Feature selection with simple ANN ensembles
- Autores
- Izetta Riera, C. Javier; Granitto, Pablo Miguel
- Año de publicación
- 2009
- Idioma
- inglés
- Tipo de recurso
- documento de conferencia
- Estado
- versión publicada
- Descripción
- Feature selection is a well-known pre-processing technique, commonly used with high-dimensional datasets. Its main goal is to discard useless or redundant variables, reducing the dimensionality of the input space, in order to increase the performance and interpretability of models. In this work we introduce the ANN-RFE, a new technique for feature selection that combines the accurate and time-e cient RFE method with the strong discrimination capabilities of ANN ensembles. In particular, we discuss two feature importance metrics that can be used with ANN-RFE: the shu ing and dE metrics. We evaluate the new method using an arti cial example and ve real-world wide datasets, including gene-expression data. Our results suggest that both metrics have equivalent capabilities for the selection of informative variables. ANNRFE seems to produce overall results that are equivalent to previous e cient methods, but can be more accurate on particular datasets.
Presentado en el X Workshop Agentes y Sistemas Inteligentes
Red de Universidades con Carreras en Informática (RedUNCI) - Materia
-
Ciencias Informáticas
Process metrics
feature selection - Nivel de accesibilidad
- acceso abierto
- Condiciones de uso
- http://creativecommons.org/licenses/by-nc-sa/2.5/ar/
- Repositorio
- Institución
- Universidad Nacional de La Plata
- OAI Identificador
- oai:sedici.unlp.edu.ar:10915/20884
Ver los metadatos del registro completo
id |
SEDICI_545f5f70fbc692acafe123c8fac12dcc |
---|---|
oai_identifier_str |
oai:sedici.unlp.edu.ar:10915/20884 |
network_acronym_str |
SEDICI |
repository_id_str |
1329 |
network_name_str |
SEDICI (UNLP) |
spelling |
Feature selection with simple ANN ensemblesIzetta Riera, C. JavierGranitto, Pablo MiguelCiencias InformáticasProcess metricsfeature selectionFeature selection is a well-known pre-processing technique, commonly used with high-dimensional datasets. Its main goal is to discard useless or redundant variables, reducing the dimensionality of the input space, in order to increase the performance and interpretability of models. In this work we introduce the ANN-RFE, a new technique for feature selection that combines the accurate and time-e cient RFE method with the strong discrimination capabilities of ANN ensembles. In particular, we discuss two feature importance metrics that can be used with ANN-RFE: the shu ing and dE metrics. We evaluate the new method using an arti cial example and ve real-world wide datasets, including gene-expression data. Our results suggest that both metrics have equivalent capabilities for the selection of informative variables. ANNRFE seems to produce overall results that are equivalent to previous e cient methods, but can be more accurate on particular datasets.Presentado en el X Workshop Agentes y Sistemas InteligentesRed de Universidades con Carreras en Informática (RedUNCI)2009-10info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf60-69http://sedici.unlp.edu.ar/handle/10915/20884enginfo:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/2.5/ar/Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T10:54:25Zoai:sedici.unlp.edu.ar:10915/20884Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 10:54:25.851SEDICI (UNLP) - Universidad Nacional de La Platafalse |
dc.title.none.fl_str_mv |
Feature selection with simple ANN ensembles |
title |
Feature selection with simple ANN ensembles |
spellingShingle |
Feature selection with simple ANN ensembles Izetta Riera, C. Javier Ciencias Informáticas Process metrics feature selection |
title_short |
Feature selection with simple ANN ensembles |
title_full |
Feature selection with simple ANN ensembles |
title_fullStr |
Feature selection with simple ANN ensembles |
title_full_unstemmed |
Feature selection with simple ANN ensembles |
title_sort |
Feature selection with simple ANN ensembles |
dc.creator.none.fl_str_mv |
Izetta Riera, C. Javier Granitto, Pablo Miguel |
author |
Izetta Riera, C. Javier |
author_facet |
Izetta Riera, C. Javier Granitto, Pablo Miguel |
author_role |
author |
author2 |
Granitto, Pablo Miguel |
author2_role |
author |
dc.subject.none.fl_str_mv |
Ciencias Informáticas Process metrics feature selection |
topic |
Ciencias Informáticas Process metrics feature selection |
dc.description.none.fl_txt_mv |
Feature selection is a well-known pre-processing technique, commonly used with high-dimensional datasets. Its main goal is to discard useless or redundant variables, reducing the dimensionality of the input space, in order to increase the performance and interpretability of models. In this work we introduce the ANN-RFE, a new technique for feature selection that combines the accurate and time-e cient RFE method with the strong discrimination capabilities of ANN ensembles. In particular, we discuss two feature importance metrics that can be used with ANN-RFE: the shu ing and dE metrics. We evaluate the new method using an arti cial example and ve real-world wide datasets, including gene-expression data. Our results suggest that both metrics have equivalent capabilities for the selection of informative variables. ANNRFE seems to produce overall results that are equivalent to previous e cient methods, but can be more accurate on particular datasets. Presentado en el X Workshop Agentes y Sistemas Inteligentes Red de Universidades con Carreras en Informática (RedUNCI) |
description |
Feature selection is a well-known pre-processing technique, commonly used with high-dimensional datasets. Its main goal is to discard useless or redundant variables, reducing the dimensionality of the input space, in order to increase the performance and interpretability of models. In this work we introduce the ANN-RFE, a new technique for feature selection that combines the accurate and time-e cient RFE method with the strong discrimination capabilities of ANN ensembles. In particular, we discuss two feature importance metrics that can be used with ANN-RFE: the shu ing and dE metrics. We evaluate the new method using an arti cial example and ve real-world wide datasets, including gene-expression data. Our results suggest that both metrics have equivalent capabilities for the selection of informative variables. ANNRFE seems to produce overall results that are equivalent to previous e cient methods, but can be more accurate on particular datasets. |
publishDate |
2009 |
dc.date.none.fl_str_mv |
2009-10 |
dc.type.none.fl_str_mv |
info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/publishedVersion Objeto de conferencia http://purl.org/coar/resource_type/c_5794 info:ar-repo/semantics/documentoDeConferencia |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.none.fl_str_mv |
http://sedici.unlp.edu.ar/handle/10915/20884 |
url |
http://sedici.unlp.edu.ar/handle/10915/20884 |
dc.language.none.fl_str_mv |
eng |
language |
eng |
dc.rights.none.fl_str_mv |
info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/2.5/ar/ Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5) |
eu_rights_str_mv |
openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-sa/2.5/ar/ Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5) |
dc.format.none.fl_str_mv |
application/pdf 60-69 |
dc.source.none.fl_str_mv |
reponame:SEDICI (UNLP) instname:Universidad Nacional de La Plata instacron:UNLP |
reponame_str |
SEDICI (UNLP) |
collection |
SEDICI (UNLP) |
instname_str |
Universidad Nacional de La Plata |
instacron_str |
UNLP |
institution |
UNLP |
repository.name.fl_str_mv |
SEDICI (UNLP) - Universidad Nacional de La Plata |
repository.mail.fl_str_mv |
alira@sedici.unlp.edu.ar |
_version_ |
1844615801401769984 |
score |
13.070432 |