DocumentCode
1744157
Title
The relationship between state space subspace identification methods and the EM method
Author
Gibson, Stuart ; Ninness, Brett
Author_Institution
Dept. of Electr. & Comput. Eng., Newcastle Univ., NSW, Australia
Volume
3
fYear
2000
fDate
2000
Firstpage
2415
Abstract
This paper exposes a close connection between subspace-type estimates and single iterates of the expectation maximisation method for maximum likelihood (ML) estimation. A key implication of this is that it suggests a means by which ML estimates for MIMO systems may be computed in a numerically robust and straightforward manner
Keywords
MIMO systems; least squares approximations; maximum likelihood estimation; state-space methods; EM algorithm; MIMO systems; expectation maximisation method; maximum likelihood estimation; parameter estimation; state space; subspace identification; Kalman filters; MIMO; Maximum likelihood estimation; Parameter estimation; State estimation; State-space methods; Stochastic processes; Technological innovation; White noise; Zinc;
fLanguage
English
Publisher
ieee
Conference_Titel
Decision and Control, 2000. Proceedings of the 39th IEEE Conference on
Conference_Location
Sydney, NSW
ISSN
0191-2216
Print_ISBN
0-7803-6638-7
Type
conf
DOI
10.1109/CDC.2000.914161
Filename
914161
Link To Document