Difficulties Applying Recent Blind Source Separation Techniques to EEG and MEG

  • K. H. Knuth
Part of the Fundamental Theories of Physics book series (FTPH, volume 98)


High temporal resolution measurements of human brain activity can be performed by recording the electric potentials on the scalp surface (electroencephalography, EEG), or by recording the magnetic fields near the surface of the head (magnetoencephalography, MEG). The analysis of the data is problematic due to the fact that multiple neural generators may be simultaneously active and the potentials and magnetic fields from these sources are superimposed on the detectors. It is highly desirable to un-mix the data into signals representing the behaviors of the original individual generators. This general problem is called blind source separation and several recent techniques utilizing maximum entropy, minimum mutual information, and maximum likelihood estimation have been applied. These techniques have had much success in separating signals such as natural sounds or speech, but appear to be ineffective when applied to EEG or MEG signals. Many of these techniques implicitly assume that the source distributions have a large kurtosis, whereas an analysis of EEG/MEG signals reveals that the distributions are multimodal. This suggests that more effective separation techniques could be designed for EEG and MEG signals.


Audio Signal Independent Component Analysis Blind Source Separation Neural Generator High Kurtosis 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bell, A.J. and Sejnowski, T.J. (1995) An information-maximization approach to blind separation and blind deconvolution, Neural Computation, 7, 1129–1159.CrossRefGoogle Scholar
  2. Cardoso, J.-F. (1995) A tetradic decomposition of 4th-order tensors: application to the source separation problem, in M. Moonen and B. de Moor (eds.),Algorithms, Architectures and Applications, Volume III of SVD and Signal Processing, Elsevier, Amsterdam, pp. 375–382.Google Scholar
  3. Cardoso, J.-F. (1997) Infomax and maximum likelihood for source separation, IEEE Letters on Signal Processing, 4(4), 112–114.CrossRefGoogle Scholar
  4. Comon, P. (1994) Independent component analysis, a new concept?, Signal Processing, 36, 287–314.zbMATHCrossRefGoogle Scholar
  5. MacKay, D.J.C. (1996) Maximum likelihood and covariant algorithms for independent component analysis, Draft Paper, Scholar
  6. Pearlmutter, B.A. and Parra, L.C. (1996) A context-sensitive generalization of ICA, 1996 International Conference on Neural Information Processing, Hong Kong.Google Scholar
  7. Penrose, R. (1955) A generalized inverse for matrices, Proceedings of the Cambridge Philosophical Society, part 3, pp. 406–413.Google Scholar
  8. Yang, H.H. and Amari S. (1997) Adaptive on-line learning algorithms for blind separation – maximum entropy and minimum mutual information, To appear in Neural Computation.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1998

Authors and Affiliations

  • K. H. Knuth
    • 1
  1. 1.Dynamic Brain Imaging Laboratory, Department of NeuroscienceAlbert Einstein College of MedicineBronxUSA

Personalised recommendations