Adaptive parallel/serial sampling mechanisms for particle filtering in dynamic bayesian networks

Monitoring the variables of real world dynamical systems is a difficult task due to their inherent complexity and uncertainty. Particle Filters (PF) perform that task, yielding probability distribution over the unobserved variables. However, they suffer from the curse of dimensionality problem: the...

Descripción completa

Detalles Bibliográficos
Autores: Besada Portas, Eva, Cruz García, Jesús Manuel de la, Plis, Sergey M., Lane, Terran
Tipo de recurso: capítulo de libro
Fecha de publicación:2010
País:España
Institución:Universidad Complutense de Madrid (UCM)
Repositorio:Docta Complutense
Idioma:inglés
OAI Identifier:oai:docta.ucm.es:20.500.14352/45447
Acceso en línea:https://hdl.handle.net/20.500.14352/45447
Access Level:acceso abierto
Palabra clave:004
Computer scienceI
Artificial intelligence
Inteligencia artificial (Informática)
Informática (Informática)
1203.04 Inteligencia Artificial
1203.17 Informática
id ES_5aa24cfd523c9fda3797e958bbbb952e
oai_identifier_str oai:docta.ucm.es:20.500.14352/45447
network_acronym_str ES
network_name_str España
repository_id_str
spelling Adaptive parallel/serial sampling mechanisms for particle filtering in dynamic bayesian networksBesada Portas, EvaCruz García, Jesús Manuel de laPlis, Sergey M.Lane, Terran004Computer scienceIArtificial intelligenceInteligencia artificial (Informática)Informática (Informática)1203.04 Inteligencia Artificial1203.17 InformáticaMonitoring the variables of real world dynamical systems is a difficult task due to their inherent complexity and uncertainty. Particle Filters (PF) perform that task, yielding probability distribution over the unobserved variables. However, they suffer from the curse of dimensionality problem: the necessary number of particles grows exponentially with the dimensionality of the hidden state space. The problem is aggravated when the initial distribution of the variables is not well known, as happens in global localization problems. In this paper we present two new adaptive sampling mechanisms for PFs for systems whose variable dependencies can be factored into a Dynamic Bayesian Network. The novel PFs, developed over the proposed sampling mechanisms, exploit the strengths of other existing PFs. Their adaptive mechanisms 1) modify or establish probabilistic links among the subspaces of hidden variables that are independently explored to build particles consistent with the current measurements and past history, and 2) tune the performance of the new PFs toward the behaviors of several existing PFs. We demonstrate their performance on some complex dynamical system estimation problems, showing that our methods successfully localize and track hidden states, and outperform some of the existing PFs.Springer-Verlag BerlinUniversidad Complutense de Madrid20102010-01-0120102010-01-01book parthttp://purl.org/coar/resource_type/c_3248info:eu-repo/semantics/bookPartapplication/pdfhttps://hdl.handle.net/20.500.14352/45447reponame:Docta Complutenseinstname:Universidad Complutense de Madrid (UCM)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:docta.ucm.es:20.500.14352/454472026-06-02T12:44:21Z
dc.title.none.fl_str_mv Adaptive parallel/serial sampling mechanisms for particle filtering in dynamic bayesian networks
title Adaptive parallel/serial sampling mechanisms for particle filtering in dynamic bayesian networks
spellingShingle Adaptive parallel/serial sampling mechanisms for particle filtering in dynamic bayesian networks
Besada Portas, Eva
004
Computer scienceI
Artificial intelligence
Inteligencia artificial (Informática)
Informática (Informática)
1203.04 Inteligencia Artificial
1203.17 Informática
title_short Adaptive parallel/serial sampling mechanisms for particle filtering in dynamic bayesian networks
title_full Adaptive parallel/serial sampling mechanisms for particle filtering in dynamic bayesian networks
title_fullStr Adaptive parallel/serial sampling mechanisms for particle filtering in dynamic bayesian networks
title_full_unstemmed Adaptive parallel/serial sampling mechanisms for particle filtering in dynamic bayesian networks
title_sort Adaptive parallel/serial sampling mechanisms for particle filtering in dynamic bayesian networks
dc.creator.none.fl_str_mv Besada Portas, Eva
Cruz García, Jesús Manuel de la
Plis, Sergey M.
Lane, Terran
author Besada Portas, Eva
author_facet Besada Portas, Eva
Cruz García, Jesús Manuel de la
Plis, Sergey M.
Lane, Terran
author_role author
author2 Cruz García, Jesús Manuel de la
Plis, Sergey M.
Lane, Terran
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidad Complutense de Madrid
dc.subject.none.fl_str_mv 004
Computer scienceI
Artificial intelligence
Inteligencia artificial (Informática)
Informática (Informática)
1203.04 Inteligencia Artificial
1203.17 Informática
topic 004
Computer scienceI
Artificial intelligence
Inteligencia artificial (Informática)
Informática (Informática)
1203.04 Inteligencia Artificial
1203.17 Informática
description Monitoring the variables of real world dynamical systems is a difficult task due to their inherent complexity and uncertainty. Particle Filters (PF) perform that task, yielding probability distribution over the unobserved variables. However, they suffer from the curse of dimensionality problem: the necessary number of particles grows exponentially with the dimensionality of the hidden state space. The problem is aggravated when the initial distribution of the variables is not well known, as happens in global localization problems. In this paper we present two new adaptive sampling mechanisms for PFs for systems whose variable dependencies can be factored into a Dynamic Bayesian Network. The novel PFs, developed over the proposed sampling mechanisms, exploit the strengths of other existing PFs. Their adaptive mechanisms 1) modify or establish probabilistic links among the subspaces of hidden variables that are independently explored to build particles consistent with the current measurements and past history, and 2) tune the performance of the new PFs toward the behaviors of several existing PFs. We demonstrate their performance on some complex dynamical system estimation problems, showing that our methods successfully localize and track hidden states, and outperform some of the existing PFs.
publishDate 2010
dc.date.none.fl_str_mv 2010
2010-01-01
2010
2010-01-01
dc.type.none.fl_str_mv book part
http://purl.org/coar/resource_type/c_3248
dc.type.openaire.fl_str_mv info:eu-repo/semantics/bookPart
format bookPart
dc.identifier.none.fl_str_mv https://hdl.handle.net/20.500.14352/45447
url https://hdl.handle.net/20.500.14352/45447
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Springer-Verlag Berlin
publisher.none.fl_str_mv Springer-Verlag Berlin
dc.source.none.fl_str_mv reponame:Docta Complutense
instname:Universidad Complutense de Madrid (UCM)
instname_str Universidad Complutense de Madrid (UCM)
reponame_str Docta Complutense
collection Docta Complutense
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869408732139487232
score 15.300724

Similares en LA Referencia