Optimizing spatial filters for robust EEG single-trial analysis

Benjamin Blankertz, Ryota Tomioka, Steven Lemm, Motoaki Kawanabe, Klaus Muller

Research output: Contribution to journalArticle

1041 Citations (Scopus)

Abstract

The common spatial pattern (CSP) provides a clearer image of brain activity in single-trial analysis and improves signal-to-noise ratio in conducting multichannel electroencephalogram (EEG) recordings. CSP is a popular method in brain-computer interface (BCI) research. BCI systems promise developments in usability, information transfer and robustness for which modern machine learning and signal processing techniques have been instrumental. CSP produces a data-driven supervised decomposition of the signal parameterized by a certain matrix and is used to analyze multichannel data based on recordings from two conditions. CSP filters maximize the variance of the spatially filtered signal under one condition while minimizing it for another condition and can be applicable to band-pass filtered signals in order to yield an effective discrimination of mental stats that are characterized by ERD/ERS (event-related desynchronizationevent-related synchronization) effects. CSP can be used to extract general discriminative spatio-temporal structure for multivariate data streams beyond EEG.

Original languageEnglish
Pages (from-to)41-56
Number of pages16
JournalIEEE Signal Processing Magazine
Volume25
Issue number1
DOIs
Publication statusPublished - 2008
Externally publishedYes

Fingerprint

Brain computer interface
Spatial Pattern
Electroencephalography
Filter
Learning systems
Brain
Signal to noise ratio
Synchronization
Signal processing
Decomposition
Information Transfer
Multivariate Data
System Development
Data Streams
Data-driven
Usability
Discrimination
Signal Processing
Machine Learning
Maximise

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M., & Muller, K. (2008). Optimizing spatial filters for robust EEG single-trial analysis. IEEE Signal Processing Magazine, 25(1), 41-56. https://doi.org/10.1109/MSP.2008.4408441

Optimizing spatial filters for robust EEG single-trial analysis. / Blankertz, Benjamin; Tomioka, Ryota; Lemm, Steven; Kawanabe, Motoaki; Muller, Klaus.

In: IEEE Signal Processing Magazine, Vol. 25, No. 1, 2008, p. 41-56.

Research output: Contribution to journalArticle

Blankertz, B, Tomioka, R, Lemm, S, Kawanabe, M & Muller, K 2008, 'Optimizing spatial filters for robust EEG single-trial analysis', IEEE Signal Processing Magazine, vol. 25, no. 1, pp. 41-56. https://doi.org/10.1109/MSP.2008.4408441
Blankertz, Benjamin ; Tomioka, Ryota ; Lemm, Steven ; Kawanabe, Motoaki ; Muller, Klaus. / Optimizing spatial filters for robust EEG single-trial analysis. In: IEEE Signal Processing Magazine. 2008 ; Vol. 25, No. 1. pp. 41-56.
@article{ae25edfd7e064762b7d3b999f5783205,
title = "Optimizing spatial filters for robust EEG single-trial analysis",
abstract = "The common spatial pattern (CSP) provides a clearer image of brain activity in single-trial analysis and improves signal-to-noise ratio in conducting multichannel electroencephalogram (EEG) recordings. CSP is a popular method in brain-computer interface (BCI) research. BCI systems promise developments in usability, information transfer and robustness for which modern machine learning and signal processing techniques have been instrumental. CSP produces a data-driven supervised decomposition of the signal parameterized by a certain matrix and is used to analyze multichannel data based on recordings from two conditions. CSP filters maximize the variance of the spatially filtered signal under one condition while minimizing it for another condition and can be applicable to band-pass filtered signals in order to yield an effective discrimination of mental stats that are characterized by ERD/ERS (event-related desynchronizationevent-related synchronization) effects. CSP can be used to extract general discriminative spatio-temporal structure for multivariate data streams beyond EEG.",
author = "Benjamin Blankertz and Ryota Tomioka and Steven Lemm and Motoaki Kawanabe and Klaus Muller",
year = "2008",
doi = "10.1109/MSP.2008.4408441",
language = "English",
volume = "25",
pages = "41--56",
journal = "IEEE Signal Processing Magazine",
issn = "1053-5888",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Optimizing spatial filters for robust EEG single-trial analysis

AU - Blankertz, Benjamin

AU - Tomioka, Ryota

AU - Lemm, Steven

AU - Kawanabe, Motoaki

AU - Muller, Klaus

PY - 2008

Y1 - 2008

N2 - The common spatial pattern (CSP) provides a clearer image of brain activity in single-trial analysis and improves signal-to-noise ratio in conducting multichannel electroencephalogram (EEG) recordings. CSP is a popular method in brain-computer interface (BCI) research. BCI systems promise developments in usability, information transfer and robustness for which modern machine learning and signal processing techniques have been instrumental. CSP produces a data-driven supervised decomposition of the signal parameterized by a certain matrix and is used to analyze multichannel data based on recordings from two conditions. CSP filters maximize the variance of the spatially filtered signal under one condition while minimizing it for another condition and can be applicable to band-pass filtered signals in order to yield an effective discrimination of mental stats that are characterized by ERD/ERS (event-related desynchronizationevent-related synchronization) effects. CSP can be used to extract general discriminative spatio-temporal structure for multivariate data streams beyond EEG.

AB - The common spatial pattern (CSP) provides a clearer image of brain activity in single-trial analysis and improves signal-to-noise ratio in conducting multichannel electroencephalogram (EEG) recordings. CSP is a popular method in brain-computer interface (BCI) research. BCI systems promise developments in usability, information transfer and robustness for which modern machine learning and signal processing techniques have been instrumental. CSP produces a data-driven supervised decomposition of the signal parameterized by a certain matrix and is used to analyze multichannel data based on recordings from two conditions. CSP filters maximize the variance of the spatially filtered signal under one condition while minimizing it for another condition and can be applicable to band-pass filtered signals in order to yield an effective discrimination of mental stats that are characterized by ERD/ERS (event-related desynchronizationevent-related synchronization) effects. CSP can be used to extract general discriminative spatio-temporal structure for multivariate data streams beyond EEG.

UR - http://www.scopus.com/inward/record.url?scp=85032751688&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032751688&partnerID=8YFLogxK

U2 - 10.1109/MSP.2008.4408441

DO - 10.1109/MSP.2008.4408441

M3 - Article

VL - 25

SP - 41

EP - 56

JO - IEEE Signal Processing Magazine

JF - IEEE Signal Processing Magazine

SN - 1053-5888

IS - 1

ER -