An Overview of BSS Techniques Based on Order Statistics: Formulation and Implementation Issues

  • Yolanda Blanco
  • Santiago Zazo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3195)


The main goal of this paper is to review the fundamental ideas of the method called “ICA with OS”. We review a set of alternative statistical distances between distributions based on the Cumulative Density Function (cdf). In particular, these gaussianity distances provide new cost functions whose maximization perform the extraction of one independent component at each successive stage of a new proposed deflation ICA procedure. These measures are estimated through Order Statistics (OS) that are consistent estimators of the inverse cdf. The new Gaussianity measures improve the ICA performance and also increase the robustness against outliers compared with the traditional ones.


Order Statistics Independent Component Analysis Independent Component Analysis Gaussianity Measure Cumulative Density Function 
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.
    Amari, S., Cichocki, A., Yang, H.H.: A New Learning Algorithm for Blind Signal Separation. In: Proc. of Neural Information Processing Systems, NIPS 1996, vol. 8, pp. 757–763 (1996)Google Scholar
  2. 2.
    Lee, T.-W.: Independent Component Analysis: Theory and Applications. Kluwer Academic Publishers, Dordrecht (1998)zbMATHGoogle Scholar
  3. 3.
    Blanco, Y., Zazo, S., Páez-Borrallo, J.M.: Adaptive Processing of Blind Source Separation through ’ICA with OS’. In: Proceedings of the International Conference On Acoustics And Signal Processing ICASSP 2000, vol. I, pp. 233–236 S (2000)Google Scholar
  4. 4.
    Blanco, Y., Zazo, S., Principe, J.C.: Alternative Statistical Gaussianity Measure using the Cumulative Density Function. In: Proceedings of the Second Workshop on Independent Component Analysis and Blind Signal Separation: ICA 2000. pp. 537–542 (2000)Google Scholar
  5. 5.
    Blanco, Y., Zazo, S., Páez-Borrallo, J.M.: Adaptive ICA with Order Statistics: An efficient approach based on serial orthogonal projections. In: Mira, J., Prieto, A.G. (eds.) IWANN 2001. LNCS, vol. 2085, pp. 770–778. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  6. 6.
    Blanco, Y., Zazo, S.: New Gaussianity Measures based on Order Statistics. Application to ICA. Elsevier. Neurocomputing 51, 303–320 (2003)CrossRefGoogle Scholar
  7. 7.
    Cardoso, J.F., Soulimiac, A.: Blind beamforming for Non Gaussian Signals. IEE Proceedings-F 140(6), 362–370 (1993)Google Scholar
  8. 8.
    Common, P.: Independent Component Analysis, A New Concept. Signal Processing (36), 287–314 (1992)CrossRefGoogle Scholar
  9. 9.
    Hyvärien, A., Karhunen, J., Oja, E.: Independent Component Analysis. Ed. John Wiley & sons, Chichester (2001)CrossRefGoogle Scholar
  10. 10.
    Kung, S.Y., Mejuto, C.: Extraction of Independent Components from Hybrid Mixture: Knicnet Learning Algorithm and Applications. In: Proc. International Conference On Acoustics And Signal Processing ICASSP 1998, vol. II, pp. 1209,1211 (1998)Google Scholar
  11. 11.
    Papoulis, A.: Probability and Statistics. Prentice Hall International, INC, Englewood Cliffs (1999)Google Scholar
  12. 12.
    Learned-Miller, E.G.: ICA Using Spacing Estimates of Entropy. Journal of Machine Learning Research 4, 1271–1295 (2003)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Yolanda Blanco
    • 1
    • 2
  • Santiago Zazo
    • 1
    • 2
  1. 1.Departamento de Ingenieria Eléctrica y ElectrónicaUniversidad Europea de MadridMadridSpain
  2. 2.ETS. Ingenieros TelecomunicaciónUniversidad Politécnica de MadridMadridSpain

Personalised recommendations