Dynamic ensemble selection for quantification tasks

Ensembles are among the most effective and successful methods for almost all supervised tasks. Not long ago, an ensemble approach has been proposed for quantification learning The idea of such method is to exploit the prior knowledge about quantification tasks, building ensembles in which diversity...

Descripción completa

Detalles Bibliográficos
Autores: Pérez Gallego, Pablo José, Castaño Gutiérrez, Alberto|||0000-0002-3946-5820, Quevedo Pérez, José Ramón|||0000-0001-7211-4312, Coz Velasco, Juan José del|||0000-0002-4288-3839
Tipo de recurso: artículo
Fecha de publicación:2018
País:España
Institución:Universidad de Oviedo (UNIOVI)
Repositorio:RUO. Repositorio Institucional de la Universidad de Oviedo
Idioma:inglés
OAI Identifier:oai:digibuo.uniovi.es:10651/46050
Acceso en línea:http://hdl.handle.net/10651/46050
https://dx.doi.org/10.1016/j.inffus.2018.01.001
Access Level:acceso abierto
Palabra clave:Quantification
Ensembles
Dynamic Ensemble Selection
id ES_8b4e9bfa8910d2aff79a6474b0b79141
oai_identifier_str oai:digibuo.uniovi.es:10651/46050
network_acronym_str ES
network_name_str España
repository_id_str
spelling Dynamic ensemble selection for quantification tasksPérez Gallego, Pablo JoséCastaño Gutiérrez, Alberto|||0000-0002-3946-5820Quevedo Pérez, José Ramón|||0000-0001-7211-4312Coz Velasco, Juan José del|||0000-0002-4288-3839QuantificationEnsemblesDynamic Ensemble SelectionEnsembles are among the most effective and successful methods for almost all supervised tasks. Not long ago, an ensemble approach has been proposed for quantification learning The idea of such method is to exploit the prior knowledge about quantification tasks, building ensembles in which diversity is achieved by training each model with a different distribution. These training samples are generated taking into account the expected drift in class distribution. This paper extends this method proposing three new quantifier selection criteria particularly devised for quantification problems, where two of them are defined for dynamic ensemble selection. The experiments demonstrate that, in many cases, these selection functions outperform straightforward approaches, like averaging all models and using quantification accuracy to prune the ensemble. Moreover, the results show that performance heavily depends on the combination of the base quantification algorithm and the selection measureThis research has been funded by MINECO (the Spanish Ministerio de Econom a y Competitividad) and FEDER (Fondo Europeo de Desarrollo Regional), grant TIN2015-65069-C2-2-R (MINECO/FEDER)Elsevier20182018-01-01journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articlehttp://hdl.handle.net/10651/46050https://dx.doi.org/10.1016/j.inffus.2018.01.001reponame:RUO. Repositorio Institucional de la Universidad de Oviedoinstname:Universidad de Oviedo (UNIOVI)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:digibuo.uniovi.es:10651/460502026-06-07T06:38:51Z
dc.title.none.fl_str_mv Dynamic ensemble selection for quantification tasks
title Dynamic ensemble selection for quantification tasks
spellingShingle Dynamic ensemble selection for quantification tasks
Pérez Gallego, Pablo José
Quantification
Ensembles
Dynamic Ensemble Selection
title_short Dynamic ensemble selection for quantification tasks
title_full Dynamic ensemble selection for quantification tasks
title_fullStr Dynamic ensemble selection for quantification tasks
title_full_unstemmed Dynamic ensemble selection for quantification tasks
title_sort Dynamic ensemble selection for quantification tasks
dc.creator.none.fl_str_mv Pérez Gallego, Pablo José
Castaño Gutiérrez, Alberto|||0000-0002-3946-5820
Quevedo Pérez, José Ramón|||0000-0001-7211-4312
Coz Velasco, Juan José del|||0000-0002-4288-3839
author Pérez Gallego, Pablo José
author_facet Pérez Gallego, Pablo José
Castaño Gutiérrez, Alberto|||0000-0002-3946-5820
Quevedo Pérez, José Ramón|||0000-0001-7211-4312
Coz Velasco, Juan José del|||0000-0002-4288-3839
author_role author
author2 Castaño Gutiérrez, Alberto|||0000-0002-3946-5820
Quevedo Pérez, José Ramón|||0000-0001-7211-4312
Coz Velasco, Juan José del|||0000-0002-4288-3839
author2_role author
author
author
dc.subject.none.fl_str_mv Quantification
Ensembles
Dynamic Ensemble Selection
topic Quantification
Ensembles
Dynamic Ensemble Selection
description Ensembles are among the most effective and successful methods for almost all supervised tasks. Not long ago, an ensemble approach has been proposed for quantification learning The idea of such method is to exploit the prior knowledge about quantification tasks, building ensembles in which diversity is achieved by training each model with a different distribution. These training samples are generated taking into account the expected drift in class distribution. This paper extends this method proposing three new quantifier selection criteria particularly devised for quantification problems, where two of them are defined for dynamic ensemble selection. The experiments demonstrate that, in many cases, these selection functions outperform straightforward approaches, like averaging all models and using quantification accuracy to prune the ensemble. Moreover, the results show that performance heavily depends on the combination of the base quantification algorithm and the selection measure
publishDate 2018
dc.date.none.fl_str_mv 2018
2018-01-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10651/46050
https://dx.doi.org/10.1016/j.inffus.2018.01.001
url http://hdl.handle.net/10651/46050
https://dx.doi.org/10.1016/j.inffus.2018.01.001
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
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
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
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:RUO. Repositorio Institucional de la Universidad de Oviedo
instname:Universidad de Oviedo (UNIOVI)
instname_str Universidad de Oviedo (UNIOVI)
reponame_str RUO. Repositorio Institucional de la Universidad de Oviedo
collection RUO. Repositorio Institucional de la Universidad de Oviedo
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869412799265898496
score 15,300719

Similares en LA Referencia