Exterior Penalty Function Method Based ICA Algorithm for Hybrid Sources Using GKNN Estimation

  • Fasong Wang
  • Hongwei Li
  • Rui Li
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4232)


Novel Independent Component analysis(ICA) algorithm for hybrid sources separation based on constrained optimization—exterior penalty function method is proposed. The proposed exterior penalty ICA algorithm is under the framework of constrained ICA(cICA) method to solve the constrained optimization problem by using the exterior penalty function method. In order to choose nonlinear functions as the probability density function(PDF) estimation of the source signals, generalized k-nearest neighbor(GKNN) PDF estimation is proposed which can separate the hybrid mixtures of source signals using only a flexible model and more important it is completely blind to the sources. The proposed EX-cICA algorithm provides the way to wider applications of ICA methods to real world signal processing. Simulations confirm the effectiveness of the proposed algorithm.


Independent Component Analysis Constrain Optimization Problem Independent Component Analysis Natural Gradient Penalty Function Method 
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.
    Comon, P.: Independent component analysis: A new concept? Signal Processing 36(3), 287–314 (1994)MATHCrossRefGoogle Scholar
  2. 2.
    Bell, A., Sejnowski, T.: An information maximization approach to blind separation and blind deconvolution. Neural Computation 7(6), 1129–1159 (1995)CrossRefGoogle Scholar
  3. 3.
    Amari, S.: Natural gradient works efficiently in learning. Neural Computation 10(1), 251–276 (1998)CrossRefMathSciNetGoogle Scholar
  4. 4.
    Xu, L., Cheung, C.C., Amari, S.I.: Learned Parametric Mixture Based ICA Algorithm. Neurocomputing 22(1-3), 69–80 (1998)MATHCrossRefGoogle Scholar
  5. 5.
    Zhang, X.D., Zhu, X.L., Bao, Z.: Grading learning for blind source separation. Science in China (Series F) 46(1), 31–44 (2003)MATHCrossRefGoogle Scholar
  6. 6.
    Hyvarinen, A., Oja, E.: A fast fixed-point algorithm for independent component analysis. Neural Computation 9(7), 1483–1492 (1998)CrossRefGoogle Scholar
  7. 7.
    Boscolo, R., Pan, H., Roychowdhury, V.P.: Independent Component Analysis Based on Nonparametric Density Estimation. IEEE Trans. on Neural Networks 15(1), 55–65 (2004)CrossRefGoogle Scholar
  8. 8.
    Lu, W., Rajapakse, J.C.: Constrained independent component analysis. In: Leen, T., Dietterich, T., Tresp, V. (eds.) Advances in Neural Information Processing Systems, vol. 10, pp. 570–576. MIT Press, Cambridge (2001)Google Scholar
  9. 9.
    Lu, W., Rajapakse, J.C.: Eliminating indeterminacy in ica. Neurocomputing 50, 271–290 (2003)MATHCrossRefGoogle Scholar
  10. 10.
    Lu, W., Rajapakse, J.C.: Approach and Applications of Constrained ICA. IEEE Trans. on Neural Network 16(1), 203–212 (2005)CrossRefGoogle Scholar
  11. 11.
    Silverman, B.W.: Density Estimation for Statistics and Data Analysis. Chapman and Hall, New York (1985)Google Scholar
  12. 12.
    Pierani, A., Piazza, F., Solazzi, M., Uncini, A.: Low complexity adaptive nonlinear function for blind signal separation. In: Proc. IEEE Int. Joint Conf. Neural Networks, Italy, vol. 3, pp. 333–338 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Fasong Wang
    • 1
  • Hongwei Li
    • 1
  • Rui Li
    • 2
  1. 1.School of Mathematics and PhysicsChina University of GeosciencesWuhanP.R. China
  2. 2.School of Mathematics and PhysicsHenan University of TechnologyZhengzhouP.R. China

Personalised recommendations