Skip to main content
SpringerLink
Log in

Independent Component Analysis for Time-dependent Processes Using AR Source Model

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Independent component analysis is a fundamental and important task in unsupervised learning, that was studied mainly in the domain of Hebbian learning. In this paper, the temporal dependencies are explained by assuming that each source is an autoregressive (AR) process and innovations are independently and identically distributed (i.i.d). First, the likelihood of the model is derived, which takes into account both spatial and temporal information of the sources. Next, batch and on-line blind source separation algorithms are developed by maximizing likelihood function, and their local stability analysis are introduced simultaneously. Finally, computer simulations show that the algorithms achieve better separation of the mixed signals and mixed nature images which are difficult to be separated by the basic independent component analysis algorithms.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Hyvärinen A, Karhunen J, Oja E (2001) Independent component analysis. Wiley, New York

    Google Scholar 

  2. Jutten C, Hérault J (1991) Blind separation of sources, part I: an adaptive algorithm based on neuromimetic architecture. Signal Process 24: 1–10

    Article  MATH  Google Scholar 

  3. Common P (1994) Independent component analysis—a new concept?. Signal Process 36: 287–314

    Article  Google Scholar 

  4. Tong L, Liu R-W, Soon VC, Huang Y-F (1991) Indeterminacy and identifiability of blind identification. IEEE Trans Circuit Syst 38: 499–509

    Article  MATH  Google Scholar 

  5. Molgedey L, Schuster HG (1994) Separation of a mixture of independent signals using time delayed correlations. Phys Rev Lett 72: 3634–3636

    Article  ADS  Google Scholar 

  6. Belouchrani A, Abed Meraim K, Cardoso J-F, Moulines E (1997) A blind source separation technique based on second order statistics. IEEE Trans Signal Process 45(2): 434–444

    Article  Google Scholar 

  7. Pham D-T (2001) Blind separation of instantaneous mixtures of sources via the Gaussian mutual information criterion. Signal Process 81: 855–870

    Article  MATH  Google Scholar 

  8. Ziehe A, Müller K-R (1998) TDSEP—an efficient algorithm for blind separation using time structure. In: Proc. Int. Conf. on Artificial Neural Networks (ICANN’98), Skövde, Sweden, pp 675–680

  9. Kawamoto M, Matsuoka K, Oya M (1997) Blind separation of sources using temporal correlation of the observed signals. IEICE Trans Fund E80-A(4): 695–704

    Google Scholar 

  10. Amari S-I (2000) Estimating functions of independent component analysis for temporally correlated signals. Neural Comput 12(9): 2083–2107

    Article  Google Scholar 

  11. Degerine S, Malki R (2000) Second-order blind separation of sources based on canonical partial innovations. IEEE Trans Signal Process 48(3): 629–641

    Article  Google Scholar 

  12. Hyvärinen A (2001) Complexity pursuit: separating interesting component from time-series. Neural Comput 13(4): 883–898

    Article  MATH  Google Scholar 

  13. Müller K-R, Philips P, Ziehe A (1999) JADE TD : combining higher-order statistics and temporal information for blind source separation (with noise). In: Proc. int. Workshop on independent component analysis and signal separation (ICA’99), Aussois, France, pp 87–92

  14. Hild II KE, Attias HT, Nagarajan SS (2006) An EM method for spatio-temporal blind source separation using an AR-MOG source model. In: Proc. Int. Workshop on independent component analysis and signal separation (ICA’06), Charleston, USA, pp 98–105

  15. Moulines E, Cardoso JF, Gassiat E (1997) Maximum likelihood for blind source separation and deconvolution of noisy signals using mixture models. In: Proc. IEEE Int. Conf. on acoustics, speech, and signal processing, Munich, Germany, pp 3617–3620

  16. Pearlmutter BA, Parra LC (1996) A context-sensitive generalization of ICA. In: Proc. Int. Conf. on neural information processing, Hong Kong, pp 151–157

  17. Xu L (2007) One-bit-matching theorem for ICA, convex-concave programming on polyhedral set, and distribution approximation for combinatorics. Neural Comput 19(2): 546–569

    Article  MathSciNet  MATH  Google Scholar 

  18. Liu ZY, Chiu KC, Xu L (2004) One-bit-matching conjecture for independent component analysis. Neural Comput 16(2): 383–399

    Article  MATH  Google Scholar 

  19. Amari S-I, Chen TP, Cichocki A (1997) Stability analysis of learning algorithms for blind source separation. Neural Networks 10: 1345–1351

    Article  Google Scholar 

  20. Amari S-I, Cichocki A, Yang HH (1996) A new learning algorithm for blind source separation. In: Advances in neural information processing systems, vol 8, MIT Press, Cambridge, pp 757–763

  21. Pajunen P (1998) Blind source separation using algorithmic information theory. Neurocomputing 22: 35–48

    Article  MATH  Google Scholar 

  22. Hyvärinen A, Oja E (1997) A fast fixed-point algorithm for independent component analysis. Neural Comput 9(7): 1483–1492

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Applied Mathematics, Dalian University of Technology, Dalian, 116024, P. R. China

    Yumin Yang & Zunquan Xia

  2. Department of Mathematics, Anshan Normal University, Anshan, 114001, P. R. China

    Yumin Yang

  3. Institute of Systems Engineering, Dalian University of Technology, Dalian, 116024, P. R. China

    Chonghui Guo

Authors
  1. Yumin Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chonghui Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zunquan Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chonghui Guo.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Yang, Y., Guo, C. & Xia, Z. Independent Component Analysis for Time-dependent Processes Using AR Source Model. Neural Process Lett 27, 227–236 (2008). https://doi.org/10.1007/s11063-008-9071-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-008-9071-3

Keywords

Search

Navigation