Detail publikačního výsledku

Sequential Monte Carlo estimation of transition probabilities in mixture filtering problems

PAPEŽ, M.

Originální název

Sequential Monte Carlo estimation of transition probabilities in mixture filtering problems

Anglický název

Sequential Monte Carlo estimation of transition probabilities in mixture filtering problems

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

Physical systems switching between various working regimes are often encountered in practical applications. However, transition probabilities, according to which a system switches from the current regime to another one, are commonly designed as a priori known parameters, and their misspecification can degrade the performance of the algorithms filtering (or estimating) latent variables of the system. To overcome the misspecification, the present paper proposes a novel Sequential Monte Carlo procedure for estimating the transition probabilities. More specifically, it extends the concept of Rao-Blackwellization to the Dirichlet distribution, which represents the model of these probabilities. The experiments show that the proposed technique outperforms some of the classical methods in terms of the estimation precision and also the precision stability.

Anglický abstrakt

Physical systems switching between various working regimes are often encountered in practical applications. However, transition probabilities, according to which a system switches from the current regime to another one, are commonly designed as a priori known parameters, and their misspecification can degrade the performance of the algorithms filtering (or estimating) latent variables of the system. To overcome the misspecification, the present paper proposes a novel Sequential Monte Carlo procedure for estimating the transition probabilities. More specifically, it extends the concept of Rao-Blackwellization to the Dirichlet distribution, which represents the model of these probabilities. The experiments show that the proposed technique outperforms some of the classical methods in terms of the estimation precision and also the precision stability.

Klíčová slova

Sequential Monte Carlo methods, Rao-Blackwellized particle filter, probabilistic mixtures, switching state-space models

Klíčová slova v angličtině

Sequential Monte Carlo methods, Rao-Blackwellized particle filter, probabilistic mixtures, switching state-space models

Autoři

PAPEŽ, M.

Rok RIV

2017

Vydáno

04.08.2016

Nakladatel

International Society of Information Fusion

Místo

Heidelberg

ISBN

978-1-5090-2012-6

Kniha

Proceedings of the 19th International Conference on Information Fusion, FUSION 2016

Strany od

1063

Strany do

1070

Strany počet

8

URL

http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7528003&isnumber=7527857

BibTex

@inproceedings{BUT127524,
  author="Milan {Papež}",
  title="Sequential Monte Carlo estimation of transition probabilities in mixture filtering problems",
  booktitle="Proceedings of the 19th International Conference on Information Fusion, FUSION 2016",
  year="2016",
  pages="1063--1070",
  publisher="International Society of Information Fusion",
  address="Heidelberg",
  isbn="978-1-5090-2012-6",
  url="http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7528003&isnumber=7527857"
}