Title :
On the Cramér-Rao Bound for Estimating the Mixing Matrix in Noisy Sparse Component Analysis
Author :
Zayyani, Hadi ; Babaie-zadeh, Masoud ; Haddadi, Farzan ; Jutten, Christian
Author_Institution :
Electr. Eng. Dept., Sharif Univ. of Technol., Tehran
fDate :
6/30/1905 12:00:00 AM
Abstract :
In this letter, we address the theoretical limitations in estimating the mixing matrix in noisy sparse component analysis (SCA) for the two-sensor case. We obtain the Cramer-Rao lower bound (CRLB) error estimation of the mixing matrix. Using the Bernouli-Gaussian (BG) sparse distribution, and some simple assumptions, an approximation of the Fisher information matrix (FIM) is calculated. Moreover, this CRLB is compared to some of the main methods of mixing matrix estimation in the literature.
Keywords :
blind source separation; error statistics; sparse matrices; Bernouli-Gaussian sparse distribution; Cramer-Rao bound; Fisher information; blind source separation; error estimation; mixing matrix estimation; noisy sparse component analysis; two-sensor case; Blind source separation; Error analysis; Estimation theory; Histograms; Independent component analysis; Information analysis; Laplace equations; Mathematical model; Source separation; Sparse matrices; Blind source separation; Cramér–Rao bound; mixing matrix estimation; sparse component analysis;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2008.2003989
