Recursive algorithm for state space spectrum estimation

Author

Edmonson, William ; Alexander, Winser

Author_Institution

City Coll., City Univ. of New York, NY, USA

fYear

1990

fDate

10-12 Oct. 1990

Firstpage

265

Lastpage

269

Abstract

A new method is proposed for implementing an adaptive state space filter. This method is based upon the matrix minimum principle of optimal control theory. The adaptive state space filter is a two part algorithm. The first part is a recursive algorithm for optimizing a predictor matrix which describes the transformation from past data to future data. A matrix steepest descent algorithm is developed for use as the update equation in optimizing the predictor matrix. The second part determines the system parameters from the optimized predictor matrix by the decomposition of the predictor matrix and the use of projection techniques. The result is the estimation of the innovations realization which can further describe the spectral characteristics of the model.<>

Keywords

adaptive filters; filtering and prediction theory; matrix algebra; optimisation; recursive functions; spectral analysis; state-space methods; adaptive state space filter; decomposition; matrix minimum principle; matrix steepest descent algorithm; optimal control theory; optimisation; predictor matrix; projection; recursive algorithm; state space spectrum estimation; Adaptive filters; Equations; IIR filters; Least squares approximation; Matrix decomposition; Noise measurement; Particle measurements; Spectral analysis; State-space methods; Technological innovation;

fLanguage

English

Publisher

ieee

Conference_Titel

Spectrum Estimation and Modeling, 1990., Fifth ASSP Workshop on

Conference_Location

Rochester, NY, USA

Type

conf

DOI

10.1109/SPECT.1990.205588

Filename

205588