Presentation	2001/3/10 On-line EM Algorithm for Identification of a Linear Non-Stationary Dynamical System Mitsuru Oka, Shigeyuki Oba, Shin Ishii,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	We propose an identification method for state-space models that change over time. Internal states of the system are inferred by the Kalman filter method, and the system identification is done by an on-line EM algorithm. This method identifies the time-varying system in a successive manner. The merits of our method are; (1) the computation time is much smaller than that based on the conventional off-line EM algorithm; (2) it needs small storage capacity because there is no need to keep the past data.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	State-space model / System identification / Kalman filter / Maximum likelihood estimation / On-line EM algorithm
Paper #	NLP2000-172
Date of Issue

Conference Information
Committee	NLP
Conference Date	2001/3/10(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Nonlinear Problems (NLP)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	On-line EM Algorithm for Identification of a Linear Non-Stationary Dynamical System
Sub Title (in English)
Keyword(1)	State-space model
Keyword(2)	System identification
Keyword(3)	Kalman filter
Keyword(4)	Maximum likelihood estimation
Keyword(5)	On-line EM algorithm
1st Author's Name	Mitsuru Oka
1st Author's Affiliation	Nara Institute of Science and Technology()
2nd Author's Name	Shigeyuki Oba
2nd Author's Affiliation	Nara Institute of Science and Technology
3rd Author's Name	Shin Ishii
3rd Author's Affiliation	Nara Institute of Science and Technology
Date	2001/3/10
Paper #	NLP2000-172
Volume (vol)	vol.100
Number (no)	681
Page	pp.pp.-
#Pages	8
Date of Issue