A new class of gradient-based algorithm by using variable step-size technique

Author

Phuvasitkul, Sittisak ; Benjangkaprasert, Chawalit ; Anantrasirichai, Noppin

Author_Institution

Fac. of Eng., King Mongkut´´s Inst. of Technol., Bangkok, Thailand

Volume

1

fYear

2002

fDate

26-30 Aug. 2002

Firstpage

85

Abstract

This paper presents a new class of gradient-based algorithm for second-order IIR adaptive notch filters (ANF); the algorithm is based on least mean p-power (LMP) error criterion. The variable step-size technique is used to detect high convergence speed and high impulse noise robustness. It is proved here that the proposed algorithm has good properties in both cases, when compared with the previous one (Punchalard et al. 2000). Simulation results are presented to demonstrate the effectiveness of the proposed algorithm.

Keywords

IIR filters; adaptive filters; convergence of numerical methods; gradient methods; impulse noise; least mean squares methods; notch filters; ANF; convergence speed; gradient-based algorithm; impulse noise; least mean p-power error criterion; second-order IIR adaptive notch filter; variable step-size technique; Adaptive algorithm; Adaptive filters; Convergence; Frequency estimation; IIR filters; Noise robustness; Power engineering and energy; Signal to noise ratio; Transfer functions; White noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 2002 6th International Conference on

Print_ISBN

0-7803-7488-6

Type

conf

DOI

10.1109/ICOSP.2002.1180990

Filename

1180990