Blind Second-Order Source Extraction of Instantaneous Noisy Mixtures

Author

Liu, Wei ; Mandic, Danilo P. ; Cichocki, Andrzej

Author_Institution

Dept. of Electron. & Electr. Eng., Univ. of Sheffield

Volume

53

Issue

9

fYear

2006

Firstpage

931

Lastpage

935

Abstract

The problem of blind source extraction (BSE) for noisy measurements is addressed in the domain of second-order statistics using the linear predictor method. By extending the results from the noise-free case, two methods for the noisy case are proposed, whereby, for rigor, the effect of noise is removed from the cost function. The so introduced algorithms are based, respectively, on the minimization of the normalized mean square prediction error (MSPE), and the minimization of MPSE. The analysis of the derived BSE algorithms is supported by simulations

Keywords

blind source separation; higher order statistics; mean square error methods; additive noise; blind second-order source extraction; instantaneous noisy mixtures; linear predictor method; noisy measurements; normalized mean square prediction error; second-order statistics; Adaptive algorithm; Additive noise; Algorithm design and analysis; Analytical models; Cost function; Higher order statistics; Minimization methods; Signal processing; Signal processing algorithms; Vectors; Additive noise; blind source extraction (BSE); online learning; second-order statistics;

fLanguage

English

Journal_Title

Circuits and Systems II: Express Briefs, IEEE Transactions on

Publisher

ieee

ISSN

1549-7747

Type

jour

DOI

10.1109/TCSII.2006.881815

Filename

1705069