Abstract
The goal of blind source separation is to separate multiple signals from linear mixtures without extensive knowledge about the statistical properties of the unknown signals. The design of separation criteria that achieve accurate and robust source estimates within a simple adaptive algorithm is an important part of this task. The purpose of this paper is threefold: (1) We introduce the Huber M-estimator cost function as a contrast function for use within prewhitened blind source separation algorithms such as the well-known and popular FastICA algorithm of Hyvärinen and Oja. The resulting algorithm obtained from this cost is particularly simple to implement. We establish key properties regarding the local stability of the algorithm for general non-Gaussian source distributions, and its separating capabilities are shown through analysis to be largely insensitive to the cost function’s single threshold parameter. (2) We illustrate the use of the Huber M-estimator cost as a criterion within the winning algorithm entry for the blind source separation portion of the first Machine Learning for Signal Processing Workshop Data Analysis Competition, describing the key features of the algorithm design for successful separation of large-scale and ill-conditioned signal mixtures with reduced data set requirements. (3) We show how the FastICA algorithm can be implemented without significant additional memory resources by careful use of sequential processing strategies.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
J.-F. Cardoso and A. Soloumiac, “Blind Beamforming for Non-Gaussian Signals,” IEE Proc. F, vol. 140, 1993, pp. 362–370 (December).
P. Comon, “Independent Component Analysis: A New Concept?,” Signal Process., vol. 36, 1994, pp. 287–314 (April).
S. Amari, T. Chen, and A. Cichocki, “Stability Analysis of Learning Algorithms for Blind Source Separation,” Neural Netw., vol. 8, 1997, pp. 1345–1351.
A. Hyvärinen, “Fast and Robust Fixed-point Algorithms for Independent Component Analysis,” IEEE Trans. Neural Netw., vol. 10, 1999, pp. 626–634 (May).
H. Mathis and S. C. Douglas, “On the Existence of Universal Nonlinearities for Blind Source Separation,” IEEE Trans. Signal Process., vol. 50, 2002, pp. 1007–1016 (May).
P. Huber, Robust Statistics, Wiley, New York, 1981.
A. Hyvärinen, P. O. Hoyer, and E. Oja, “Sparse Code Shrinkage: Denoising by Nonlinear Maximum Likelihood Estimation,” in Advances in Neural Information Processing Systems 11 (NIPS*98), MIT Press, 1999, pp. 473–479.
A. Cichocki and D. Erdogmus, “MLSP 2005 Competition: Large Scale, Ill-Conditioned Blind Source Separation Problem with Limited Number of Samples,” in 2005 IEEE Workshop on Machine Learning for Signal Processing, Mystic, CT, Sept. 2005.
S. C. Douglas and J. Chao, “A Blind Source Separation Solution for the MLSP 2005 Competition (Invited Talk),” in 2005 IEEE Workshop on Machine Learning for Signal Processing, Mystic, CT, Sept. 2005.
S.C. Douglas, “An Adaptive Constraint Method for Paraunitary Filter Banks with Applications to Spatiotemporal Subspace Tracking,” in EURASIP J. Appl. Signal Process., 2007 in press. DOI 10.1155/2007/80301
V. Calhoun and T. Adali, “Complex Infomax: Convergence and Approximation of Infomax with Complex Nonlinearities,” in Proc. IEEE Workshop on Neural Networks for Signal Processing, Martigny, Switzerland, September 2002, pp. 307–316.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Douglas, S.C., Chao, JC. Simple, Robust, and Memory-Efficient FastICA Algorithms Using the Huber M-Estimator Cost Function. J VLSI Sign Process Syst Sign Im 48, 143–159 (2007). https://doi.org/10.1007/s11265-007-0046-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11265-007-0046-9