A Robust Algorithm for Joint Sparse Recovery in Presence of Impulsive Noise

Author

Jiadong Shang ; Zulin Wang ; Qin Huang

Author_Institution

Sch. of Electr. & Inf. Eng., Beihang Univ., Beijing, China

Volume

22

Issue

8

fYear

2015

fDate

Aug. 2015

Firstpage

1166

Lastpage

1170

Abstract

This letter presents a robust solution for joint sparse recovery (JSR) under impulsive noise. The unknown measurement noise is endowed with the Student-t distribution, then a novel Bayesian probabilistic model is proposed to describe the JSR problem. To effectively recover the joint row sparse signal, variational Bayes (VB) method is introduced for Bayesian theory based JSR algorithms such that it overcomes the intractable integrations inherent. Simulation results verify that the proposed algorithm significantly outperforms the existing algorithms under impulsive noise.

Keywords

Bayes methods; compressed sensing; Bayesian theory; JSR; Student-t distribution; VB method; impulsive noise; joint sparse recovery; noise measurement; novel Bayesian probabilistic model; robust algorithm; variational Bayes method; Approximation algorithms; Bayes methods; Joints; Noise; Noise measurement; Robustness; Signal processing algorithms; Bayesian inference; impulsive noise; joint sparse recovery; student-t distribution; variational Bayes method;

fLanguage

English

Journal_Title

Signal Processing Letters, IEEE

Publisher

ieee

ISSN

1070-9908

Type

jour

DOI

10.1109/LSP.2014.2387435

Filename

7001173