Identification of sparse FIR systems using a general quantisation scheme
Authors:
- Boris I. GodoyBGBoris I. Godoy
- Juan C. AgüeroJAJuan C. Agüero
- Rodrigo CarvajalRCRodrigo Carvajal
- Graham C. GoodwinGGGraham C. Goodwin
- Juan I. YuzJYJuan I. Yuz
- 4 December 2013
- journal article
- Published by Taylor & Francis in International Journal of Control
- Vol. 87 (4) , 874-886
Abstract
This paper presents an identification scheme for sparse FIR systems with quantised data. We consider a general quantisation scheme, which includes the commonly deployed static quantiser as a special case. To tackle the sparsity issue, we utilise a Bayesian approach, where an ℓ₁ a priori distribution for the parameters is used as a mechanism to promote sparsity. The general framework used to solve the problem is maximum likelihood (ML). The ML problem is solved by using a generalised expectation maximisation algorithmKeywords
This publication has 40 references indexed in Scilit:
- Sparse Channel Estimation with Zero Tap DetectionIEEE Transactions on Wireless Communications, 2007
- Compressed sensingIEEE Transactions on Information Theory, 2006
- For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solutionCommunications on Pure and Applied Mathematics, 2006
- Inference in Hidden Markov Models2005
- Sparse channel estimation via matching pursuit with application to equalizationIEEE Transactions on Communications, 2002
- Sampling Truncated Normal, Beta, and Gamma DensitiesJournal of Computational and Graphical Statistics, 2001
- Sequential Monte Carlo Methods in Practice2001
- Maximizing Generalized Linear Mixed Model Likelihoods With an Automated Monte Carlo EM AlgorithmJournal of the Royal Statistical Society Series B: Statistical Methodology, 1999
- Normal Variance-Mean Mixtures and z DistributionsInternational Statistical Review, 1982
- Estimation and Control with Quantized Measurements1970