Sparse Signal Recovery Based On A Mixture Distribution

DOI

10.2991/mbdasm-19.2019.11How to use a DOI?

Keywords

sparse signal; variational bayesian; compressive sensing

Abstract

Based on the sparse characteristic of most signals under some transformation, compressive sampling has been brought out to replace the traditional Nyquist theory based sampling. This paper presents a Bayesian method to recovery the original signal from compressed measurements. A hierarchical Bayesian model is built to model the relation between the measurement and the underlying sparse coefficients. To model the sparse property of the signal, a mixture distribution is placed over the coefficient, which enforces the sparsity of the coefficient. The Variational Bayesian theory is applied to the model, and the estimation is obtained. To demonstrate the performance of the algorithm, experiments are carried out on both synthetic sparse signal and image signal.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hongjie Wan
AU  - Haiyun Zhang
PY  - 2019/10
DA  - 2019/10
TI  - Sparse Signal Recovery Based On A Mixture Distribution
BT  - Proceedings of the 2019 International Conference on Mathematics, Big Data Analysis and Simulation and Modelling (MBDASM 2019)
PB  - Atlantis Press
SP  - 47
EP  - 50
SN  - 2352-538X
UR  - https://doi.org/10.2991/mbdasm-19.2019.11
DO  - 10.2991/mbdasm-19.2019.11
ID  - Wan2019/10
ER  -