Brain computer interface approach using sensor covariance matrix with forced whitening

Hyuksoo Shin; Wonzoo Chung

doi:10.1109/IWW-BCI.2017.7858161

Brain computer interface approach using sensor covariance matrix with forced whitening

Hyuksoo Shin, Wonzoo Chung

Division of Computer and Communication Engineering

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

Abstract

In this paper, we present a novel motor imagery classification method in electroencephalogmphy (EEG)-based Bmin-Computer lnterfaces (BCIs) using forced whitened sampIe covariance matdces as features. The proposed method performs a constant-forcing to the weaker sources of covadance matrices before a whitening process to prevent amplifications of noise sources which have small power relative to class relevant sources. Expedmental results show the improved accuracy in comparison with a classification without forced whitening process.

Original language	English
Title of host publication	5th International Winter Conference on Brain-Computer Interface, BCI 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	66-68
Number of pages	3
ISBN (Electronic)	9781509050963
DOIs	https://doi.org/10.1109/IWW-BCI.2017.7858161
Publication status	Published - 2017 Feb 16
Event	5th International Winter Conference on Brain-Computer Interface, BCI 2017 - Gangwon Province, Korea, Republic of Duration: 2017 Jan 9 → 2017 Jan 11

Other

Other	5th International Winter Conference on Brain-Computer Interface, BCI 2017
Country	Korea, Republic of
City	Gangwon Province
Period	17/1/9 → 17/1/11

Keywords

Brain-computer interface (BCI)
Classification
Sensor covariance matrix
Supporting vector machine (SVM)
Whitening matrix

ASJC Scopus subject areas

Signal Processing
Human-Computer Interaction

Access to Document

10.1109/IWW-BCI.2017.7858161

Fingerprint Dive into the research topics of 'Brain computer interface approach using sensor covariance matrix with forced whitening'. Together they form a unique fingerprint.

Cite this

Shin, H & Chung, W 2017, Brain computer interface approach using sensor covariance matrix with forced whitening. in 5th International Winter Conference on Brain-Computer Interface, BCI 2017., 7858161, Institute of Electrical and Electronics Engineers Inc., pp. 66-68, 5th International Winter Conference on Brain-Computer Interface, BCI 2017, Gangwon Province, Korea, Republic of, 17/1/9. https://doi.org/10.1109/IWW-BCI.2017.7858161

@inproceedings{d9320c38e6cf4420ba08bb536169b4d9,

title = "Brain computer interface approach using sensor covariance matrix with forced whitening",

abstract = "In this paper, we present a novel motor imagery classification method in electroencephalogmphy (EEG)-based Bmin-Computer lnterfaces (BCIs) using forced whitened sampIe covariance matdces as features. The proposed method performs a constant-forcing to the weaker sources of covadance matrices before a whitening process to prevent amplifications of noise sources which have small power relative to class relevant sources. Expedmental results show the improved accuracy in comparison with a classification without forced whitening process.",

keywords = "Brain-computer interface (BCI), Classification, Sensor covariance matrix, Supporting vector machine (SVM), Whitening matrix",

author = "Hyuksoo Shin and Wonzoo Chung",

year = "2017",

month = feb,

day = "16",

doi = "10.1109/IWW-BCI.2017.7858161",

language = "English",

pages = "66--68",

booktitle = "5th International Winter Conference on Brain-Computer Interface, BCI 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "5th International Winter Conference on Brain-Computer Interface, BCI 2017 ; Conference date: 09-01-2017 Through 11-01-2017",

}

TY - GEN

T1 - Brain computer interface approach using sensor covariance matrix with forced whitening

AU - Shin, Hyuksoo

AU - Chung, Wonzoo

PY - 2017/2/16

Y1 - 2017/2/16

N2 - In this paper, we present a novel motor imagery classification method in electroencephalogmphy (EEG)-based Bmin-Computer lnterfaces (BCIs) using forced whitened sampIe covariance matdces as features. The proposed method performs a constant-forcing to the weaker sources of covadance matrices before a whitening process to prevent amplifications of noise sources which have small power relative to class relevant sources. Expedmental results show the improved accuracy in comparison with a classification without forced whitening process.

AB - In this paper, we present a novel motor imagery classification method in electroencephalogmphy (EEG)-based Bmin-Computer lnterfaces (BCIs) using forced whitened sampIe covariance matdces as features. The proposed method performs a constant-forcing to the weaker sources of covadance matrices before a whitening process to prevent amplifications of noise sources which have small power relative to class relevant sources. Expedmental results show the improved accuracy in comparison with a classification without forced whitening process.

KW - Brain-computer interface (BCI)

KW - Classification

KW - Sensor covariance matrix

KW - Supporting vector machine (SVM)

KW - Whitening matrix

UR - http://www.scopus.com/inward/record.url?scp=85016023525&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016023525&partnerID=8YFLogxK

U2 - 10.1109/IWW-BCI.2017.7858161

DO - 10.1109/IWW-BCI.2017.7858161

M3 - Conference contribution

AN - SCOPUS:85016023525

SP - 66

EP - 68

BT - 5th International Winter Conference on Brain-Computer Interface, BCI 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th International Winter Conference on Brain-Computer Interface, BCI 2017

Y2 - 9 January 2017 through 11 January 2017

ER -