Title :
On the solution of circular and noncircular complex KLD-ICA in the presence of noise
Author :
Loesch, Benedikt ; Yang, Bin
Author_Institution :
Inst. of Signal Process. & Syst. Theor., Univ. of Stuttgart, Stuttgart, Germany
Abstract :
This paper aims at studying the solution of linear independent component analysis (ICA) based on Kullback-Leibler divergence (KLD) for a linear noisy mixing model in the determined case. The derivation is done using a perturbation analysis valid for small noise variance. We study the noncircular complex and the circular complex case. We show that for a wide range of both the shape parameter and the noncircularity index of the generalized Gaussian distribution (GGD), the signal-to-interference-plus-noise ratio (SINR) of KLD-based ICA is close to that of linear minimum mean squared error (MMSE) estimation.
Keywords :
Gaussian distribution; blind source separation; independent component analysis; interference (signal); least mean squares methods; perturbation techniques; GGD; Kullback-Leibler divergence; MMSE estimation; SINR; blind source separation; circular complex KLD-ICA; generalized Gaussian distribution; linear independent component analysis; linear minimum mean squared error estimation; linear noisy mixing model; noise presence; noncircular complex KLD-ICA; perturbation analysis; signal-to-interference-plus-noise ratio; small noise variance; Independent component analysis; Indexes; Interference; Noise measurement; Signal to noise ratio; Taylor series; Blind source separation; Independent component analysis; Kullback-Leibler divergence; Minimum mean square error; Perturbation analysis; noncircular complex;
Conference_Titel :
Signal Processing Conference (EUSIPCO), 2012 Proceedings of the 20th European
Print_ISBN :
978-1-4673-1068-0
