Robust Second-Order Source Separation Identifies Experimental Responses in Biomedical Imaging

  • Fabian J. Theis
  • Nikola S. Müller
  • Claudia Plant
  • Christian Böhm
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6365)


Multidimensional biomedical imaging requires robust statistical analyses. Corresponding experiments such as EEG or FRAP commonly result in multiple time series. These data are classically characterized by recording response patterns to any kind of stimulation mixed with any degree of noise levels. Here, we want to detect the underlying signal sources such as these experimental responses in an unbiased fashion, and therefore extend and employ a source separation technique based on temporal autodecorrelation. Our extension first centers the data using a multivariate median, and then separates the sources based on approximate joint diagonalization of multiple sign autocovariance matrices.


Independent Component Analysis Scatter Matrice Spatial Median Robust Covariance Multivariate Median 
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. 1.
    Oja, H., Sirkiä, S., Eriksson, J.: Scatter matrices and independent component analysis. Austrian Journal of Statistics 35(2), 175–189 (2006)Google Scholar
  2. 2.
    Nordhausen, K., Oja, H., Ollila, E.: Robust independent component analysis based on two scatter matrices. Austrian Journal of Statistics 37(1), 91–100 (2008)Google Scholar
  3. 3.
    Fekete, S., Mitchell, J., Weinbrecht, K.: On the continuous weber and k-median problems. In: Proc. sixteenth SoCG, pp. 70–79 (2000)Google Scholar
  4. 4.
    Weber, A.: Über den Standort der Industrien. Tübingen (1909)Google Scholar
  5. 5.
    Dudley, R.: Department of mathematics, MIT, course 18.465 (2005)Google Scholar
  6. 6.
    Weiszfeld, E.: Sur le point par lequel la somme des distances de n points donnés est minimum. Tohoku Mathematics Journal 43, 355–386 (1937)Google Scholar
  7. 7.
    Vardi, Y., Zhang, C.H.: The multivariate L 1-median and associated data depth. Proc. Nat. Acad. Sci. USA 97(4), 1423–1426 (2000)zbMATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Visuri, S., Koivunen, V., Oja, H.: Sign and rank covariance matrices and rank covariance matrices. Journal of Statistical Planning and Inference 91(2), 557–575 (2000)zbMATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Kirshner, S., Poczos, B.: ICA and ISA using schweizer-wolff measure of dependence. In: Proc. ICML 2008, vol. 307 (2008)Google Scholar
  10. 10.
    Tong, L., Liu, R.W., Soon, V., Huang, Y.F.: Indeterminacy and identifiability of blind identification. IEEE Transactions on Circuits and Systems 38, 499–509 (1991)zbMATHCrossRefGoogle Scholar
  11. 11.
    Belouchrani, A., Meraim, K.A., Cardoso, J.F., Moulines, E.: A blind source separation technique based on second order statistics. IEEE Transactions on Signal Processing 45(2), 434–444 (1997)CrossRefGoogle Scholar
  12. 12.
    Cardoso, J., Souloumiac, A.: Blind beamforming for non gaussian signals. IEE Proceedings - F 140(6), 362–370 (1993)Google Scholar
  13. 13.
    Iannetti, G.D., Zambreanu, L., Cruccu, G., Tracey, I.: Operculoinsular cortex encodes pain intensity at the earliest stages of cortical processing as indicated by amplitude of laser-evoked potentials in humans. Neuroscience 131, 199–208 (2005)CrossRefGoogle Scholar
  14. 14.
    Wedlich-Söldner, R., Wai, S.C., Schmidt, T., Li, R.: Robust cell polarity is a dynamic state established by coupling transport and GTPase signaling. J. Cell Biol. 166, 889–900 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Fabian J. Theis
    • 1
  • Nikola S. Müller
    • 2
  • Claudia Plant
    • 3
  • Christian Böhm
    • 4
  1. 1.IBIS, Helmholtz Zentrum MunichGermany
  2. 2.Max Planck Institute for BiochemistryMartinsriedGermany
  3. 3.Florida State UniversityUSA
  4. 4.University of MunichGermany

Personalised recommendations