Blind source separation using Renyi´s mutual information

Author

Hild, Kenneth E., II ; Erdogmus, Deniz ; Príncipe, José

Author_Institution

Lab. of Comput. NeuroEngineering, Florida Univ., Gainesville, FL, USA

Volume

8

Issue

6

fYear

2001

fDate

6/1/2001 12:00:00 AM

Firstpage

174

Lastpage

176

Abstract

A blind source separation algorithm is proposed that is based on minimizing Renyi´s mutual information by means of nonparametric probability density function (PDF) estimation. The two-stage process consists of spatial whitening and a series of Givens rotations and produces a cost function consisting only of marginal entropies. This formulation avoids the problems of PDF inaccuracy due to truncation of series expansion and the estimation of joint PDFs in high-dimensional spaces given the typical paucity of data. Simulations illustrate the superior efficiency, in terms of data length, of the proposed method compared to fast independent component analysis (FastICA), Comon´s (1994) minimum mutual information, and Bell and Sejnowski´s (1995) Infomax.

Keywords

entropy; information theory; minimisation; nonparametric statistics; probability; signal processing; FastICA; Givens rotations; Infomax; PDF estimation; Renyi´s mutual information minimization; blind source separation algorithm; cost function; independent component analysis; marginal entropies; minimum mutual information; nonparametric probability density function; spatial whitening; Analytical models; Blind source separation; Cost function; Entropy; Independent component analysis; Information analysis; Mutual information; Polynomials; Probability density function; Source separation;

fLanguage

English

Journal_Title

Signal Processing Letters, IEEE

Publisher

ieee

ISSN

1070-9908

Type

jour

DOI

10.1109/97.923043

Filename

923043