FINITE DIMENSIONAL OPTIMAL FILTERS FOR A CLASS OF ITO-PROCESSES WITH JUMPING PARAMETERS.

被引：57

作者：

Bjork, T.

机构：

来源：

Stochastics | 1980年 / 4卷 / 02期

关键词：

PROBABILITY - Random Processes;

D O I：

10.1080/17442508008833160

中图分类号：

学科分类号：

摘要：

A finite state Markov process theta , feeding the coefficients of a linear Ito-equation with state xi is considered. The theta -process is observed in white noise, and it is shown that the optimal nonlinear filter for xi is of finite dimension. Finite dimensional equations for optimal prediction and smoothing are derived.

引用

页码：167 / 183