Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensemble

Detalhes bibliográficos
Autor(a) principal: Peralta Donate, Juan
Data de Publicação: 2013
Outros Autores: Cortez, Paulo, Gutierrez Sanchez, German, Sanchis de Miguel, Araceli
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: https://hdl.handle.net/1822/24678
Resumo: The ability to forecast the future based on past data is a key tool to support individual and organizational decision making. In particular, the goal of Time Series Forecasting (TSF) is to predict the behavior of complex systems by looking only at past patterns of the same phenomenon. In recent years, several works in the literature have adopted Evolutionary Artificial Neural Networks (EANNs) for TSF. In this work, we propose a novel EANN approach, where a weighted n-fold validation fitness scheme is used to build an ensemble of neural networks, under four different combination methods: mean, median, softmax and rank-based. Several experiments were held, using six real-world time series with different characteristics and from distinct domains. Overall, the proposed approach achieved competitive results when compared with a non-weighted n-fold EANN ensemble, the simpler 0-fold EANN and also the popular Holt–Winters statistical method.
id RCAP_911fd0946707f08c5cb65affdaa84ab3
oai_identifier_str oai:repositorium.sdum.uminho.pt:1822/24678
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensembleEnsemblesEvolutionary computationGenetic algorithmsMultilayer perceptronTime series forecastingScience & TechnologyThe ability to forecast the future based on past data is a key tool to support individual and organizational decision making. In particular, the goal of Time Series Forecasting (TSF) is to predict the behavior of complex systems by looking only at past patterns of the same phenomenon. In recent years, several works in the literature have adopted Evolutionary Artificial Neural Networks (EANNs) for TSF. In this work, we propose a novel EANN approach, where a weighted n-fold validation fitness scheme is used to build an ensemble of neural networks, under four different combination methods: mean, median, softmax and rank-based. Several experiments were held, using six real-world time series with different characteristics and from distinct domains. Overall, the proposed approach achieved competitive results when compared with a non-weighted n-fold EANN ensemble, the simpler 0-fold EANN and also the popular Holt–Winters statistical method.This work was supported by University Carlos III of Madrid and by Community of Madrid under project CCG10-UC3M/TIC-5174. The work of P. Cortez was funded by FEDER (program COMPETE and FCT) under project FCOMP-01-0124-FEDER-022674.Elsevier 1Universidade do MinhoPeralta Donate, JuanCortez, PauloGutierrez Sanchez, GermanSanchis de Miguel, Araceli2013-062013-06-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/1822/24678eng0925-231210.1016/j.neucom.2012.02.053http://dx.doi.org/10.1016/j.neucom.2012.02.053info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-05-25T01:53:30Zoai:repositorium.sdum.uminho.pt:1822/24678Portal AgregadorONGhttps://www.rcaap.pt/oai/openairemluisa.alvim@gmail.comopendoar:71602024-05-25T01:53:30Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensemble
title Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensemble
spellingShingle Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensemble
Peralta Donate, Juan
Ensembles
Evolutionary computation
Genetic algorithms
Multilayer perceptron
Time series forecasting
Science & Technology
title_short Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensemble
title_full Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensemble
title_fullStr Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensemble
title_full_unstemmed Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensemble
title_sort Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensemble
author Peralta Donate, Juan
author_facet Peralta Donate, Juan
Cortez, Paulo
Gutierrez Sanchez, German
Sanchis de Miguel, Araceli
author_role author
author2 Cortez, Paulo
Gutierrez Sanchez, German
Sanchis de Miguel, Araceli
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidade do Minho
dc.contributor.author.fl_str_mv Peralta Donate, Juan
Cortez, Paulo
Gutierrez Sanchez, German
Sanchis de Miguel, Araceli
dc.subject.por.fl_str_mv Ensembles
Evolutionary computation
Genetic algorithms
Multilayer perceptron
Time series forecasting
Science & Technology
topic Ensembles
Evolutionary computation
Genetic algorithms
Multilayer perceptron
Time series forecasting
Science & Technology
description The ability to forecast the future based on past data is a key tool to support individual and organizational decision making. In particular, the goal of Time Series Forecasting (TSF) is to predict the behavior of complex systems by looking only at past patterns of the same phenomenon. In recent years, several works in the literature have adopted Evolutionary Artificial Neural Networks (EANNs) for TSF. In this work, we propose a novel EANN approach, where a weighted n-fold validation fitness scheme is used to build an ensemble of neural networks, under four different combination methods: mean, median, softmax and rank-based. Several experiments were held, using six real-world time series with different characteristics and from distinct domains. Overall, the proposed approach achieved competitive results when compared with a non-weighted n-fold EANN ensemble, the simpler 0-fold EANN and also the popular Holt–Winters statistical method.
publishDate 2013
dc.date.none.fl_str_mv 2013-06
2013-06-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/1822/24678
url https://hdl.handle.net/1822/24678
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 0925-2312
10.1016/j.neucom.2012.02.053
http://dx.doi.org/10.1016/j.neucom.2012.02.053
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier 1
publisher.none.fl_str_mv Elsevier 1
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv mluisa.alvim@gmail.com
_version_ 1817544466791137280