Fourth-order cumulant based sources number estimation from mixtures of unknown number of sources

Author

Fanglin Gu ; Wei Li ; Wenwu Wang

Author_Institution

Coll. of Electron. Sci. & Eng., Nat. Univ. of Defense Technol., Changsha, China

fYear

2014

fDate

23-25 Oct. 2014

Firstpage

1

Lastpage

6

Abstract

We consider the source number estimation problem in the presence of unknown spatially nonuniform noise and underdetermined mixtures. We develop a new attractive source number estimator by replacing the covariance with the Fourth-Order (FO) cumulant of the observations. Furthermore, a Modified Minimum Description Length (MMDL) principle is proposed to reduce the divergence of the singular values corresponding to noise thereby improving the performance of the estimator. Simulation experiments validate the superiority of the proposed FO cumulant MMDL method to the conventional Minimum Description Length (MDL) method.

Keywords

blind source separation; estimation theory; higher order statistics; BSS; FO cumulant; MMDL principle; blind source separation; fourth-order cumulant; modified minimum description length principle; source number estimation problem; underdetermined mixture; unknown spatially nonuniform noise presence; Arrays; Covariance matrices; Eigenvalues and eigenfunctions; Estimation; Noise; Sensors;

fLanguage

English

Publisher

ieee

Conference_Titel

Wireless Communications and Signal Processing (WCSP), 2014 Sixth International Conference on

Conference_Location

Hefei

Type

conf

DOI

10.1109/WCSP.2014.6992083

Filename

6992083