Adaptive modelling of sparse systems

Author

Chia, Bock-Sim ; Etter, Delores

Author_Institution

Dept. of Electr. & Comput. Eng., New Mexico Univ., Albuquerque, NM, USA

fYear

1990

fDate

3-6 Apr 1990

Firstpage

2447

Abstract

An algorithm for modeling sparse impulse systems is proposed. The method works well for both sparse and nonsparse systems. However, it offers significant savings in computational costs when the system is nonsparse. The approach used in this method is to determine all the delay positions of the unknown system simultaneously and then use an LMS (least-mean-square) algorithm to adapt the gains at delays with significant impulse response, in parallel. This method is the parallel implementation of Y.F. Chen and D.M. Etter (1989), and hence will work faster than serial implementation

Keywords

adaptive filters; digital filters; filtering and prediction theory; least squares approximations; modelling; parallel algorithms; FIR systems; LMS algorithm; adaptive modelling; algorithm; delay positions; impulse response; least mean square algorithm; nonsparse systems; parallel implementation; sparse impulse systems; Adaptive systems; Computational efficiency; Delay; Delay estimation; Filters; Least squares approximation; Modeling; Partitioning algorithms; Sampling methods; White noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.116085

Filename

116085