liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Estimating State-Space Models in Innovations Form using the Expectation Maximisation Algorithm
University of Newcastle, Australia.
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
University of Newcastle, Australia.
2010 (English)In: Proceedings of the 49th IEEE Conference on Decision and Control, 2010, 5524-5529 p.Conference paper (Refereed)
Abstract [en]

The expectation maximisation (EM) algorithm has proven to be effective for a range of identification problems. Unfortunately, the way in which the EM algorithm has previously been applied has proven unsuitable for the commonly employed innovations form model structure. This paper addresses this problem, and presents a previously unexamined method of EM algorithm employment. The results are profiled, which indicate that a hybrid EM/gradient-search technique may in some cases outperform either a pure EM or a pure gradient-based search approach.

Place, publisher, year, edition, pages
2010. 5524-5529 p.
Keyword [en]
Maximum likelihood, System identification, Expectation maximisation, Innovation model
National Category
Control Engineering
URN: urn:nbn:se:liu:diva-63595DOI: 10.1109/CDC.2010.5717145ISBN: 978-1-4244-7745-6OAI: diva2:380830
49th IEEE Conference on Decision and Control, Atlanta, GA, USA, 15-17 December, 2010
Swedish Research CouncilSwedish Foundation for Strategic Research
Available from: 2010-12-22 Created: 2010-12-22 Last updated: 2013-09-23

Open Access in DiVA

No full text

Other links

Publisher's full textRelated report

Search in DiVA

By author/editor
Schön, Thomas
By organisation
Automatic ControlThe Institute of Technology
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 79 hits
ReferencesLink to record
Permanent link

Direct link