DocumentCode
3315400
Title
Frequency-weighting model identification with an adaptive ARMA lattice filter
Author
Haseyama, Miki ; Nagai, Nobuo ; Miki, Nobuhiro
Author_Institution
Res. Inst. for Electron. Sci., Hokkaido Univ., Sapporo, Japan
fYear
1992
fDate
17-19 Sep 1992
Firstpage
543
Lastpage
546
Abstract
A method for model identification with frequency weighting using an adaptive autoregressive moving average (ARMA) lattice filter is proposed. Based on this algorithm, the accuracy of the model identification can be higher in focused frequency bands than in other bands. The proposed algorithm contains two algorithms. One is a realization algorithm of an ARMA lattice filter with frequency weighting. The other is an algorithm which computes ARMA parameters from the coefficients of the ARMA lattice filter. Simulation results demonstrate that the proposed filter has low sensitivity
Keywords
adaptive filters; identification; signal processing; statistical analysis; time series; adaptive ARMA lattice filter; frequency weighting; model identification; Adaptive filters; Algorithm design and analysis; Computational modeling; Digital signal processing; Frequency; Lattices; Signal processing algorithms;
fLanguage
English
Publisher
ieee
Conference_Titel
Systems Engineering, 1992., IEEE International Conference on
Conference_Location
Kobe
Print_ISBN
0-7803-0734-8
Type
conf
DOI
10.1109/ICSYSE.1992.236969
Filename
236969
Link To Document