一种对统计信号处理中缺失数据估计的算法  

An Algorithm of Estimation for Missing Data in Statistical Signal Processing

作　　者：万果果[1] 张元[1] 李建武[1] 谢妞妞[1] 

机构地区：[1]河南工业大学信息科学与工程学院,郑州450001

出　　处：《计算机与数字工程》2010年第10期35-37,105,共4页Computer & Digital Engineering

摘　　要：EM算法是一种有效的应对缺失数据的估计算法,它的应用非常广泛,比如人工智能、模式识别、数理统计、图像处理、信号检测等等。首先对最有效的估计算法极大似然估计进行简单阐述,接下来引出算法的主要内容,在原理上说明了基于迭代理论的似然估计期望最大化算法,讨论EM算法的收敛性,并提出了EM算法的应用,最后简单介绍了几种EM改进型算法。EM algorithm is an effective estimation algorithm for missing data and has a wide application,such as artificial intelligence,pattern recognition,statistics,image processing,signal detection and so on.This paper simplify describes the most efficient estimation algorithm,that is ML.The main content has presented,in principle explains likelihood expectation maximization algorithm based on iterative theory,discusses the convergence of EM algorithm,proposes the application of EM algorithm,and simply introduced several EM algorithms.

关 键 词：ML EM 迭代 EM改进算法 

分 类 号：TN911.72[电子电信—通信与信息系统]