3D fast convex-hull-based evolutionary multiobjective optimization algorithm

Detalhes bibliográficos
Autor(a) principal: Zhao, J.
Data de Publicação: 2018
Outros Autores: Jiao, L., Liu, F., Basto-Fernandes, V., Yevseyeva, I., Xia, S., Emmerichd, M. T. M.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10071/17017
Resumo: The receiver operating characteristic (ROC) and detection error tradeoff (DET) curves have been widely used in the machine learning community to analyze the performance of classifiers. The area (or volume) under the convex hull has been used as a scalar indicator for the performance of a set of classifiers in ROC and DET space. Recently, 3D convex-hull-based evolutionary multiobjective optimization algorithm (3DCH-EMOA) has been proposed to maximize the volume of convex hull for binary classification combined with parsimony and three-way classification problems. However, 3DCH-EMOA revealed high consumption of computational resources due to redundant convex hull calculations and a frequent execution of nondominated sorting. In this paper, we introduce incremental convex hull calculation and a fast replacement for non-dominated sorting. While achieving the same high quality results, the computational effort of 3DCH-EMOA can be reduced by orders of magnitude. The average time complexity of 3DCH-EMOA in each generation is reduced from to per iteration, where n is the population size. Six test function problems are used to test the performance of the newly proposed method, and the algorithms are compared to several state-of-the-art algorithms, including NSGA-III, RVEA, etc., which were not compared to 3DCH-EMOA before. Experimental results show that the new version of the algorithm (3DFCH-EMOA) can speed up 3DCH-EMOA for about 30 times for a typical population size of 300 without reducing the performance of the method. Besides, the proposed algorithm is applied for neural networks pruning, and several UCI datasets are used to test the performance.
id RCAP_39f1d77efc55b71328ecd930be8a1d36
oai_identifier_str oai:repositorio.iscte-iul.pt:10071/17017
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling 3D fast convex-hull-based evolutionary multiobjective optimization algorithmConvex hullArea under ROCIndicator-based evolutionary algorithmMultiobjective optimizationROC analysisThe receiver operating characteristic (ROC) and detection error tradeoff (DET) curves have been widely used in the machine learning community to analyze the performance of classifiers. The area (or volume) under the convex hull has been used as a scalar indicator for the performance of a set of classifiers in ROC and DET space. Recently, 3D convex-hull-based evolutionary multiobjective optimization algorithm (3DCH-EMOA) has been proposed to maximize the volume of convex hull for binary classification combined with parsimony and three-way classification problems. However, 3DCH-EMOA revealed high consumption of computational resources due to redundant convex hull calculations and a frequent execution of nondominated sorting. In this paper, we introduce incremental convex hull calculation and a fast replacement for non-dominated sorting. While achieving the same high quality results, the computational effort of 3DCH-EMOA can be reduced by orders of magnitude. The average time complexity of 3DCH-EMOA in each generation is reduced from to per iteration, where n is the population size. Six test function problems are used to test the performance of the newly proposed method, and the algorithms are compared to several state-of-the-art algorithms, including NSGA-III, RVEA, etc., which were not compared to 3DCH-EMOA before. Experimental results show that the new version of the algorithm (3DFCH-EMOA) can speed up 3DCH-EMOA for about 30 times for a typical population size of 300 without reducing the performance of the method. Besides, the proposed algorithm is applied for neural networks pruning, and several UCI datasets are used to test the performance.Elsevier2019-01-10T10:06:18Z2019-07-10T00:00:00Z2018-01-01T00:00:00Z20182019-01-10T10:05:55Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10071/17017eng1568-494610.1016/j.asoc.2018.03.005Zhao, J.Jiao, L.Liu, F.Basto-Fernandes, V.Yevseyeva, I.Xia, S.Emmerichd, M. T. M.info: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:RCAAP2023-11-09T18:01:37Zoai:repositorio.iscte-iul.pt:10071/17017Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:33:01.581844Repositório 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 3D fast convex-hull-based evolutionary multiobjective optimization algorithm
title 3D fast convex-hull-based evolutionary multiobjective optimization algorithm
spellingShingle 3D fast convex-hull-based evolutionary multiobjective optimization algorithm
Zhao, J.
Convex hull
Area under ROC
Indicator-based evolutionary algorithm
Multiobjective optimization
ROC analysis
title_short 3D fast convex-hull-based evolutionary multiobjective optimization algorithm
title_full 3D fast convex-hull-based evolutionary multiobjective optimization algorithm
title_fullStr 3D fast convex-hull-based evolutionary multiobjective optimization algorithm
title_full_unstemmed 3D fast convex-hull-based evolutionary multiobjective optimization algorithm
title_sort 3D fast convex-hull-based evolutionary multiobjective optimization algorithm
author Zhao, J.
author_facet Zhao, J.
Jiao, L.
Liu, F.
Basto-Fernandes, V.
Yevseyeva, I.
Xia, S.
Emmerichd, M. T. M.
author_role author
author2 Jiao, L.
Liu, F.
Basto-Fernandes, V.
Yevseyeva, I.
Xia, S.
Emmerichd, M. T. M.
author2_role author
author
author
author
author
author
dc.contributor.author.fl_str_mv Zhao, J.
Jiao, L.
Liu, F.
Basto-Fernandes, V.
Yevseyeva, I.
Xia, S.
Emmerichd, M. T. M.
dc.subject.por.fl_str_mv Convex hull
Area under ROC
Indicator-based evolutionary algorithm
Multiobjective optimization
ROC analysis
topic Convex hull
Area under ROC
Indicator-based evolutionary algorithm
Multiobjective optimization
ROC analysis
description The receiver operating characteristic (ROC) and detection error tradeoff (DET) curves have been widely used in the machine learning community to analyze the performance of classifiers. The area (or volume) under the convex hull has been used as a scalar indicator for the performance of a set of classifiers in ROC and DET space. Recently, 3D convex-hull-based evolutionary multiobjective optimization algorithm (3DCH-EMOA) has been proposed to maximize the volume of convex hull for binary classification combined with parsimony and three-way classification problems. However, 3DCH-EMOA revealed high consumption of computational resources due to redundant convex hull calculations and a frequent execution of nondominated sorting. In this paper, we introduce incremental convex hull calculation and a fast replacement for non-dominated sorting. While achieving the same high quality results, the computational effort of 3DCH-EMOA can be reduced by orders of magnitude. The average time complexity of 3DCH-EMOA in each generation is reduced from to per iteration, where n is the population size. Six test function problems are used to test the performance of the newly proposed method, and the algorithms are compared to several state-of-the-art algorithms, including NSGA-III, RVEA, etc., which were not compared to 3DCH-EMOA before. Experimental results show that the new version of the algorithm (3DFCH-EMOA) can speed up 3DCH-EMOA for about 30 times for a typical population size of 300 without reducing the performance of the method. Besides, the proposed algorithm is applied for neural networks pruning, and several UCI datasets are used to test the performance.
publishDate 2018
dc.date.none.fl_str_mv 2018-01-01T00:00:00Z
2018
2019-01-10T10:06:18Z
2019-07-10T00:00:00Z
2019-01-10T10:05:55Z
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 http://hdl.handle.net/10071/17017
url http://hdl.handle.net/10071/17017
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 1568-4946
10.1016/j.asoc.2018.03.005
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
publisher.none.fl_str_mv Elsevier
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
_version_ 1799134891233771520