A novel approach for epileptic EEG signals classification based on biclustering technique

Qin LIN; Cui Hong WU; Wen Cheng GU; Jing Jing LIU; Yun XUE; Xi Zhao WANG; Xiao Hui HU

doi:10.1109/ICMLC.2016.7872982

A novel approach for epileptic EEG signals classification based on biclustering technique

Qin LIN, Cui Hong WU, Wen Cheng GU, Jing Jing LIU, Yun XUE^*, Xi Zhao WANG, Xiao Hui HU

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

2 Citations (Scopus)

Abstract

Epilepsy is increasingly occurred disease in the modern world, and the use of automatic detection technology of epileptic Electroencephalogram (EEG) signals is more and more important. In this essay, a novel approach named CC-ELM of automatic epileptic EEG signals detection is proposed. Unlike traditional dimension reducing methods of most current automatic detection, the proposed approach adopts biclustering to perform an unsupervised dimension reduction, which is more suitable to the characteristic of EEG signals. To verify the performance of the presented approach, experiments have been carried out in the epileptic EEG data. The average sensitivity, specificity and recognition accuracy obtained by our method are 96.67%, 100.00% and 98.00%. The study might be meaningful for improving the diagnostic accuracy of epileptic disease, relieving the workload of doctors and reducing the medical cost.

Original language	English
Title of host publication	Proceedings of 2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016
Publisher	IEEE
Pages	756-760
Number of pages	5
ISBN (Electronic)	9781509003891
DOIs	https://doi.org/10.1109/ICMLC.2016.7872982
Publication status	Published - 2 Jul 2016
Externally published	Yes
Event	2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016 - Jeju Island, Korea, Republic of Duration: 10 Jul 2016 → 13 Jul 2016

Publication series

Name	Proceedings - International Conference on Machine Learning and Cybernetics
Volume	2
ISSN (Print)	2160-133X
ISSN (Electronic)	2160-1348

Conference

Conference	2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016
Country/Territory	Korea, Republic of
City	Jeju Island
Period	10/07/16 → 13/07/16

Bibliographical note

This study was supported by the Science and Technology Project of Guangdong Province (No.2013B010401023ˈ2016A010101020, 2016A010101022, 016A010101021), the Research Funds of Guangdong Medical University (No.M2015031, M2015029), the Science and Technology Project of Zhanjiang City (No.2016B01118), Undergraduate Innovative Experiment Project of Guangdong Medical University (No.2014ZZDI002).

Keywords

Biclustering
Electroencephalogram (EEG)
Epilepsy
Extreme learning machine (ELM)
Seizures

Access to Document

10.1109/ICMLC.2016.7872982

Cite this

LIN, Q., WU, C. H., GU, W. C., LIU, J. J., XUE, Y., WANG, X. Z., & HU, X. H. (2016). A novel approach for epileptic EEG signals classification based on biclustering technique. In Proceedings of 2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016 (pp. 756-760). Article 7872982 (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 2). IEEE. https://doi.org/10.1109/ICMLC.2016.7872982

@inproceedings{e8480a4014d941818ce606d4b0cd0550,

title = "A novel approach for epileptic EEG signals classification based on biclustering technique",

abstract = "Epilepsy is increasingly occurred disease in the modern world, and the use of automatic detection technology of epileptic Electroencephalogram (EEG) signals is more and more important. In this essay, a novel approach named CC-ELM of automatic epileptic EEG signals detection is proposed. Unlike traditional dimension reducing methods of most current automatic detection, the proposed approach adopts biclustering to perform an unsupervised dimension reduction, which is more suitable to the characteristic of EEG signals. To verify the performance of the presented approach, experiments have been carried out in the epileptic EEG data. The average sensitivity, specificity and recognition accuracy obtained by our method are 96.67%, 100.00% and 98.00%. The study might be meaningful for improving the diagnostic accuracy of epileptic disease, relieving the workload of doctors and reducing the medical cost.",

keywords = "Biclustering, Electroencephalogram (EEG), Epilepsy, Extreme learning machine (ELM), Seizures",

author = "Qin LIN and WU, {Cui Hong} and GU, {Wen Cheng} and LIU, {Jing Jing} and Yun XUE and WANG, {Xi Zhao} and HU, {Xiao Hui}",

note = "This study was supported by the Science and Technology Project of Guangdong Province (No.2013B010401023ˈ2016A010101020, 2016A010101022, 016A010101021), the Research Funds of Guangdong Medical University (No.M2015031, M2015029), the Science and Technology Project of Zhanjiang City (No.2016B01118), Undergraduate Innovative Experiment Project of Guangdong Medical University (No.2014ZZDI002).; 2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016 ; Conference date: 10-07-2016 Through 13-07-2016",

year = "2016",

month = jul,

day = "2",

doi = "10.1109/ICMLC.2016.7872982",

language = "English",

series = "Proceedings - International Conference on Machine Learning and Cybernetics",

publisher = "IEEE",

pages = "756--760",

booktitle = "Proceedings of 2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016",

}

LIN, Q, WU, CH, GU, WC, LIU, JJ, XUE, Y, WANG, XZ & HU, XH 2016, A novel approach for epileptic EEG signals classification based on biclustering technique. in Proceedings of 2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016., 7872982, Proceedings - International Conference on Machine Learning and Cybernetics, vol. 2, IEEE, pp. 756-760, 2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016, Jeju Island, Korea, Republic of, 10/07/16. https://doi.org/10.1109/ICMLC.2016.7872982

A novel approach for epileptic EEG signals classification based on biclustering technique. / LIN, Qin; WU, Cui Hong; GU, Wen Cheng et al.
Proceedings of 2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016. IEEE, 2016. p. 756-760 7872982 (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 2).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - A novel approach for epileptic EEG signals classification based on biclustering technique

AU - LIN, Qin

AU - WU, Cui Hong

AU - GU, Wen Cheng

AU - LIU, Jing Jing

AU - XUE, Yun

AU - WANG, Xi Zhao

AU - HU, Xiao Hui

N1 - This study was supported by the Science and Technology Project of Guangdong Province (No.2013B010401023ˈ2016A010101020, 2016A010101022, 016A010101021), the Research Funds of Guangdong Medical University (No.M2015031, M2015029), the Science and Technology Project of Zhanjiang City (No.2016B01118), Undergraduate Innovative Experiment Project of Guangdong Medical University (No.2014ZZDI002).

PY - 2016/7/2

Y1 - 2016/7/2

N2 - Epilepsy is increasingly occurred disease in the modern world, and the use of automatic detection technology of epileptic Electroencephalogram (EEG) signals is more and more important. In this essay, a novel approach named CC-ELM of automatic epileptic EEG signals detection is proposed. Unlike traditional dimension reducing methods of most current automatic detection, the proposed approach adopts biclustering to perform an unsupervised dimension reduction, which is more suitable to the characteristic of EEG signals. To verify the performance of the presented approach, experiments have been carried out in the epileptic EEG data. The average sensitivity, specificity and recognition accuracy obtained by our method are 96.67%, 100.00% and 98.00%. The study might be meaningful for improving the diagnostic accuracy of epileptic disease, relieving the workload of doctors and reducing the medical cost.

AB - Epilepsy is increasingly occurred disease in the modern world, and the use of automatic detection technology of epileptic Electroencephalogram (EEG) signals is more and more important. In this essay, a novel approach named CC-ELM of automatic epileptic EEG signals detection is proposed. Unlike traditional dimension reducing methods of most current automatic detection, the proposed approach adopts biclustering to perform an unsupervised dimension reduction, which is more suitable to the characteristic of EEG signals. To verify the performance of the presented approach, experiments have been carried out in the epileptic EEG data. The average sensitivity, specificity and recognition accuracy obtained by our method are 96.67%, 100.00% and 98.00%. The study might be meaningful for improving the diagnostic accuracy of epileptic disease, relieving the workload of doctors and reducing the medical cost.

KW - Biclustering

KW - Electroencephalogram (EEG)

KW - Epilepsy

KW - Extreme learning machine (ELM)

KW - Seizures

UR - http://www.scopus.com/inward/record.url?scp=85021209895&partnerID=8YFLogxK

U2 - 10.1109/ICMLC.2016.7872982

DO - 10.1109/ICMLC.2016.7872982

M3 - Conference paper (refereed)

AN - SCOPUS:85021209895

T3 - Proceedings - International Conference on Machine Learning and Cybernetics

SP - 756

EP - 760

BT - Proceedings of 2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016

PB - IEEE

T2 - 2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016

Y2 - 10 July 2016 through 13 July 2016

ER -

LIN Q, WU CH, GU WC, LIU JJ, XUE Y, WANG XZ et al. A novel approach for epileptic EEG signals classification based on biclustering technique. In Proceedings of 2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016. IEEE. 2016. p. 756-760. 7872982. (Proceedings - International Conference on Machine Learning and Cybernetics). doi: 10.1109/ICMLC.2016.7872982

A novel approach for epileptic EEG signals classification based on biclustering technique

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this