Unsupervised fuzzy c-means clustering for motor imagery EEG recognition

Wei Yen Hsu, Chi Yuan Lin, Wen Feng Kuo, Michelle Liou, Yung-Nien Sun, Arthur Chih Hsin Tsai, Hsien Jen Hsu, Po Hsun Chen, I. Ru Chen

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

In this study, an electroencephalogram (EEG) recognition system is proposed on single-trial motor imagery (MI) data. Fuzzy c-means (FCM) clustering is used for the unsupervised recognition of left and right MI data by combining with selected active segments and multiresolution fractal features. Active segment selection is used to detect active segments situated at most discriminable areas in the time-frequency domain. The multiresolution fractal features are then extracted by using modified fractal dimension from wavelet data. Finally, FCM clustering is used as the discriminant of MI features. The FCM clustering is an adaptive approach suitable for the clustering of non-stationary biomedical signals. Compared with several popular supervised classifiers, FCM clustering provides a potential for BCI application.

Original languageEnglish
Pages (from-to)4965-4976
Number of pages12
JournalInternational Journal of Innovative Computing, Information and Control
Volume7
Issue number8
Publication statusPublished - 2011 Aug 1

Fingerprint

Fuzzy C-means Clustering
Electroencephalography
Fractals
Multiresolution
Fractal
Fractal dimension
Classifiers
Discriminant
Fractal Dimension
Frequency Domain
Time Domain
Wavelets
Classifier
Clustering
Electroencephalogram
Imagery

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Computational Theory and Mathematics

Cite this

Hsu, W. Y., Lin, C. Y., Kuo, W. F., Liou, M., Sun, Y-N., Tsai, A. C. H., ... Chen, I. R. (2011). Unsupervised fuzzy c-means clustering for motor imagery EEG recognition. International Journal of Innovative Computing, Information and Control, 7(8), 4965-4976.
Hsu, Wei Yen ; Lin, Chi Yuan ; Kuo, Wen Feng ; Liou, Michelle ; Sun, Yung-Nien ; Tsai, Arthur Chih Hsin ; Hsu, Hsien Jen ; Chen, Po Hsun ; Chen, I. Ru. / Unsupervised fuzzy c-means clustering for motor imagery EEG recognition. In: International Journal of Innovative Computing, Information and Control. 2011 ; Vol. 7, No. 8. pp. 4965-4976.
@article{ff82c2aa619a4ccbb1d4c191c8e4eaf8,
title = "Unsupervised fuzzy c-means clustering for motor imagery EEG recognition",
abstract = "In this study, an electroencephalogram (EEG) recognition system is proposed on single-trial motor imagery (MI) data. Fuzzy c-means (FCM) clustering is used for the unsupervised recognition of left and right MI data by combining with selected active segments and multiresolution fractal features. Active segment selection is used to detect active segments situated at most discriminable areas in the time-frequency domain. The multiresolution fractal features are then extracted by using modified fractal dimension from wavelet data. Finally, FCM clustering is used as the discriminant of MI features. The FCM clustering is an adaptive approach suitable for the clustering of non-stationary biomedical signals. Compared with several popular supervised classifiers, FCM clustering provides a potential for BCI application.",
author = "Hsu, {Wei Yen} and Lin, {Chi Yuan} and Kuo, {Wen Feng} and Michelle Liou and Yung-Nien Sun and Tsai, {Arthur Chih Hsin} and Hsu, {Hsien Jen} and Chen, {Po Hsun} and Chen, {I. Ru}",
year = "2011",
month = "8",
day = "1",
language = "English",
volume = "7",
pages = "4965--4976",
journal = "International Journal of Innovative Computing, Information and Control",
issn = "1349-4198",
publisher = "IJICIC Editorial Office",
number = "8",

}

Hsu, WY, Lin, CY, Kuo, WF, Liou, M, Sun, Y-N, Tsai, ACH, Hsu, HJ, Chen, PH & Chen, IR 2011, 'Unsupervised fuzzy c-means clustering for motor imagery EEG recognition', International Journal of Innovative Computing, Information and Control, vol. 7, no. 8, pp. 4965-4976.

Unsupervised fuzzy c-means clustering for motor imagery EEG recognition. / Hsu, Wei Yen; Lin, Chi Yuan; Kuo, Wen Feng; Liou, Michelle; Sun, Yung-Nien; Tsai, Arthur Chih Hsin; Hsu, Hsien Jen; Chen, Po Hsun; Chen, I. Ru.

In: International Journal of Innovative Computing, Information and Control, Vol. 7, No. 8, 01.08.2011, p. 4965-4976.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Unsupervised fuzzy c-means clustering for motor imagery EEG recognition

AU - Hsu, Wei Yen

AU - Lin, Chi Yuan

AU - Kuo, Wen Feng

AU - Liou, Michelle

AU - Sun, Yung-Nien

AU - Tsai, Arthur Chih Hsin

AU - Hsu, Hsien Jen

AU - Chen, Po Hsun

AU - Chen, I. Ru

PY - 2011/8/1

Y1 - 2011/8/1

N2 - In this study, an electroencephalogram (EEG) recognition system is proposed on single-trial motor imagery (MI) data. Fuzzy c-means (FCM) clustering is used for the unsupervised recognition of left and right MI data by combining with selected active segments and multiresolution fractal features. Active segment selection is used to detect active segments situated at most discriminable areas in the time-frequency domain. The multiresolution fractal features are then extracted by using modified fractal dimension from wavelet data. Finally, FCM clustering is used as the discriminant of MI features. The FCM clustering is an adaptive approach suitable for the clustering of non-stationary biomedical signals. Compared with several popular supervised classifiers, FCM clustering provides a potential for BCI application.

AB - In this study, an electroencephalogram (EEG) recognition system is proposed on single-trial motor imagery (MI) data. Fuzzy c-means (FCM) clustering is used for the unsupervised recognition of left and right MI data by combining with selected active segments and multiresolution fractal features. Active segment selection is used to detect active segments situated at most discriminable areas in the time-frequency domain. The multiresolution fractal features are then extracted by using modified fractal dimension from wavelet data. Finally, FCM clustering is used as the discriminant of MI features. The FCM clustering is an adaptive approach suitable for the clustering of non-stationary biomedical signals. Compared with several popular supervised classifiers, FCM clustering provides a potential for BCI application.

UR - http://www.scopus.com/inward/record.url?scp=79961034318&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79961034318&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:79961034318

VL - 7

SP - 4965

EP - 4976

JO - International Journal of Innovative Computing, Information and Control

JF - International Journal of Innovative Computing, Information and Control

SN - 1349-4198

IS - 8

ER -