Summary
the 2014 International Symposium on Nonlinear Theory and its Applications
2014
Session Number:D1L-B
Session:
Number:D1L-B5
A fast converging improved NLMS algorithm for spares system’s identification
Shihab Jimaa, Luis Weruaga, Ammar Sadiq, Hamad Alhammadi, Tetsuya Shimamura,
pp.676-679
Publication Date:2014/9/14
Online ISSN:2188-5079
Summary:
The Least Mean Square (LMS) and its variant the Normalized LMS (NLMS) adaptive algorithms are widely used in system identification, however they are better in identifying non sparse systems. Hence, in order to improve the performance of the LMS based system identification of sparse systems, an improved adaptive NLMS algorithm is proposed which utilizes the sparsity property of such systems. A sparse system is one whose impulse response consists of many near-zero coefficients. In this paper, a comparative analysis of the LMS, NLMS and the proposed improved NLMS algorithms, to identify an unknown sparse system, is presented. Simulation results demonstrates that the proposed improved NLMS algorithm provides significant performance gains in comparison to the conventional LMS and NLMS algorithms in both convergence rate and steady state behavior.