Convergence properties of the frequency-domain block-LMS adaptive algorithm

Author

Li, Xiaohui ; Jenkins, W. Kenneth

Author_Institution

Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA

Volume

2

fYear

1994

fDate

31 Oct-2 Nov 1994

Firstpage

1515

Abstract

The block-based LMS algorithm (BLMS) is an efficient adaptive filtering algorithm aimed at increasing the convergence speed and reducing the computational complexity. The basic principle of the BLMS algorithm is that the filter coefficients remain unchanged during the processing of each data block, and are updated only once per block. The convergence properties of the unconstrained frequency-domain block LMS adaptive algorithm are analyzed. The learning characteristics of the unconstrained case are compared with the constrained case via computer simulation. It is shown that the unconstrained algorithm has a slower convergence rate and smaller stable range of step size than that of the constrained algorithm

Keywords

adaptive filters; adaptive signal processing; computational complexity; convergence of numerical methods; filtering theory; frequency-domain analysis; least mean squares methods; adaptive filtering algorithm; computational complexity; computer simulation; constrained algorithm; convergence properties; convergence rate; convergence speed; frequency-domain block-LMS adaptive algorithm; learning characteristics; stable range; step size; unconstrained frequency-domain algorithm; Adaptive algorithm; Algorithm design and analysis; Computational complexity; Convergence; Convolution; Equations; Filtering algorithms; Filters; Frequency domain analysis; Least squares approximation;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 1994. 1994 Conference Record of the Twenty-Eighth Asilomar Conference on

Conference_Location

Pacific Grove, CA

ISSN

1058-6393

Print_ISBN

0-8186-6405-3

Type

conf

DOI

10.1109/ACSSC.1994.471711

Filename

471711