Semi-wrapper feature subset selector for feed-forward neural networks: Applications to binary and multi-class classification problems

This paper explores widely the data preparation stage within the process of knowledge discovery and data mining via feature subset selection in the context of two very well-known neural models: radial basis function neural networks and multi-layer perceptron. It is known the best performance of wrap...

Descripción completa

Detalles Bibliográficos
Autores: Tallón Ballesteros, Antonio Javier, Riquelme Santos, José Cristóbal, Ruiz Sánchez, Roberto
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2019
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/145681
Acceso en línea:https://hdl.handle.net/11441/145681
https://doi.org/10.1016/j.neucom.2018.05.133
Access Level:acceso abierto
Palabra clave:Feed-forward artificial neural networks
Feature selection
Supervised machine learning
Feature subset selection
Computational intelligence
Semi-wrapper
id ES_9dcba6c0456044d2be632a8357907b4e
oai_identifier_str oai:idus.us.es:11441/145681
network_acronym_str ES
network_name_str España
repository_id_str
spelling Semi-wrapper feature subset selector for feed-forward neural networks: Applications to binary and multi-class classification problemsTallón Ballesteros, Antonio JavierRiquelme Santos, José CristóbalRuiz Sánchez, RobertoFeed-forward artificial neural networksFeature selectionSupervised machine learningFeature subset selectionComputational intelligenceSemi-wrapperThis paper explores widely the data preparation stage within the process of knowledge discovery and data mining via feature subset selection in the context of two very well-known neural models: radial basis function neural networks and multi-layer perceptron. It is known the best performance of wrapper attribute selection methods based on the evaluation measure provided by a classifier, although the temporal complexity of learning neural networks practically precludes the use of wrapper techniques, especially in complex databases with high dimensionality and a large number of labels. In this paper, we propose the use of the Naïve Bayes classifier as a fitness function within a semi-wrapper feature selec tion approach. The Naïve Bayes classifier is a good fast approach to a neural network and utilising it as a measure of goodness in a backward search on a ranking provides a specific attribute selection method for neural networks in complex data. The test-bed consists of 34 binary and multi-class classification problems and 7 feature selectors. Of these, there are 6 data sets with upwards of 5 classes. According to the reported accuracy results that have been supported by non-parametric statistical tests in different scenarios, our method has been shown to be very suitable for both kinds of neural networks. Moreover, the reduced feature-space is around 20% of the full attribute space. The speedup with the aforementioned semi-wrapper is very outstanding and its value fluctuates, on average, from about 1.5 with radial basis function neural networks to around 30 with multi-layer perceptronComisión Interministerial de Ciencia y Tecnología TIN2014-55894-C2-RScienceDirectLenguajes y Sistemas InformáticosComisión Interministerial de Ciencia y Tecnología (CICYT). España2019info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/145681https://doi.org/10.1016/j.neucom.2018.05.133reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésNeurocomputing, 353, 28-44.TIN2014-55894-C2-Rhttps://www.sciencedirect.com/science/article/pii/S0925231219303303?via%3Dihubinfo:eu-repo/semantics/openAccessoai:idus.us.es:11441/1456812026-06-17T12:51:07Z
dc.title.none.fl_str_mv Semi-wrapper feature subset selector for feed-forward neural networks: Applications to binary and multi-class classification problems
title Semi-wrapper feature subset selector for feed-forward neural networks: Applications to binary and multi-class classification problems
spellingShingle Semi-wrapper feature subset selector for feed-forward neural networks: Applications to binary and multi-class classification problems
Tallón Ballesteros, Antonio Javier
Feed-forward artificial neural networks
Feature selection
Supervised machine learning
Feature subset selection
Computational intelligence
Semi-wrapper
title_short Semi-wrapper feature subset selector for feed-forward neural networks: Applications to binary and multi-class classification problems
title_full Semi-wrapper feature subset selector for feed-forward neural networks: Applications to binary and multi-class classification problems
title_fullStr Semi-wrapper feature subset selector for feed-forward neural networks: Applications to binary and multi-class classification problems
title_full_unstemmed Semi-wrapper feature subset selector for feed-forward neural networks: Applications to binary and multi-class classification problems
title_sort Semi-wrapper feature subset selector for feed-forward neural networks: Applications to binary and multi-class classification problems
dc.creator.none.fl_str_mv Tallón Ballesteros, Antonio Javier
Riquelme Santos, José Cristóbal
Ruiz Sánchez, Roberto
author Tallón Ballesteros, Antonio Javier
author_facet Tallón Ballesteros, Antonio Javier
Riquelme Santos, José Cristóbal
Ruiz Sánchez, Roberto
author_role author
author2 Riquelme Santos, José Cristóbal
Ruiz Sánchez, Roberto
author2_role author
author
dc.contributor.none.fl_str_mv Lenguajes y Sistemas Informáticos
Comisión Interministerial de Ciencia y Tecnología (CICYT). España
dc.subject.none.fl_str_mv Feed-forward artificial neural networks
Feature selection
Supervised machine learning
Feature subset selection
Computational intelligence
Semi-wrapper
topic Feed-forward artificial neural networks
Feature selection
Supervised machine learning
Feature subset selection
Computational intelligence
Semi-wrapper
description This paper explores widely the data preparation stage within the process of knowledge discovery and data mining via feature subset selection in the context of two very well-known neural models: radial basis function neural networks and multi-layer perceptron. It is known the best performance of wrapper attribute selection methods based on the evaluation measure provided by a classifier, although the temporal complexity of learning neural networks practically precludes the use of wrapper techniques, especially in complex databases with high dimensionality and a large number of labels. In this paper, we propose the use of the Naïve Bayes classifier as a fitness function within a semi-wrapper feature selec tion approach. The Naïve Bayes classifier is a good fast approach to a neural network and utilising it as a measure of goodness in a backward search on a ranking provides a specific attribute selection method for neural networks in complex data. The test-bed consists of 34 binary and multi-class classification problems and 7 feature selectors. Of these, there are 6 data sets with upwards of 5 classes. According to the reported accuracy results that have been supported by non-parametric statistical tests in different scenarios, our method has been shown to be very suitable for both kinds of neural networks. Moreover, the reduced feature-space is around 20% of the full attribute space. The speedup with the aforementioned semi-wrapper is very outstanding and its value fluctuates, on average, from about 1.5 with radial basis function neural networks to around 30 with multi-layer perceptron
publishDate 2019
dc.date.none.fl_str_mv 2019
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/145681
https://doi.org/10.1016/j.neucom.2018.05.133
url https://hdl.handle.net/11441/145681
https://doi.org/10.1016/j.neucom.2018.05.133
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Neurocomputing, 353, 28-44.
TIN2014-55894-C2-R
https://www.sciencedirect.com/science/article/pii/S0925231219303303?via%3Dihub
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv ScienceDirect
publisher.none.fl_str_mv ScienceDirect
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869414772768768000
score 15.301603

Similares en LA Referencia