Unified derivation and initial convergence of three prewindowed fast transversal recursive least squares algorithms

Author

Wang, Jin-der

Author_Institution

AT&T Data Commun., Middletown, NJ, USA

Volume

36

Issue

7

fYear

1988

fDate

7/1/1988 12:00:00 AM

Firstpage

1091

Lastpage

1096

Abstract

Three prewindowed transversal fast RLS (recursive least-squares) algorithms, the FK (fast Kalman), FAEST (fast a posteriori estimation sequential technique), and FTF (fast transversal filter) algorithms, are derived in a unified approach. It is shown that their mathematical equivalence can be established only by properly choosing their initial conditions. It is confirmed by computer simulations that the choice of initial conditions and the algorithmic forgetting factor could strongly affect the speed of the initial convergence

Keywords

convergence; digital simulation; estimation theory; filtering and prediction theory; least squares approximations; FAEST; FK; FTF; RLS; algorithmic forgetting factor; computer simulations; fast Kalman; fast a posteriori estimation sequential technique; fast transversal filter; initial convergence; prewindowed fast transversal recursive least squares algorithms; unified derivation; Circuits; Computer simulation; Conformal mapping; Controllability; Convergence; Filters; Image processing; Kalman filters; MIMO; Observability; Recursive estimation; Resonance light scattering; State-space methods; Testing; Transversal filters;

fLanguage

English

Journal_Title

Acoustics, Speech and Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

0096-3518

Type

jour

DOI

10.1109/29.1635

Filename

1635