Title :
A variable step-size transform-domain LMS algorithm based on minimum mean-square deviation for autoregressive process
Author :
Shengkui Zhao ; Zhihong Man ; Jones, Douglas L. ; Suiyang Khoo
Author_Institution :
Adv. Digital Sci. Center (ADSC), Singapore, Singapore
Abstract :
In this paper, we investigate the optimal variable step-size approach for the transform-domain least-mean-square (TDLMS) algorithm to achieve fast convergence speed and low steady-state misadjustment. By minimizing the mean-square deviation (MSD) between the filter weight vector and the true vector, we derive and approximate the optimal variable step-size for the TDLMS algorithm given autoregressive (AR) process as input signals. The resulted variable step-size has simple formulation and easily-setting parameters. Computer simulation is demonstrated in the framework of adaptive system modeling with a fourth-order AR input process. The overall performance are observed superior to the existing popular variable step-size approaches of the TDLMS algorithm.
Keywords :
adaptive filters; autoregressive processes; least mean squares methods; transforms; vectors; MSD; TDLMS algorithm; adaptive filtering; adaptive system modeling; autoregressive process; convergence speed; filter weight vector-true vector mean-square deviation minimization; fourth-order AR input process; minimum mean-square deviation; optimal variable step-size approach; steady-state misadjustment; transform-domain least-mean-square algorithm; variable step-size transform-domain LMS algorithm; Approximation algorithms; Convergence; Least squares approximations; Signal processing algorithms; Steady-state; Time-domain analysis; Vectors;
Conference_Titel :
Industrial Electronics and Applications (ICIEA), 2013 8th IEEE Conference on
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4673-6320-4
DOI :
10.1109/ICIEA.2013.6566507