Convergence Analysis of Recursive Maximum Likelihood Estimation for Symbol Timing Recovery over AWGN Channels

Autor:	Wen-shan Wang, 王文山
Rok vydání:	1996
Druh dokumentu:	學位論文 ; thesis
Popis:	84 The problem of estimating symbol timing for PAM signals over additive white Gaussian noise (AWGN) channels is considered. Conventional approaches to this problem are usually based on maximization of likelihood functions. In \cite{Won-Lu}, a recursive maximum likelihood estimation (RMLE) algorithm has been proposed suitable for timing recovery over AWGN channels. However, details on convergence analysis of the RMLE algorithm has not been touched yet. In this thesis, we investigate the asymptotic behavior of the RMLE algorithm, including convergence with probability one (w.p.1) and asymptotic distribution. The convergence problem of the RMLE algorithm can be effectively reduced to the stability problem of stationary points of an associated deterministic ordinary differential equation (ODE). Furthermore, we show that the RMLE algorithm is consistent and asymptotically efficient.
Databáze:	Networked Digital Library of Theses & Dissertations
Externí odkaz:	http://ndltd.ncl.edu.tw/handle/77270170792842330779 Zobrazit plný text záznamu