New strategies for OVO feature selection on multiclass problems

Feature selection is a useful machine learning technique aimed at reducing the dimensionality of the input space, discarding useless or redundant variables, in order to increase the performance and interpretability of models. The well-known Recursive Feature Elimination (RFE) algorithm provides good...

Descripción completa

Detalles Bibliográficos
Autores principales: Izetta, Javier, Grinblat, Guillermo L., Granitto, Pablo Miguel
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2011
Materias:
Ciencias Informáticas
Feature Selection
Multiclass Problems
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/125264
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-125264
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Feature Selection
Multiclass Problems
spellingShingle Ciencias Informáticas
Feature Selection
Multiclass Problems
Izetta, Javier
Grinblat, Guillermo L.
Granitto, Pablo Miguel
New strategies for OVO feature selection on multiclass problems
topic_facet Ciencias Informáticas
Feature Selection
Multiclass Problems
description Feature selection is a useful machine learning technique aimed at reducing the dimensionality of the input space, discarding useless or redundant variables, in order to increase the performance and interpretability of models. The well-known Recursive Feature Elimination (RFE) algorithm provides good performance with moderate computational efforts, in particular for wide datasets. When using Support Vector Machines (SVM) for multiclass classification problems, the most typical strategy is to apply a simple One–Vs–One (OVO) strategy to produce a multiclass classifier starting from binary ones. In this work we introduce improved methods to produce the final ranking of features on multiclass problems with OVO–SVM, based on different combinations of the set of rankings produced by the diverse binary problems. We evaluated our new strategies using wide datasets from mass–spectrometry analysis and standard datasets from the UCI repository. In particular, we compared the new methods with the traditional average strategy. Our results suggest that one of our new methods outperforms the traditional scheme in most situations.
format Objeto de conferencia
Objeto de conferencia
author Izetta, Javier
Grinblat, Guillermo L.
Granitto, Pablo Miguel
author_facet Izetta, Javier
Grinblat, Guillermo L.
Granitto, Pablo Miguel
author_sort Izetta, Javier
title New strategies for OVO feature selection on multiclass problems
title_short New strategies for OVO feature selection on multiclass problems
title_full New strategies for OVO feature selection on multiclass problems
title_fullStr New strategies for OVO feature selection on multiclass problems
title_full_unstemmed New strategies for OVO feature selection on multiclass problems
title_sort new strategies for ovo feature selection on multiclass problems
publishDate 2011
url http://sedici.unlp.edu.ar/handle/10915/125264
work_keys_str_mv AT izettajavier newstrategiesforovofeatureselectiononmulticlassproblems
AT grinblatguillermol newstrategiesforovofeatureselectiononmulticlassproblems
AT granittopablomiguel newstrategiesforovofeatureselectiononmulticlassproblems
bdutipo_str Repositorios
_version_ 1764820451467460608

Ejemplares similares