Statistical analysis of the LMS algorithm with a zero-memory nonlinearity after the adaptive filter

Author

Costa, Márcio H. ; Bermudez, José C M ; Bershad, Neil J.

Author_Institution

Biomed. Instrum. Group, Univ. Catolica de Pelotas, Pelotas, Brazil

Volume

3

fYear

1999

fDate

15-19 Mar 1999

Firstpage

1661

Abstract

This paper presents a statistical analysis of the least mean square (LMS) algorithm when a zero-memory nonlinearity appears at the adaptive filter output. The nonlinearity is modelled by a scaled error function. Deterministic nonlinear recursions are derived for the mean weight and mean square error (MSE) behavior for white Gaussian inputs and slow adaptation. Monte Carlo simulations show excellent agreement with the behavior predicted by the theoretical models. The analytical results show that a small nonlinear effect has a significant impact on the converged MSE

Keywords

Monte Carlo methods; adaptive filters; adaptive signal processing; digital simulation; filtering theory; least mean squares methods; nonlinear filters; statistical analysis; LMS algorithm; Monte Carlo simulations; adaptive filter; converged MSE; deterministic nonlinear recursions; least mean square; mean square error; mean weight; nonlinear effect; scaled error function; slow adaptation; statistical analysis; white Gaussian inputs; zero-memory nonlinearity; Adaptive filters; Biomedical computing; Biomedical engineering; Biomedical measurements; Computer errors; Electronic mail; Equations; Least squares approximation; Predictive models; Statistical analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on

Conference_Location

Phoenix, AZ

ISSN

1520-6149

Print_ISBN

0-7803-5041-3

Type

conf

DOI

10.1109/ICASSP.1999.756311

Filename

756311