A variable step size LMS adaptive filtering algorithm based on the number of computing mechanisms

Author

Liu, Fu-cai ; Zhang, Yan-xin ; Wang, Ya-jing

Author_Institution

Key Lab. of Ind. Comput. Control Eng. of Hebei Province, Yanshan Univ., Qin Huang Dao, China

Volume

4

fYear

2009

fDate

12-15 July 2009

Firstpage

1904

Lastpage

1908

Abstract

This paper proposes a novel variable step size LMS algorithm based on the number of computing mechanisms by analyzing the basic principles of the variable step LMS adaptive filtering algorithms. The algorithm establishes a different nonlinear relation-ship between step factor and error signal based on the different sampling time, which not only can control step size by using sampling time indirectly, but also change the parameters to meet the requirement of fast convergence. Compared with the other variable step algorithms, this algorithm is proved to have faster convergence speed and higher stability.

Keywords

adaptive filters; filtering theory; least mean squares methods; signal sampling; adaptive filtering algorithm; error signal; least mean square algorithm; sampling time; step factor; variable step size LMS algorithm; Adaptive filters; Algorithm design and analysis; Convergence; Error correction; Filtering algorithms; Iterative algorithms; Least squares approximation; Sampling methods; Signal processing algorithms; Stability; Adaptive filtering; LMS; Many computing mechanism; Variable step size;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2009 International Conference on

Conference_Location

Baoding

Print_ISBN

978-1-4244-3702-3

Electronic_ISBN

978-1-4244-3703-0

Type

conf

DOI

10.1109/ICMLC.2009.5212187

Filename

5212187