Wavelet-based envelope features with automatic EOG artifact removal: Application to single-trial EEG data

Wei Yen Hsu, Chao Hung Lin, Hsien Jen Hsu, Po Hsun Chen, I. Ru Chen

研究成果: Article

40 引文 (Scopus)

摘要

In this study, we propose an analysis system for single-trial classification of electroencephalogram (EEG) data. Combined with automatic EOG artifact removal and wavelet-based amplitude modulation (AM) features, the support vector machine (SVM) classifier is applied to the classification of left finger lifting and resting. Automatic EOG artifact removal is proposed to eliminate the EOG artifacts automatically by means of independent component analysis (ICA) and correlation coefficient. The features are then extracted from the discrete wavelet transform (DWT) data by the AM method. Finally, the SVM is used for the discriminant of wavelet-based AM features. Compared with EEG data without EOG artifact removal, band power features and LDA classifier, the proposed system achieves promising results in classification accuracy.

原文English
頁(從 - 到)2743-2749
頁數7
期刊Expert Systems With Applications
39
發行號3
DOIs
出版狀態Published - 2012 二月 15

指紋

Amplitude modulation
Electroencephalography
Support vector machines
Classifiers
Discrete wavelet transforms
Independent component analysis

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

引用此文

Hsu, Wei Yen ; Lin, Chao Hung ; Hsu, Hsien Jen ; Chen, Po Hsun ; Chen, I. Ru. / Wavelet-based envelope features with automatic EOG artifact removal : Application to single-trial EEG data. 於: Expert Systems With Applications. 2012 ; 卷 39, 編號 3. 頁 2743-2749.
@article{330a56df83454bf589bbfe29186c25a1,
title = "Wavelet-based envelope features with automatic EOG artifact removal: Application to single-trial EEG data",
abstract = "In this study, we propose an analysis system for single-trial classification of electroencephalogram (EEG) data. Combined with automatic EOG artifact removal and wavelet-based amplitude modulation (AM) features, the support vector machine (SVM) classifier is applied to the classification of left finger lifting and resting. Automatic EOG artifact removal is proposed to eliminate the EOG artifacts automatically by means of independent component analysis (ICA) and correlation coefficient. The features are then extracted from the discrete wavelet transform (DWT) data by the AM method. Finally, the SVM is used for the discriminant of wavelet-based AM features. Compared with EEG data without EOG artifact removal, band power features and LDA classifier, the proposed system achieves promising results in classification accuracy.",
author = "Hsu, {Wei Yen} and Lin, {Chao Hung} and Hsu, {Hsien Jen} and Chen, {Po Hsun} and Chen, {I. Ru}",
year = "2012",
month = "2",
day = "15",
doi = "10.1016/j.eswa.2011.08.132",
language = "English",
volume = "39",
pages = "2743--2749",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "3",

}

Wavelet-based envelope features with automatic EOG artifact removal : Application to single-trial EEG data. / Hsu, Wei Yen; Lin, Chao Hung; Hsu, Hsien Jen; Chen, Po Hsun; Chen, I. Ru.

於: Expert Systems With Applications, 卷 39, 編號 3, 15.02.2012, p. 2743-2749.

研究成果: Article

TY - JOUR

T1 - Wavelet-based envelope features with automatic EOG artifact removal

T2 - Application to single-trial EEG data

AU - Hsu, Wei Yen

AU - Lin, Chao Hung

AU - Hsu, Hsien Jen

AU - Chen, Po Hsun

AU - Chen, I. Ru

PY - 2012/2/15

Y1 - 2012/2/15

N2 - In this study, we propose an analysis system for single-trial classification of electroencephalogram (EEG) data. Combined with automatic EOG artifact removal and wavelet-based amplitude modulation (AM) features, the support vector machine (SVM) classifier is applied to the classification of left finger lifting and resting. Automatic EOG artifact removal is proposed to eliminate the EOG artifacts automatically by means of independent component analysis (ICA) and correlation coefficient. The features are then extracted from the discrete wavelet transform (DWT) data by the AM method. Finally, the SVM is used for the discriminant of wavelet-based AM features. Compared with EEG data without EOG artifact removal, band power features and LDA classifier, the proposed system achieves promising results in classification accuracy.

AB - In this study, we propose an analysis system for single-trial classification of electroencephalogram (EEG) data. Combined with automatic EOG artifact removal and wavelet-based amplitude modulation (AM) features, the support vector machine (SVM) classifier is applied to the classification of left finger lifting and resting. Automatic EOG artifact removal is proposed to eliminate the EOG artifacts automatically by means of independent component analysis (ICA) and correlation coefficient. The features are then extracted from the discrete wavelet transform (DWT) data by the AM method. Finally, the SVM is used for the discriminant of wavelet-based AM features. Compared with EEG data without EOG artifact removal, band power features and LDA classifier, the proposed system achieves promising results in classification accuracy.

UR - http://www.scopus.com/inward/record.url?scp=80255137439&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80255137439&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2011.08.132

DO - 10.1016/j.eswa.2011.08.132

M3 - Article

AN - SCOPUS:80255137439

VL - 39

SP - 2743

EP - 2749

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 3

ER -