Computationally efficient iterative refinement techniques for polynomial phase signals

Author

Sando, Simon ; Huang, Dawei ; Pettitt, Tony

Author_Institution

Centre in Stat. Sci. & Ind. Math., Queensland Univ. of Technol., Brisbane, Qld., Australia

fYear

2001

fDate

6/23/1905 12:00:00 AM

Firstpage

421

Lastpage

424

Abstract

Recursive and efficient estimation of polynomial-phase is considered here, with alternatives to the standard Gauss-Newton approach presented. We consider approximations of the likelihood and phase noise distribution to derive recursive approximate maximum likelihood and Bayesian estimators. Monte Carlo simulations indicate that these methods compare favourably with the Gauss-Newton scheme both in terms of computational expense and efficiency thresholds

Keywords

Bayes methods; approximation theory; iterative methods; maximum likelihood estimation; phase estimation; polynomials; recursive estimation; signal processing; Bayesian estimators; Gauss-Newton approach; approximations; iterative refinement techniques; maximum likelihood estimators; polynomial phase signals; recursive estimation; signal processing; Bayesian methods; Least squares approximation; Least squares methods; Maximum likelihood estimation; Monte Carlo methods; Newton method; Phase estimation; Polynomials; Recursive estimation; Signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Statistical Signal Processing, 2001. Proceedings of the 11th IEEE Signal Processing Workshop on

Print_ISBN

0-7803-7011-2

Type

conf

DOI

10.1109/SSP.2001.955312

Filename

955312