Robust common spatial filters with a maxmin approach.

Motoaki Kawanabe, Carmen Vidaurre, Simon Scholler, Klaus Robert Müller

Research output: Contribution to journalArticle

Abstract

Electroencephalographic signals are known to be non-stationary and easily affected by artifacts, therefore their analysis requires methods that can deal with noise. In this work we present two ways of calculating robust common spatial patterns under a maxmin approach. The worst-case objective function is optimized within prefixed sets of the covariance matrices that are defined either very simply as identity matrices or in a data driven way using PCA. We test common spatial filters derived with these two approaches with real world brain-computer interface (BCI) data sets in which we expect substantial "day-to-day" fluctuations (session transfer problem). We compare our results with the classical common spatial filters and show that both can improve the performance of the latter.

Original languageEnglish
Pages (from-to)2470-2473
Number of pages4
JournalConference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference
Publication statusPublished - 2009
Externally publishedYes

Fingerprint

Brain-Computer Interfaces
Passive Cutaneous Anaphylaxis
Brain computer interface
Covariance matrix
Artifacts
Noise
Datasets

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Robust common spatial filters with a maxmin approach. / Kawanabe, Motoaki; Vidaurre, Carmen; Scholler, Simon; Müller, Klaus Robert.

In: Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, 2009, p. 2470-2473.

Research output: Contribution to journalArticle

@article{6a90804beb1e43db9adff488dc510d16,
title = "Robust common spatial filters with a maxmin approach.",
abstract = "Electroencephalographic signals are known to be non-stationary and easily affected by artifacts, therefore their analysis requires methods that can deal with noise. In this work we present two ways of calculating robust common spatial patterns under a maxmin approach. The worst-case objective function is optimized within prefixed sets of the covariance matrices that are defined either very simply as identity matrices or in a data driven way using PCA. We test common spatial filters derived with these two approaches with real world brain-computer interface (BCI) data sets in which we expect substantial {"}day-to-day{"} fluctuations (session transfer problem). We compare our results with the classical common spatial filters and show that both can improve the performance of the latter.",
author = "Motoaki Kawanabe and Carmen Vidaurre and Simon Scholler and M{\"u}ller, {Klaus Robert}",
year = "2009",
language = "English",
pages = "2470--2473",
journal = "The BMJ",
issn = "0730-6512",
publisher = "Kluwer Academic Publishers",

}

TY - JOUR

T1 - Robust common spatial filters with a maxmin approach.

AU - Kawanabe, Motoaki

AU - Vidaurre, Carmen

AU - Scholler, Simon

AU - Müller, Klaus Robert

PY - 2009

Y1 - 2009

N2 - Electroencephalographic signals are known to be non-stationary and easily affected by artifacts, therefore their analysis requires methods that can deal with noise. In this work we present two ways of calculating robust common spatial patterns under a maxmin approach. The worst-case objective function is optimized within prefixed sets of the covariance matrices that are defined either very simply as identity matrices or in a data driven way using PCA. We test common spatial filters derived with these two approaches with real world brain-computer interface (BCI) data sets in which we expect substantial "day-to-day" fluctuations (session transfer problem). We compare our results with the classical common spatial filters and show that both can improve the performance of the latter.

AB - Electroencephalographic signals are known to be non-stationary and easily affected by artifacts, therefore their analysis requires methods that can deal with noise. In this work we present two ways of calculating robust common spatial patterns under a maxmin approach. The worst-case objective function is optimized within prefixed sets of the covariance matrices that are defined either very simply as identity matrices or in a data driven way using PCA. We test common spatial filters derived with these two approaches with real world brain-computer interface (BCI) data sets in which we expect substantial "day-to-day" fluctuations (session transfer problem). We compare our results with the classical common spatial filters and show that both can improve the performance of the latter.

UR - http://www.scopus.com/inward/record.url?scp=84903875885&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903875885&partnerID=8YFLogxK

M3 - Article

C2 - 19964963

SP - 2470

EP - 2473

JO - The BMJ

JF - The BMJ

SN - 0730-6512

ER -