A QR-decomposition LMS-Newton adaptive filtering algorithm with variable convergence factor

Author

de Campos, M.L.R. ; Siqueira, M.G. ; Antoniou, A. ; Wilson, A.N.

Author_Institution

Dept. of Electr. & Comput. Eng., Victoria Univ., BC, Canada

Volume

1

fYear

1993

fDate

19-21 May 1993

Firstpage

350

Abstract

A purely deterministic approach to the LMS (least mean square)-Newton algorithm for adaptive filters is proposed. A QR-decomposition method for solving the algorithm´s equations is described. Simulations using fixed-point arithmetic are provided, which confirm the good numerical characteristics of the method. A variable convergence factor is also discussed which is optimum in the sense that the output a posteriori error is zero

Keywords

Newton method; adaptive filters; convergence of numerical methods; deterministic algorithms; digital arithmetic; least mean squares methods; LMS-Newton adaptive filtering algorithm; QR-decomposition method; fixed-point arithmetic; least mean square; numerical characteristics; variable convergence factor; Adaptive filters; Convergence; Digital signal processing; Educational programs; Equations; Filtering algorithms; Matrices; Resonance light scattering; Signal processing; Signal processing algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications, Computers and Signal Processing, 1993., IEEE Pacific Rim Conference on

Conference_Location

Victoria, BC

Print_ISBN

0-7803-0971-5

Type

conf

DOI

10.1109/PACRIM.1993.407153

Filename

407153