Tracking of linear time-variant systems

Author

Haykin, S. ; Sayed, A.H. ; Zeidler, J. ; Yee, P. ; Wei, P.

Author_Institution

McMaster Univ., Hamilton, Ont., Canada

Volume

2

fYear

1995

fDate

35010

Firstpage

602

Abstract

In this paper we exploit the one-to-one correspondences between the recursive least-squares (RLS) and Kalman variables to formulate extended forms of the RLS algorithm. Two particular forms are considered, one pertaining to a system identification problem and the other to the tracking of a chirped sinusoid in additive noise. For both applications, experiments are presented that demonstrate the tracking optimality of the extended RLS algorithms, compared with the standard RLS and least-mean-squares (LMS) algorithms

Keywords

adaptive Kalman filters; identification; interference (signal); least squares approximations; optimisation; recursive filters; tracking; Kalman variables; RLS algorithm; additive noise; chirped sinusoid; least-mean-squares algorithms; linear adaptive filtering; linear time-variant systems; recursive least-squares variables; system identification problem; tracking optimality; Adaptive filters; Chirp; Convergence; Eigenvalues and eigenfunctions; Filtering algorithms; Kalman filters; Least squares approximation; Resonance light scattering; System identification; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Military Communications Conference, 1995. MILCOM '95, Conference Record, IEEE

Conference_Location

San Diego, CA

Print_ISBN

0-7803-2489-7

Type

conf

DOI

10.1109/MILCOM.1995.483537

Filename

483537