Blind source separation techniques for decomposing event-related brain signals

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

Research output: Contribution to journalArticlepeer-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 languageEnglish
Pages (from-to)773-791
Number of pages19
JournalInternational Journal of Bifurcation and Chaos in Applied Sciences and Engineering
Volume14
Issue number2
DOIs
Publication statusPublished - 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

Fingerprint

Dive into the research topics of 'Blind source separation techniques for decomposing event-related brain signals'. Together they form a unique fingerprint.

Cite this