Blind source separation techniques for decomposing event-related brain signals

Klaus Robert Müller; Ricardo Vigário; Frank Meinecke; Andreas Ziehe

doi:10.1142/S0218127404009466

Blind source separation techniques for decomposing event-related brain signals

Klaus Robert Müller, Ricardo Vigário, Frank Meinecke, Andreas Ziehe

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

33 Citations (Scopus)

Abstract

Recently blind source separation (BSS) methods have been highly successful when applied to biomedical data. This paper reviews the concept of BSS and demonstrates its usefulness in the context of event-related MEG measurements. In a first experiment we apply BSS to artifact identification of raw MEG data and discuss how the quality of the resulting independent component projections can be evaluated. The second part of our study considers averaged data of event-related magnetic fields. Here, it is particularly important to monitor and thus avoid possible overfitting due to limited sample size. A stability assessment of the BSS decomposition allows to solve this task and an additional grouping of the BSS components reveals interesting structure, that could ultimately be used for gaining a better physiological modeling of the data.

Original language	English
Pages (from-to)	773-791
Number of pages	19
Journal	International Journal of Bifurcation and Chaos in Applied Sciences and Engineering
Volume	14
Issue number	2
DOIs	https://doi.org/10.1142/S0218127404009466
Publication status	Published - 2004 Feb

Bibliographical note

Funding Information:
Valuable discussions with M. Kawanabe, C. Schäfer, J. Kohlmorgen, G. Nolte, B. Blankertz, G. Curio, J. Särelä, Harri Valpola and participants of the Potsdam workshop on ERPs 2001 are gratefully acknowledged. The authors thank the Low Temperature Laboratory at HUTs for the permission to use their data in this work. R. Vigário was funded by EU (Marie Curie fellowship HPMF-CT-2000-00813). K.-R. Müller and A. Ziehe were partly funded by EU (IST-1999-14190 – BLISS) and the BMBF in the BCI project.

Keywords

Blind Source Separation (BSS)
Bootstrap
Evoked responses
High order statistics
Independent Component Analysis (ICA)
MEG
Reliability
TDSEP
Temporal decorrelation

ASJC Scopus subject areas

Modelling and Simulation
Engineering (miscellaneous)
General
Applied Mathematics

Access to Document

10.1142/S0218127404009466

Cite this

@article{c56e8a4fdf774313a946f767d60cd7fd,

title = "Blind source separation techniques for decomposing event-related brain signals",

abstract = "Recently blind source separation (BSS) methods have been highly successful when applied to biomedical data. This paper reviews the concept of BSS and demonstrates its usefulness in the context of event-related MEG measurements. In a first experiment we apply BSS to artifact identification of raw MEG data and discuss how the quality of the resulting independent component projections can be evaluated. The second part of our study considers averaged data of event-related magnetic fields. Here, it is particularly important to monitor and thus avoid possible overfitting due to limited sample size. A stability assessment of the BSS decomposition allows to solve this task and an additional grouping of the BSS components reveals interesting structure, that could ultimately be used for gaining a better physiological modeling of the data.",

keywords = "Blind Source Separation (BSS), Bootstrap, Evoked responses, High order statistics, Independent Component Analysis (ICA), MEG, Reliability, TDSEP, Temporal decorrelation",

author = "M{\"u}ller, {Klaus Robert} and Ricardo Vig{\'a}rio and Frank Meinecke and Andreas Ziehe",

note = "Funding Information: Valuable discussions with M. Kawanabe, C. Sch{\"a}fer, J. Kohlmorgen, G. Nolte, B. Blankertz, G. Curio, J. S{\"a}rel{\"a}, Harri Valpola and participants of the Potsdam workshop on ERPs 2001 are gratefully acknowledged. The authors thank the Low Temperature Laboratory at HUTs for the permission to use their data in this work. R. Vig{\'a}rio was funded by EU (Marie Curie fellowship HPMF-CT-2000-00813). K.-R. M{\"u}ller and A. Ziehe were partly funded by EU (IST-1999-14190 – BLISS) and the BMBF in the BCI project.",

year = "2004",

month = feb,

doi = "10.1142/S0218127404009466",

language = "English",

volume = "14",

pages = "773--791",

journal = "International Journal of Bifurcation and Chaos in Applied Sciences and Engineering",

issn = "0218-1274",

publisher = "World Scientific",

number = "2",

}

TY - JOUR

T1 - Blind source separation techniques for decomposing event-related brain signals

AU - Müller, Klaus Robert

AU - Vigário, Ricardo

AU - Meinecke, Frank

AU - Ziehe, Andreas

N1 - Funding Information: Valuable discussions with M. Kawanabe, C. Schäfer, J. Kohlmorgen, G. Nolte, B. Blankertz, G. Curio, J. Särelä, Harri Valpola and participants of the Potsdam workshop on ERPs 2001 are gratefully acknowledged. The authors thank the Low Temperature Laboratory at HUTs for the permission to use their data in this work. R. Vigário was funded by EU (Marie Curie fellowship HPMF-CT-2000-00813). K.-R. Müller and A. Ziehe were partly funded by EU (IST-1999-14190 – BLISS) and the BMBF in the BCI project.

PY - 2004/2

Y1 - 2004/2

N2 - Recently blind source separation (BSS) methods have been highly successful when applied to biomedical data. This paper reviews the concept of BSS and demonstrates its usefulness in the context of event-related MEG measurements. In a first experiment we apply BSS to artifact identification of raw MEG data and discuss how the quality of the resulting independent component projections can be evaluated. The second part of our study considers averaged data of event-related magnetic fields. Here, it is particularly important to monitor and thus avoid possible overfitting due to limited sample size. A stability assessment of the BSS decomposition allows to solve this task and an additional grouping of the BSS components reveals interesting structure, that could ultimately be used for gaining a better physiological modeling of the data.

AB - Recently blind source separation (BSS) methods have been highly successful when applied to biomedical data. This paper reviews the concept of BSS and demonstrates its usefulness in the context of event-related MEG measurements. In a first experiment we apply BSS to artifact identification of raw MEG data and discuss how the quality of the resulting independent component projections can be evaluated. The second part of our study considers averaged data of event-related magnetic fields. Here, it is particularly important to monitor and thus avoid possible overfitting due to limited sample size. A stability assessment of the BSS decomposition allows to solve this task and an additional grouping of the BSS components reveals interesting structure, that could ultimately be used for gaining a better physiological modeling of the data.

KW - Blind Source Separation (BSS)

KW - Bootstrap

KW - Evoked responses

KW - High order statistics

KW - Independent Component Analysis (ICA)

KW - MEG

KW - Reliability

KW - TDSEP

KW - Temporal decorrelation

UR - http://www.scopus.com/inward/record.url?scp=13844281215&partnerID=8YFLogxK

U2 - 10.1142/S0218127404009466

DO - 10.1142/S0218127404009466

M3 - Article

AN - SCOPUS:13844281215

SN - 0218-1274

VL - 14

SP - 773

EP - 791

JO - International Journal of Bifurcation and Chaos in Applied Sciences and Engineering

JF - International Journal of Bifurcation and Chaos in Applied Sciences and Engineering

IS - 2

ER -

Blind source separation techniques for decomposing event-related brain signals

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this