Heuristics for minimizing the maximum within-clusters distance
Autor(a) principal: | |
---|---|
Data de Publicação: | 2012 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNIFESP |
Texto Completo: | http://repositorio.unifesp.br/handle/11600/7427 http://dx.doi.org/10.1590/S0101-74382012005000023 |
Resumo: | The clustering problem consists in finding patterns in a data set in order to divide it into clusters with high within-cluster similarity. This paper presents the study of a problem, here called MMD problem, which aims at finding a clustering with a predefined number of clusters that minimizes the largest within-cluster distance (diameter) among all clusters. There are two main objectives in this paper: to propose heuristics for the MMD and to evaluate the suitability of the best proposed heuristic results according to the real classification of some data sets. Regarding the first objective, the results obtained in the experiments indicate a good performance of the best proposed heuristic that outperformed the Complete Linkage algorithm (the most used method from the literature for this problem). Nevertheless, regarding the suitability of the results according to the real classification of the data sets, the proposed heuristic achieved better quality results than C-Means algorithm, but worse than Complete Linkage. |
id |
UFSP_9d3e9303db705794f2ba2d001dfce9ff |
---|---|
oai_identifier_str |
oai:repositorio.unifesp.br:11600/7427 |
network_acronym_str |
UFSP |
network_name_str |
Repositório Institucional da UNIFESP |
repository_id_str |
3465 |
spelling |
Fioruci, José AugustoToledo, Franklina M.b.Nascimento, Mariá Cristina Vasconcelos [UNIFESP]Universidade de São Paulo (USP)Universidade Federal de São Paulo (UNIFESP)2015-06-14T13:45:04Z2015-06-14T13:45:04Z2012-12-01Pesquisa Operacional. Sociedade Brasileira de Pesquisa Operacional, v. 32, n. 3, p. 497-522, 2012.0101-7438http://repositorio.unifesp.br/handle/11600/7427http://dx.doi.org/10.1590/S0101-74382012005000023S0101-74382012000300002.pdfS0101-7438201200030000210.1590/S0101-74382012005000023The clustering problem consists in finding patterns in a data set in order to divide it into clusters with high within-cluster similarity. This paper presents the study of a problem, here called MMD problem, which aims at finding a clustering with a predefined number of clusters that minimizes the largest within-cluster distance (diameter) among all clusters. There are two main objectives in this paper: to propose heuristics for the MMD and to evaluate the suitability of the best proposed heuristic results according to the real classification of some data sets. Regarding the first objective, the results obtained in the experiments indicate a good performance of the best proposed heuristic that outperformed the Complete Linkage algorithm (the most used method from the literature for this problem). Nevertheless, regarding the suitability of the results according to the real classification of the data sets, the proposed heuristic achieved better quality results than C-Means algorithm, but worse than Complete Linkage.Universidade de São Paulo Instituto de Ciências Matemáticas e de ComputaçãoUniversidade Federal de São Paulo (UNIFESP) Instituto de Ciência e TecnologiaUNIFESP, Instituto de Ciência e TecnologiaSciELO497-522engSociedade Brasileira de Pesquisa OperacionalPesquisa OperacionalclusteringheuristicsGRASPminimization of the maximum diameterHeuristics for minimizing the maximum within-clusters distanceinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UNIFESPinstname:Universidade Federal de São Paulo (UNIFESP)instacron:UNIFESPORIGINALS0101-74382012000300002.pdfapplication/pdf736742${dspace.ui.url}/bitstream/11600/7427/1/S0101-74382012000300002.pdfa9a4fe7ab05cc541feed6ea565f8883bMD51open accessTEXTS0101-74382012000300002.pdf.txtS0101-74382012000300002.pdf.txtExtracted texttext/plain63831${dspace.ui.url}/bitstream/11600/7427/9/S0101-74382012000300002.pdf.txt067f220ca32bad4b19408fa6a46334b6MD59open accessTHUMBNAILS0101-74382012000300002.pdf.jpgS0101-74382012000300002.pdf.jpgIM Thumbnailimage/jpeg4231${dspace.ui.url}/bitstream/11600/7427/11/S0101-74382012000300002.pdf.jpg8270367886376b6bee3afc3221fba7c9MD511open access11600/74272023-06-05 19:07:53.721open accessoai:repositorio.unifesp.br:11600/7427Repositório InstitucionalPUBhttp://www.repositorio.unifesp.br/oai/requestopendoar:34652023-06-05T22:07:53Repositório Institucional da UNIFESP - Universidade Federal de São Paulo (UNIFESP)false |
dc.title.en.fl_str_mv |
Heuristics for minimizing the maximum within-clusters distance |
title |
Heuristics for minimizing the maximum within-clusters distance |
spellingShingle |
Heuristics for minimizing the maximum within-clusters distance Fioruci, José Augusto clustering heuristics GRASP minimization of the maximum diameter |
title_short |
Heuristics for minimizing the maximum within-clusters distance |
title_full |
Heuristics for minimizing the maximum within-clusters distance |
title_fullStr |
Heuristics for minimizing the maximum within-clusters distance |
title_full_unstemmed |
Heuristics for minimizing the maximum within-clusters distance |
title_sort |
Heuristics for minimizing the maximum within-clusters distance |
author |
Fioruci, José Augusto |
author_facet |
Fioruci, José Augusto Toledo, Franklina M.b. Nascimento, Mariá Cristina Vasconcelos [UNIFESP] |
author_role |
author |
author2 |
Toledo, Franklina M.b. Nascimento, Mariá Cristina Vasconcelos [UNIFESP] |
author2_role |
author author |
dc.contributor.institution.none.fl_str_mv |
Universidade de São Paulo (USP) Universidade Federal de São Paulo (UNIFESP) |
dc.contributor.author.fl_str_mv |
Fioruci, José Augusto Toledo, Franklina M.b. Nascimento, Mariá Cristina Vasconcelos [UNIFESP] |
dc.subject.eng.fl_str_mv |
clustering heuristics GRASP minimization of the maximum diameter |
topic |
clustering heuristics GRASP minimization of the maximum diameter |
description |
The clustering problem consists in finding patterns in a data set in order to divide it into clusters with high within-cluster similarity. This paper presents the study of a problem, here called MMD problem, which aims at finding a clustering with a predefined number of clusters that minimizes the largest within-cluster distance (diameter) among all clusters. There are two main objectives in this paper: to propose heuristics for the MMD and to evaluate the suitability of the best proposed heuristic results according to the real classification of some data sets. Regarding the first objective, the results obtained in the experiments indicate a good performance of the best proposed heuristic that outperformed the Complete Linkage algorithm (the most used method from the literature for this problem). Nevertheless, regarding the suitability of the results according to the real classification of the data sets, the proposed heuristic achieved better quality results than C-Means algorithm, but worse than Complete Linkage. |
publishDate |
2012 |
dc.date.issued.fl_str_mv |
2012-12-01 |
dc.date.accessioned.fl_str_mv |
2015-06-14T13:45:04Z |
dc.date.available.fl_str_mv |
2015-06-14T13:45:04Z |
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.citation.fl_str_mv |
Pesquisa Operacional. Sociedade Brasileira de Pesquisa Operacional, v. 32, n. 3, p. 497-522, 2012. |
dc.identifier.uri.fl_str_mv |
http://repositorio.unifesp.br/handle/11600/7427 http://dx.doi.org/10.1590/S0101-74382012005000023 |
dc.identifier.issn.none.fl_str_mv |
0101-7438 |
dc.identifier.file.none.fl_str_mv |
S0101-74382012000300002.pdf |
dc.identifier.scielo.none.fl_str_mv |
S0101-74382012000300002 |
dc.identifier.doi.none.fl_str_mv |
10.1590/S0101-74382012005000023 |
identifier_str_mv |
Pesquisa Operacional. Sociedade Brasileira de Pesquisa Operacional, v. 32, n. 3, p. 497-522, 2012. 0101-7438 S0101-74382012000300002.pdf S0101-74382012000300002 10.1590/S0101-74382012005000023 |
url |
http://repositorio.unifesp.br/handle/11600/7427 http://dx.doi.org/10.1590/S0101-74382012005000023 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.none.fl_str_mv |
Pesquisa Operacional |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
497-522 |
dc.publisher.none.fl_str_mv |
Sociedade Brasileira de Pesquisa Operacional |
publisher.none.fl_str_mv |
Sociedade Brasileira de Pesquisa Operacional |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UNIFESP instname:Universidade Federal de São Paulo (UNIFESP) instacron:UNIFESP |
instname_str |
Universidade Federal de São Paulo (UNIFESP) |
instacron_str |
UNIFESP |
institution |
UNIFESP |
reponame_str |
Repositório Institucional da UNIFESP |
collection |
Repositório Institucional da UNIFESP |
bitstream.url.fl_str_mv |
${dspace.ui.url}/bitstream/11600/7427/1/S0101-74382012000300002.pdf ${dspace.ui.url}/bitstream/11600/7427/9/S0101-74382012000300002.pdf.txt ${dspace.ui.url}/bitstream/11600/7427/11/S0101-74382012000300002.pdf.jpg |
bitstream.checksum.fl_str_mv |
a9a4fe7ab05cc541feed6ea565f8883b 067f220ca32bad4b19408fa6a46334b6 8270367886376b6bee3afc3221fba7c9 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UNIFESP - Universidade Federal de São Paulo (UNIFESP) |
repository.mail.fl_str_mv |
|
_version_ |
1802764205931102208 |