DocumentCode
567690
Title
Online EM algorithm for jump Markov systems
Author
Fritsche, Carsten ; Özkan, Emre ; Gustafsson, Fredrik
Author_Institution
Dept. of Electr. Eng., Linkoping Univ., Linkoping, Sweden
fYear
2012
fDate
9-12 July 2012
Firstpage
1941
Lastpage
1946
Abstract
The Expectation-Maximization (EM) algorithm in combination with particle filters is a powerful tool that can solve very complex problems, such as parameter estimation in general nonlinear non-Gaussian state space models. We here apply the recently proposed online EM algorithm to parameter estimation in jump Markov models, that contain both continuous and discrete states. In particular, we focus on estimating process and measurement noise distributions being modeled as mixtures of members from the exponential family.
Keywords
Gaussian processes; Markov processes; expectation-maximisation algorithm; parameter estimation; particle filtering (numerical methods); expectation-maximization algorithm; jump Markov systems; nonlinear non-Gaussian state space models; online EM algorithm; parameter estimation; particle filters; Approximation algorithms; Approximation methods; Estimation; Hidden Markov models; Markov processes; Monte Carlo methods; Signal processing algorithms;
fLanguage
English
Publisher
ieee
Conference_Titel
Information Fusion (FUSION), 2012 15th International Conference on
Conference_Location
Singapore
Print_ISBN
978-1-4673-0417-7
Electronic_ISBN
978-0-9824438-4-2
Type
conf
Filename
6290538
Link To Document