A cumulant based variable step size adaptive algorithm

Author

Pazaitis, Dimitrios I. ; Constantinides, Anthony G.

Author_Institution

IMEC, Leuven, Belgium

Volume

1

fYear

1997

fDate

2-4 Jul 1997

Firstpage

165

Abstract

An adaptive step size selection rule for least mean squares (LMS) adaptive algorithms is introduced. The step size sequence is adjusted using the kurtosis of the estimation error, thus the performance degradation due to the existence of noise with a strong variance. The proposed algorithm traces changes in the noise statistics and optimally adapts itself, exhibiting a reduced steady state error. Simulation results illustrate the algorithm´s superior performance and confirm its ability to optimally adapt to time varying noise environments. The convergence behavior of the algorithm is also addressed

Keywords

adaptive signal processing; error statistics; higher order statistics; least squares approximations; noise; numerical stability; sequences; time-varying systems; LMS adaptive algorithms; adaptive step size selection; algorithm performance; convergence; cumulant; estimation error kurtosis; least mean squares; noise statistics; noise variance; performance degradation; reduced steady state error; simulation results; stability conditions; step size sequence; time varying noise environments; variable step size adaptive algorithm; Adaptive algorithm; Convergence; Degradation; Educational institutions; Filters; Gaussian noise; Least squares approximation; Mean square error methods; Signal processing algorithms; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Signal Processing Proceedings, 1997. DSP 97., 1997 13th International Conference on

Conference_Location

Santorini

Print_ISBN

0-7803-4137-6

Type

conf

DOI

10.1109/ICDSP.1997.628004

Filename

628004