A Statistical Convergence Analysis of the FastICA Algorithm for Two-Source Mixtures

Author

Douglas, Scott C.

Author_Institution

Dept. of Electr. Eng., Southern Methodist Univ., Dallas, TX

fYear

2005

fDate

Oct. 28 2005-Nov. 1 2005

Firstpage

335

Lastpage

339

Abstract

While the FastICA algorithm is a popular procedure for independent component analysis (ICA) and blind source separation, its average convergence behavior has yet to be studied. This paper provides several statistical convergence analyses of the kurtosis-based FastICA algorithm for two-source noiseless mixtures. We derive explicit and approximate expressions for the evolutions of the average value and the p.d.f. of the inter-channel interference (ICI) under arbitrary and uniform priors for the initial separating system vector. Our results support the observation in S.C. Douglas 2003: this version of the FastICA algorithm reduces the average ICI by 1/3 or 4.77 dB at each iteration, independent of the source distributions and initial system state. Simulations verify the analytical results

Keywords

adjacent channel interference; blind source separation; independent component analysis; FastICA algorithm; average convergence behavior; blind source separation; independent component analysis; interchannel interference; source distributions; statistical convergence analysis; two-source mixtures; two-source noiseless mixtures; Algorithm design and analysis; Analytical models; Approximation algorithms; Blind source separation; Convergence; Data analysis; Entropy; Independent component analysis; Interchannel interference; Signal analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 2005. Conference Record of the Thirty-Ninth Asilomar Conference on

Conference_Location

Pacific Grove, CA

ISSN

1058-6393

Print_ISBN

1-4244-0131-3

Type

conf

DOI

10.1109/ACSSC.2005.1599763

Filename

1599763