A comparison of sparse signal recovery and approximate bayesian inference methods for sparse channel estimation

Thesis Type: Postgraduate

Institution Of The Thesis: Orta Doğu Teknik Üniversitesi, Faculty of Engineering, Department of Electrical and Electronics Engineering, Turkey

Approval Date: 2015

Student: AYLA UÇAR



The concept of sparse representation is one of the central methodologies of modern signal processing and it has had significant impact on numerous application fields such as communications and imaging. Sparsity expresses the idea that the information rate of a continuous time signal may be much smaller than suggested by its bandwidth, or that a discrete time signal depends on a number of degrees of freedom which is comparably much smaller than its (finite) length. With recent advances in sparse signal estimation, some new estimation techniques have emerged yielding more accurate sparse estimates than the traditional methods. The main goal of this thesis is to analyse the performance of recently proposed sparse signal estimation methods on the problem of sparse channel estimation. In this thesis, a literature survey has been conducted to examine the approaches for estimating the sparse channels, then greedy pursuit algorithms, convex relaxation and an approximate Bayesian inference method, namely expectation propagation method, are comparatively studied