "Boosting specificity of MEG artifact removal by weighted support vector machine",
abstract = "An automatic artifact removal method of magnetoencephalogram (MEG) was presented in this paper. The method proposed is based on independent components analysis (ICA) and support vector machine (SVM). However, different from the previous studies, in this paper we consider two factors which would influence the performance. First, the imbalance factor of independent components (ICs) of MEG is handled by weighted SVM. Second, instead of simply setting a fixed weight to each class, a re-weighting scheme is used for the preservation of useful MEG ICs. Experimental results on manually marked MEG dataset showed that the method proposed could correctly distinguish the artifacts from the MEG ICs. Meanwhile, 99.72{\%}±0.67 of MEG ICs were preserved. The classification accuracy was 97.91{\%}±1.39. In addition, it was found that this method was not sensitive to individual differences. The cross validation (leave-one-subject-out) results showed an averaged accuracy of 97.41{\%}±2.14.",
author = "Fang Duan and Montri Phothisonothai and Mitsuru Kikuchi and Yuko Yoshimura and Yoshio Minabe and Katsumi Watanabe and Kazuyuki Aihara",
year = "2013",
doi = "10.1109/EMBC.2013.6610929",
language = "English",
isbn = "9781457702167",
pages = "6039--6042",
booktitle = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

}

TY - GEN

T1 - Boosting specificity of MEG artifact removal by weighted support vector machine

AU - Duan, Fang

AU - Phothisonothai, Montri

AU - Kikuchi, Mitsuru

AU - Yoshimura, Yuko

AU - Minabe, Yoshio

AU - Watanabe, Katsumi

AU - Aihara, Kazuyuki

PY - 2013

Y1 - 2013

N2 - An automatic artifact removal method of magnetoencephalogram (MEG) was presented in this paper. The method proposed is based on independent components analysis (ICA) and support vector machine (SVM). However, different from the previous studies, in this paper we consider two factors which would influence the performance. First, the imbalance factor of independent components (ICs) of MEG is handled by weighted SVM. Second, instead of simply setting a fixed weight to each class, a re-weighting scheme is used for the preservation of useful MEG ICs. Experimental results on manually marked MEG dataset showed that the method proposed could correctly distinguish the artifacts from the MEG ICs. Meanwhile, 99.72%±0.67 of MEG ICs were preserved. The classification accuracy was 97.91%±1.39. In addition, it was found that this method was not sensitive to individual differences. The cross validation (leave-one-subject-out) results showed an averaged accuracy of 97.41%±2.14.

AB - An automatic artifact removal method of magnetoencephalogram (MEG) was presented in this paper. The method proposed is based on independent components analysis (ICA) and support vector machine (SVM). However, different from the previous studies, in this paper we consider two factors which would influence the performance. First, the imbalance factor of independent components (ICs) of MEG is handled by weighted SVM. Second, instead of simply setting a fixed weight to each class, a re-weighting scheme is used for the preservation of useful MEG ICs. Experimental results on manually marked MEG dataset showed that the method proposed could correctly distinguish the artifacts from the MEG ICs. Meanwhile, 99.72%±0.67 of MEG ICs were preserved. The classification accuracy was 97.91%±1.39. In addition, it was found that this method was not sensitive to individual differences. The cross validation (leave-one-subject-out) results showed an averaged accuracy of 97.41%±2.14.

UR - http://www.scopus.com/inward/record.url?scp=84886579210&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886579210&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2013.6610929

DO - 10.1109/EMBC.2013.6610929

M3 - Conference contribution

SN - 9781457702167

SP - 6039

EP - 6042

BT - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

ER -