Model based generalization analysis of common spatial pattern in brain computer interfaces

Gan Huang; Guangquan Liu; Jianjun Meng; Dingguo Zhang; Xiangyang Zhu

doi:10.1007/s11571-010-9117-x

Model based generalization analysis of common spatial pattern in brain computer interfaces

Gan Huang, Guangquan Liu, Jianjun Meng, Dingguo Zhang, Xiangyang Zhu

Research output: Contribution to journal › Article › peer-review

29 Scopus citations

Abstract

In the motor imagery based Brain Computer Interface (BCI) research, Common Spatial Pattern (CSP) algorithm is used widely as a spatial filter on multi-channel electroencephalogram (EEG) recordings. Recently the overfitting effect of CSP has been gradually noticed, but what influence the overfitting is still unclear. In this work, the generalization of CSP is investigated by a simple linear mixing model. Several factors in this model are discussed, and the simulation results indicate that channel numbers and the correlation between signals influence the generalization of CSP significantly. A larger number of training trials and a longer time length of the trial would prevent overfitting. The experiments on real data also verify our conclusion.

Original language	English (US)
Pages (from-to)	217-223
Number of pages	7
Journal	Cognitive Neurodynamics
Volume	4
Issue number	3
DOIs	https://doi.org/10.1007/s11571-010-9117-x
State	Published - Sep 2010
Externally published	Yes

Bibliographical note

Funding Information:
Acknowledgments This work is supported by National High Technology Research and Development Program of China (No. 2009AA04Z212), Research Fund for the Doctoral Program of Higher Education of China (No. 20090073120047), and SJTU Interdisciplinary Fund in Medicine & Engineering (No. YG2009MS45).

Keywords

Brain Computer Interfaces
Common Spatial Pattern
Generalization

Access

10.1007/s11571-010-9117-x

OpenUrl availability

Full text

Cite this

@article{4e7fb7ff94684076b56d5658c489e160,

title = "Model based generalization analysis of common spatial pattern in brain computer interfaces",

abstract = "In the motor imagery based Brain Computer Interface (BCI) research, Common Spatial Pattern (CSP) algorithm is used widely as a spatial filter on multi-channel electroencephalogram (EEG) recordings. Recently the overfitting effect of CSP has been gradually noticed, but what influence the overfitting is still unclear. In this work, the generalization of CSP is investigated by a simple linear mixing model. Several factors in this model are discussed, and the simulation results indicate that channel numbers and the correlation between signals influence the generalization of CSP significantly. A larger number of training trials and a longer time length of the trial would prevent overfitting. The experiments on real data also verify our conclusion.",

keywords = "Brain Computer Interfaces, Common Spatial Pattern, Generalization",

author = "Gan Huang and Guangquan Liu and Jianjun Meng and Dingguo Zhang and Xiangyang Zhu",

note = "Funding Information: Acknowledgments This work is supported by National High Technology Research and Development Program of China (No. 2009AA04Z212), Research Fund for the Doctoral Program of Higher Education of China (No. 20090073120047), and SJTU Interdisciplinary Fund in Medicine & Engineering (No. YG2009MS45).",

year = "2010",

month = sep,

doi = "10.1007/s11571-010-9117-x",

language = "English (US)",

volume = "4",

pages = "217--223",

journal = "Cognitive Neurodynamics",

issn = "1871-4080",

publisher = "Springer Netherlands",

number = "3",

}

TY - JOUR

T1 - Model based generalization analysis of common spatial pattern in brain computer interfaces

AU - Huang, Gan

AU - Liu, Guangquan

AU - Meng, Jianjun

AU - Zhang, Dingguo

AU - Zhu, Xiangyang

N1 - Funding Information: Acknowledgments This work is supported by National High Technology Research and Development Program of China (No. 2009AA04Z212), Research Fund for the Doctoral Program of Higher Education of China (No. 20090073120047), and SJTU Interdisciplinary Fund in Medicine & Engineering (No. YG2009MS45).

PY - 2010/9

Y1 - 2010/9

N2 - In the motor imagery based Brain Computer Interface (BCI) research, Common Spatial Pattern (CSP) algorithm is used widely as a spatial filter on multi-channel electroencephalogram (EEG) recordings. Recently the overfitting effect of CSP has been gradually noticed, but what influence the overfitting is still unclear. In this work, the generalization of CSP is investigated by a simple linear mixing model. Several factors in this model are discussed, and the simulation results indicate that channel numbers and the correlation between signals influence the generalization of CSP significantly. A larger number of training trials and a longer time length of the trial would prevent overfitting. The experiments on real data also verify our conclusion.

AB - In the motor imagery based Brain Computer Interface (BCI) research, Common Spatial Pattern (CSP) algorithm is used widely as a spatial filter on multi-channel electroencephalogram (EEG) recordings. Recently the overfitting effect of CSP has been gradually noticed, but what influence the overfitting is still unclear. In this work, the generalization of CSP is investigated by a simple linear mixing model. Several factors in this model are discussed, and the simulation results indicate that channel numbers and the correlation between signals influence the generalization of CSP significantly. A larger number of training trials and a longer time length of the trial would prevent overfitting. The experiments on real data also verify our conclusion.

KW - Brain Computer Interfaces

KW - Common Spatial Pattern

KW - Generalization

UR - http://www.scopus.com/inward/record.url?scp=77956064130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956064130&partnerID=8YFLogxK

U2 - 10.1007/s11571-010-9117-x

DO - 10.1007/s11571-010-9117-x

M3 - Article

C2 - 21886674

AN - SCOPUS:77956064130

SN - 1871-4080

VL - 4

SP - 217

EP - 223

JO - Cognitive Neurodynamics

JF - Cognitive Neurodynamics

IS - 3

ER -

Model based generalization analysis of common spatial pattern in brain computer interfaces

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this