The combination of genetic algorithm and variable step-size algorithm for adaptive IIR notch filter

Benjangkaprasert, C.; Jorphochaudom, S.; Chompoo, S.; Sangaroon, O.; Janchitrapongvej, K.

doi:10.1109/ICNNSP.2003.1279315

The combination of genetic algorithm and variable step-size algorithm for adaptive IIR notch filter

Author(s)

Benjangkaprasert, C.

Jorphochaudom, S.

Chompoo, S.

Sangaroon, O.

Janchitrapongvej, K.

Date Issued

December 1, 2003

Type

Conference Paper

DOI

10.1109/ICNNSP.2003.1279315

Abstract

In this paper, the combination algorithm for a second-order adaptive IIR notch filter is presented. The proposed algorithm is based on the genetic algorithm as an initial stage of adaptation process, as we approach the optimum step-size parameter, we using the new variable step-size algorithm. By this technique, the new algorithm achieves the optimum step-size parameter of the filter coefficient for an adaptive IIR notch filter. The results of computer simulation show that the new algorithm provides a good performance such as fast convergence rate, low mean square error and noise robustness. In addition, the new algorithm is also applied to cancel 50-Hz power line interference in the recording of electrocardiograms signal. © 2003 IEEE.

Citation

Proceedings of 2003 International Conference on Neural Networks and Signal Processing Icnnsp 03, 1, 480-483, 2003