Classification of motor imagery tasks using phase synchronization analysis of EEG based on multivariate empirical mode decomposition

Shuang Liang; Kup Sze Choi; Jing Qin; Wai Man Pang; Pheng Ann Heng

doi:10.1109/ICIST.2014.6920567

Classification of motor imagery tasks using phase synchronization analysis of EEG based on multivariate empirical mode decomposition

Shuang Liang, Kup Sze Choi, Jing Qin, Wai Man Pang, Pheng Ann Heng

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

3 Citations (Scopus)

Abstract

Phase synchronization has been employed to study brain networks and connectivity patterns. The phase locking value (PLV) is one of the most effective measures widely used for phase synchronization analysis. We first calculate the PLVs of the pair-wise intrinsic mode functions (IMFs) based on multivariate empirical mode decomposition (MEMD) method. Next, the average PLV of the prominent pairs relative to the rest duration is adopted for the classification of motor imagery (MI) tasks. Comparative analysis with the EMD-based PLV method, the proposed method has a significant increase in feature separability for most subjects. This paper demonstrates that MEMD-based PLV method can provide an effective feature in the MI task classification and the potential for BCI applications.

Original language	English
Title of host publication	ICIST 2014 - Proceedings of 2014 4th IEEE International Conference on Information Science and Technology
Publisher	IEEE
Pages	674-677
Number of pages	4
ISBN (Electronic)	9781479948086
DOIs	https://doi.org/10.1109/ICIST.2014.6920567
Publication status	Published - 1 Jan 2014
Event	2014 4th IEEE International Conference on Information Science and Technology, ICIST 2014 - Shenzhen, China Duration: 26 Apr 2014 → 28 Apr 2014

Conference

Conference	2014 4th IEEE International Conference on Information Science and Technology, ICIST 2014
Country/Territory	China
City	Shenzhen
Period	26/04/14 → 28/04/14

Keywords

brain connectivity
Electroencephalogram (EEG)
motor imagery (MI)
multivariate empirical mode decomposition (MEMD)
phase synchronization

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems

More information

10.1109/ICIST.2014.6920567

Cite this

Liang, S., Choi, K. S., Qin, J., Pang, W. M., & Heng, P. A. (2014). Classification of motor imagery tasks using phase synchronization analysis of EEG based on multivariate empirical mode decomposition. In ICIST 2014 - Proceedings of 2014 4th IEEE International Conference on Information Science and Technology (pp. 674-677). Article 6920567 IEEE. https://doi.org/10.1109/ICIST.2014.6920567

@inproceedings{e8dfc22627be40eba95de500c969ae5f,

title = "Classification of motor imagery tasks using phase synchronization analysis of EEG based on multivariate empirical mode decomposition",

abstract = "Phase synchronization has been employed to study brain networks and connectivity patterns. The phase locking value (PLV) is one of the most effective measures widely used for phase synchronization analysis. We first calculate the PLVs of the pair-wise intrinsic mode functions (IMFs) based on multivariate empirical mode decomposition (MEMD) method. Next, the average PLV of the prominent pairs relative to the rest duration is adopted for the classification of motor imagery (MI) tasks. Comparative analysis with the EMD-based PLV method, the proposed method has a significant increase in feature separability for most subjects. This paper demonstrates that MEMD-based PLV method can provide an effective feature in the MI task classification and the potential for BCI applications.",

keywords = "brain connectivity, Electroencephalogram (EEG), motor imagery (MI), multivariate empirical mode decomposition (MEMD), phase synchronization",

author = "Shuang Liang and Choi, {Kup Sze} and Jing Qin and Pang, {Wai Man} and Heng, {Pheng Ann}",

year = "2014",

month = jan,

day = "1",

doi = "10.1109/ICIST.2014.6920567",

language = "English",

pages = "674--677",

booktitle = "ICIST 2014 - Proceedings of 2014 4th IEEE International Conference on Information Science and Technology",

publisher = "IEEE",

address = "United States",

note = "2014 4th IEEE International Conference on Information Science and Technology, ICIST 2014 ; Conference date: 26-04-2014 Through 28-04-2014",

}

Liang, S, Choi, KS, Qin, J, Pang, WM & Heng, PA 2014, Classification of motor imagery tasks using phase synchronization analysis of EEG based on multivariate empirical mode decomposition. in ICIST 2014 - Proceedings of 2014 4th IEEE International Conference on Information Science and Technology., 6920567, IEEE, pp. 674-677, 2014 4th IEEE International Conference on Information Science and Technology, ICIST 2014, Shenzhen, China, 26/04/14. https://doi.org/10.1109/ICIST.2014.6920567

Classification of motor imagery tasks using phase synchronization analysis of EEG based on multivariate empirical mode decomposition. / Liang, Shuang; Choi, Kup Sze; Qin, Jing et al.
ICIST 2014 - Proceedings of 2014 4th IEEE International Conference on Information Science and Technology. IEEE, 2014. p. 674-677 6920567.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Classification of motor imagery tasks using phase synchronization analysis of EEG based on multivariate empirical mode decomposition

AU - Liang, Shuang

AU - Choi, Kup Sze

AU - Qin, Jing

AU - Pang, Wai Man

AU - Heng, Pheng Ann

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Phase synchronization has been employed to study brain networks and connectivity patterns. The phase locking value (PLV) is one of the most effective measures widely used for phase synchronization analysis. We first calculate the PLVs of the pair-wise intrinsic mode functions (IMFs) based on multivariate empirical mode decomposition (MEMD) method. Next, the average PLV of the prominent pairs relative to the rest duration is adopted for the classification of motor imagery (MI) tasks. Comparative analysis with the EMD-based PLV method, the proposed method has a significant increase in feature separability for most subjects. This paper demonstrates that MEMD-based PLV method can provide an effective feature in the MI task classification and the potential for BCI applications.

AB - Phase synchronization has been employed to study brain networks and connectivity patterns. The phase locking value (PLV) is one of the most effective measures widely used for phase synchronization analysis. We first calculate the PLVs of the pair-wise intrinsic mode functions (IMFs) based on multivariate empirical mode decomposition (MEMD) method. Next, the average PLV of the prominent pairs relative to the rest duration is adopted for the classification of motor imagery (MI) tasks. Comparative analysis with the EMD-based PLV method, the proposed method has a significant increase in feature separability for most subjects. This paper demonstrates that MEMD-based PLV method can provide an effective feature in the MI task classification and the potential for BCI applications.

KW - brain connectivity

KW - Electroencephalogram (EEG)

KW - motor imagery (MI)

KW - multivariate empirical mode decomposition (MEMD)

KW - phase synchronization

UR - http://www.scopus.com/inward/record.url?scp=84910668644&partnerID=8YFLogxK

U2 - 10.1109/ICIST.2014.6920567

DO - 10.1109/ICIST.2014.6920567

M3 - Conference article published in proceeding or book

SP - 674

EP - 677

BT - ICIST 2014 - Proceedings of 2014 4th IEEE International Conference on Information Science and Technology

PB - IEEE

T2 - 2014 4th IEEE International Conference on Information Science and Technology, ICIST 2014

Y2 - 26 April 2014 through 28 April 2014

ER -

Classification of motor imagery tasks using phase synchronization analysis of EEG based on multivariate empirical mode decomposition

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this