Bank filters for ML parameter estimation via the expectation-maximization algorithm: the continuous-time case

Author

Charalambous, Charalambos D. ; Logothetis, Andrew ; Elliott, Robert J.

Author_Institution

Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada

Volume

2

fYear

1998

fDate

16-18 Dec 1998

Firstpage

2317

Abstract

In this paper we consider continuous-time partially observed systems in which the parameters are unknown. We employ conditional moment generating functions of integrals and stochastic integrals to derive new maximum-likelihood (ML) parameter estimates which are required in the implementation of the expectation-maximization algorithm. Each parameter is estimated by a bank of Kalman filters consisting of four statistics: two are the Kalman filter statistics while the remaining two have the structure of the Kalman filter driven by the innovations process

Keywords

Kalman filters; continuous time systems; maximum likelihood estimation; probability; Kalman filters; continuous-time systems; expectation-maximization algorithm; maximum-likelihood estimation; parameter estimation; partially observed systems; probability; stochastic integrals; Expectation-maximization algorithms; Filter bank; Kalman filters; Maximum likelihood estimation; Parameter estimation; Probability; State estimation; Statistics; Stochastic processes; Technological innovation;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 1998. Proceedings of the 37th IEEE Conference on

Conference_Location

Tampa, FL

ISSN

0191-2216

Print_ISBN

0-7803-4394-8

Type

conf

DOI

10.1109/CDC.1998.758690

Filename

758690