Common spatial patterns based on generalized norms

Jangwoo Park; Wonzoo Chung

doi:10.1109/IWW-BCI.2013.6506623

Common spatial patterns based on generalized norms

Jangwoo Park, Wonzoo Chung

Department of Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

The Common Spatial Patterns (CSP) algorithm is commonly used to finds spatial filters for classification of electroencephalogram (EEG) signals. However, conventional CSP is sensitive to outliers and artifacts because it is based on variance using L2-norm. In this paper, we consider generalized L _p norm based CSP, called CSP-L_p, and verify whichp is optimal for CSP-L_p by maximizing the Lp norm ratio of filtered dispersion of one class to the other class. The spatial filters of CSP-L _p are obtained empirically. Simulation result on a toy example shows the robustness of CSP-L_p depending on L_p-norm.

Original language	English
Title of host publication	2013 International Winter Workshop on Brain-Computer Interface, BCI 2013
Pages	39-42
Number of pages	4
DOIs	https://doi.org/10.1109/IWW-BCI.2013.6506623
Publication status	Published - 2013
Event	2013 International Winter Workshop on Brain-Computer Interface, BCI 2013 - Gangwon Province, Korea, Republic of Duration: 2013 Feb 18 → 2013 Feb 20

Publication series

Name	2013 International Winter Workshop on Brain-Computer Interface, BCI 2013

Other

Other	2013 International Winter Workshop on Brain-Computer Interface, BCI 2013
Country/Territory	Korea, Republic of
City	Gangwon Province
Period	13/2/18 → 13/2/20

Keywords

CSP-Lp
Common spatial patterns (CSP)
Lp-norm
brain computer interfaces (BCI)
electroencephalogram (EEG) classification

ASJC Scopus subject areas

Human-Computer Interaction

Access to Document

10.1109/IWW-BCI.2013.6506623

Cite this

Park, J & Chung, W 2013, Common spatial patterns based on generalized norms. in 2013 International Winter Workshop on Brain-Computer Interface, BCI 2013., 6506623, 2013 International Winter Workshop on Brain-Computer Interface, BCI 2013, pp. 39-42, 2013 International Winter Workshop on Brain-Computer Interface, BCI 2013, Gangwon Province, Korea, Republic of, 13/2/18. https://doi.org/10.1109/IWW-BCI.2013.6506623

@inproceedings{bd5e3108965d4e5d878c054cb6792ee5,

title = "Common spatial patterns based on generalized norms",

abstract = "The Common Spatial Patterns (CSP) algorithm is commonly used to finds spatial filters for classification of electroencephalogram (EEG) signals. However, conventional CSP is sensitive to outliers and artifacts because it is based on variance using L2-norm. In this paper, we consider generalized L p norm based CSP, called CSP-Lp, and verify whichp is optimal for CSP-Lp by maximizing the Lp norm ratio of filtered dispersion of one class to the other class. The spatial filters of CSP-L p are obtained empirically. Simulation result on a toy example shows the robustness of CSP-Lp depending on Lp-norm.",

keywords = "CSP-Lp, Common spatial patterns (CSP), Lp-norm, brain computer interfaces (BCI), electroencephalogram (EEG) classification",

author = "Jangwoo Park and Wonzoo Chung",

year = "2013",

doi = "10.1109/IWW-BCI.2013.6506623",

language = "English",

isbn = "9781467359733",

series = "2013 International Winter Workshop on Brain-Computer Interface, BCI 2013",

pages = "39--42",

booktitle = "2013 International Winter Workshop on Brain-Computer Interface, BCI 2013",

}

TY - GEN

T1 - Common spatial patterns based on generalized norms

AU - Park, Jangwoo

AU - Chung, Wonzoo

PY - 2013

Y1 - 2013

N2 - The Common Spatial Patterns (CSP) algorithm is commonly used to finds spatial filters for classification of electroencephalogram (EEG) signals. However, conventional CSP is sensitive to outliers and artifacts because it is based on variance using L2-norm. In this paper, we consider generalized L p norm based CSP, called CSP-Lp, and verify whichp is optimal for CSP-Lp by maximizing the Lp norm ratio of filtered dispersion of one class to the other class. The spatial filters of CSP-L p are obtained empirically. Simulation result on a toy example shows the robustness of CSP-Lp depending on Lp-norm.

AB - The Common Spatial Patterns (CSP) algorithm is commonly used to finds spatial filters for classification of electroencephalogram (EEG) signals. However, conventional CSP is sensitive to outliers and artifacts because it is based on variance using L2-norm. In this paper, we consider generalized L p norm based CSP, called CSP-Lp, and verify whichp is optimal for CSP-Lp by maximizing the Lp norm ratio of filtered dispersion of one class to the other class. The spatial filters of CSP-L p are obtained empirically. Simulation result on a toy example shows the robustness of CSP-Lp depending on Lp-norm.

KW - CSP-Lp

KW - Common spatial patterns (CSP)

KW - Lp-norm

KW - brain computer interfaces (BCI)

KW - electroencephalogram (EEG) classification

UR - http://www.scopus.com/inward/record.url?scp=84877717851&partnerID=8YFLogxK

U2 - 10.1109/IWW-BCI.2013.6506623

DO - 10.1109/IWW-BCI.2013.6506623

M3 - Conference contribution

AN - SCOPUS:84877717851

SN - 9781467359733

T3 - 2013 International Winter Workshop on Brain-Computer Interface, BCI 2013

SP - 39

EP - 42

BT - 2013 International Winter Workshop on Brain-Computer Interface, BCI 2013

T2 - 2013 International Winter Workshop on Brain-Computer Interface, BCI 2013

Y2 - 18 February 2013 through 20 February 2013

ER -

Common spatial patterns based on generalized norms

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this