Spectral analysis of brain function network for the classification of motor imagery tasks

Wanzeng Kong, Xinwei Guo, Xinxin Zhao, Daming Wei, Sanqing Hu, Guojun Dai, Giovanni Vecchiato, Fabio Babiloni

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

Abstract

In order to deal with the classification for multi-class motor imagery(MI) tasks, a novel approach was presented in this paper. It is different from classical methods which classified the MI task with time-frequency analysis on EEG signals. It employs the brain function network(BFN) as a new characteristic to describe MI tasks. The BFN enlarges the features with respect to traditional time-frequency methods. Unlike analysis of statistical parameters of network such as average clustering coefficient (C) and the average pathlength (L), the proposed method employed spectral decomposition performing on BFNs, and considered the eigenvalue vector of threshold matrix as features for classification by SVM. Hence, it is speedy enough to meet the requirement of real-time in BCI-based application systems. The result of experiment demonstrates that proposed method can achieve satisfied accuracy of classification on multi-class MI tasks.

Original languageEnglish
Title of host publicationProceedings - 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011
Pages850-853
Number of pages4
Volume2
DOIs
Publication statusPublished - 2011
Event2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011 - Shanghai, China
Duration: Oct 15 2011Oct 17 2011

Other

Other2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011
CountryChina
CityShanghai
Period10/15/1110/17/11

Fingerprint

Imagery (Psychotherapy)
Spectrum analysis
Brain
Electroencephalography
Cluster Analysis
Decomposition
Experiments

Keywords

  • BCI
  • brain function network
  • classification
  • motor imagery

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Kong, W., Guo, X., Zhao, X., Wei, D., Hu, S., Dai, G., ... Babiloni, F. (2011). Spectral analysis of brain function network for the classification of motor imagery tasks. In Proceedings - 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011 (Vol. 2, pp. 850-853). [6098491] https://doi.org/10.1109/BMEI.2011.6098491

Spectral analysis of brain function network for the classification of motor imagery tasks. / Kong, Wanzeng; Guo, Xinwei; Zhao, Xinxin; Wei, Daming; Hu, Sanqing; Dai, Guojun; Vecchiato, Giovanni; Babiloni, Fabio.

Proceedings - 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011. Vol. 2 2011. p. 850-853 6098491.

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

Kong, W, Guo, X, Zhao, X, Wei, D, Hu, S, Dai, G, Vecchiato, G & Babiloni, F 2011, Spectral analysis of brain function network for the classification of motor imagery tasks. in Proceedings - 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011. vol. 2, 6098491, pp. 850-853, 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011, Shanghai, China, 10/15/11. https://doi.org/10.1109/BMEI.2011.6098491
Kong W, Guo X, Zhao X, Wei D, Hu S, Dai G et al. Spectral analysis of brain function network for the classification of motor imagery tasks. In Proceedings - 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011. Vol. 2. 2011. p. 850-853. 6098491 https://doi.org/10.1109/BMEI.2011.6098491
Kong, Wanzeng ; Guo, Xinwei ; Zhao, Xinxin ; Wei, Daming ; Hu, Sanqing ; Dai, Guojun ; Vecchiato, Giovanni ; Babiloni, Fabio. / Spectral analysis of brain function network for the classification of motor imagery tasks. Proceedings - 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011. Vol. 2 2011. pp. 850-853
@inproceedings{b447341cf860465ab0bc54d2380eaea2,
title = "Spectral analysis of brain function network for the classification of motor imagery tasks",
abstract = "In order to deal with the classification for multi-class motor imagery(MI) tasks, a novel approach was presented in this paper. It is different from classical methods which classified the MI task with time-frequency analysis on EEG signals. It employs the brain function network(BFN) as a new characteristic to describe MI tasks. The BFN enlarges the features with respect to traditional time-frequency methods. Unlike analysis of statistical parameters of network such as average clustering coefficient (C) and the average pathlength (L), the proposed method employed spectral decomposition performing on BFNs, and considered the eigenvalue vector of threshold matrix as features for classification by SVM. Hence, it is speedy enough to meet the requirement of real-time in BCI-based application systems. The result of experiment demonstrates that proposed method can achieve satisfied accuracy of classification on multi-class MI tasks.",
keywords = "BCI, brain function network, classification, motor imagery",
author = "Wanzeng Kong and Xinwei Guo and Xinxin Zhao and Daming Wei and Sanqing Hu and Guojun Dai and Giovanni Vecchiato and Fabio Babiloni",
year = "2011",
doi = "10.1109/BMEI.2011.6098491",
language = "English",
isbn = "9781424493524",
volume = "2",
pages = "850--853",
booktitle = "Proceedings - 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011",

}

TY - GEN

T1 - Spectral analysis of brain function network for the classification of motor imagery tasks

AU - Kong, Wanzeng

AU - Guo, Xinwei

AU - Zhao, Xinxin

AU - Wei, Daming

AU - Hu, Sanqing

AU - Dai, Guojun

AU - Vecchiato, Giovanni

AU - Babiloni, Fabio

PY - 2011

Y1 - 2011

N2 - In order to deal with the classification for multi-class motor imagery(MI) tasks, a novel approach was presented in this paper. It is different from classical methods which classified the MI task with time-frequency analysis on EEG signals. It employs the brain function network(BFN) as a new characteristic to describe MI tasks. The BFN enlarges the features with respect to traditional time-frequency methods. Unlike analysis of statistical parameters of network such as average clustering coefficient (C) and the average pathlength (L), the proposed method employed spectral decomposition performing on BFNs, and considered the eigenvalue vector of threshold matrix as features for classification by SVM. Hence, it is speedy enough to meet the requirement of real-time in BCI-based application systems. The result of experiment demonstrates that proposed method can achieve satisfied accuracy of classification on multi-class MI tasks.

AB - In order to deal with the classification for multi-class motor imagery(MI) tasks, a novel approach was presented in this paper. It is different from classical methods which classified the MI task with time-frequency analysis on EEG signals. It employs the brain function network(BFN) as a new characteristic to describe MI tasks. The BFN enlarges the features with respect to traditional time-frequency methods. Unlike analysis of statistical parameters of network such as average clustering coefficient (C) and the average pathlength (L), the proposed method employed spectral decomposition performing on BFNs, and considered the eigenvalue vector of threshold matrix as features for classification by SVM. Hence, it is speedy enough to meet the requirement of real-time in BCI-based application systems. The result of experiment demonstrates that proposed method can achieve satisfied accuracy of classification on multi-class MI tasks.

KW - BCI

KW - brain function network

KW - classification

KW - motor imagery

UR - http://www.scopus.com/inward/record.url?scp=84862971136&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862971136&partnerID=8YFLogxK

U2 - 10.1109/BMEI.2011.6098491

DO - 10.1109/BMEI.2011.6098491

M3 - Conference contribution

SN - 9781424493524

VL - 2

SP - 850

EP - 853

BT - Proceedings - 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011

ER -