Adaptive ICA Algorithm Based on Asymmetric Generalized Gaussian Density Model

  • Fasong Wang
  • Hongwei Li
Conference paper


A novel Independent Component Analysis(ICA) algorithm is achieved, which enable to separate mixtures of symmetric and asymmetric sources with self adaptive nonlinear score functions. It is derived by using the parameterized asymmetric generalized Gaussian density (AGGD) model. Compared with conventional ICA algorithm, the proposed AGGD-ICA method can separate a wide range of signals including skewed sources. Simulations confirm the effectiveness and performance of the approach.


Independent Component Analysis Score Function Independent Component Analysis Natural Gradient Independent Component Analysis Algorithm 
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.

5 References

  1. [1]
    Comon, P. (1994) Independent component analysis, A new concept?. Signal Processing 36: 287–314MATHCrossRefGoogle Scholar
  2. [2]
    Amari, S. (1998) Natural gradient works efficiently in learning. Neural Computation 10: 251–276CrossRefGoogle Scholar
  3. [3]
    Cardoso, J.F, Laheld, B. (1996) Equivariant adaptive source separation. IEEE Trans, on Signal Processing 44: 3017–3030CrossRefGoogle Scholar
  4. [4]
    Chamber, J.A., Jafari, M.G., McLaughlin, S. (2004) Variable step-size EASI algorithm for sequential blind source separation. Electronics Letters 40: 393–394CrossRefGoogle Scholar
  5. [5]
    Choi, S., Cichocki, A., Amari, S. (2000) Flexible Independent Component Analysis. J. VLSI Signal Process 20: 25C38Google Scholar
  6. [6]
    Tesei, A., Regazzoni, C.S. (1998) HOS-based generalized noise pdf models for signal detection optimization. Signal Processing 65: 267–281CrossRefGoogle Scholar
  7. [7]
    Cao, J., Murata, N., Amari, S., Cichocki, A., Takeda, T. (2003) A Robust Approach to Independent Component Analysis of Signals With High-Level Noise Measurements. IEEE Tans, on Neural Network 14: 631–645CrossRefGoogle Scholar
  8. [8]
    Tesei, A., Regazzoni, C.S. (1996) Use of four-order statistics for non-Gaussian noise modeling: the generalized Gaussian Pdf in terms of kurtosis. In: Ramponi, G., Sicuranza, G.L., Carrato, S., Marsi, S. (eds.) Proc. EUSIPCO’96. EdizioniLINT, pp. 671–674Google Scholar

Copyright information

© Springer-Verlag/Wien 2005

Authors and Affiliations

  • Fasong Wang
    • 1
  • Hongwei Li
    • 1
  1. 1.Department of Mathematics and PhysicsChina University of GeosciencesWuhanChina

Personalised recommendations