A Hyperheuristic Approach for Unsupervised Land-Cover Classification

Detalhes bibliográficos
Autor(a) principal: Papa, Joao Papa [UNESP]
Data de Publicação: 2016
Outros Autores: Papa, Luciene Patrici, Pereira, Danillo Roberto [UNESP], Pisani, Rodrigo Jose
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1109/JSTARS.2016.2557584
http://hdl.handle.net/11449/161736
Resumo: Unsupervised land-use/cover classification is of great interest, since it becomes even more difficult to obtain high-quality labeled data. Still considered one of the most used clustering techniques, the well-known k-means plays an important role in the pattern recognition community. Its simple formulation and good results in a number of applications have fostered the development of new variants and methodologies to address the problem of minimizing the distance from each dataset sample to its nearest centroid (mean). In this paper, we present a genetic programming-based hyperheuristic approach to combine different metaheuristic techniques used to enhance k-means effectiveness. The proposed approach is evaluated in four satellite and one radar image showing promising results, while outperforming each individual metaheuristic technique.
id UNSP_63f21e45e0ee5325a1fd83b8bd8e4595
oai_identifier_str oai:repositorio.unesp.br:11449/161736
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling A Hyperheuristic Approach for Unsupervised Land-Cover ClassificationHyperheuristick-meansland-cover classificationUnsupervised land-use/cover classification is of great interest, since it becomes even more difficult to obtain high-quality labeled data. Still considered one of the most used clustering techniques, the well-known k-means plays an important role in the pattern recognition community. Its simple formulation and good results in a number of applications have fostered the development of new variants and methodologies to address the problem of minimizing the distance from each dataset sample to its nearest centroid (mean). In this paper, we present a genetic programming-based hyperheuristic approach to combine different metaheuristic techniques used to enhance k-means effectiveness. The proposed approach is evaluated in four satellite and one radar image showing promising results, while outperforming each individual metaheuristic technique.Sao Paulo State Univ, Dept Comp, BR-17033360 Bauru, SP, BrazilSao Paulo State South West Coll, Dept Hlth, Av Prof Clso Ferreira da Silva 1001, BR-18707150 Sao Paulo, BrazilUniv Fed Alfenas, Inst Nat Sci, BR-37130000 Alfenas, BrazilSao Paulo State Univ, Dept Comp, BR-17033360 Bauru, SP, BrazilIeee-inst Electrical Electronics Engineers IncUniversidade Estadual Paulista (Unesp)Sao Paulo State South West CollUniv Fed AlfenasPapa, Joao Papa [UNESP]Papa, Luciene PatriciPereira, Danillo Roberto [UNESP]Pisani, Rodrigo Jose2018-11-26T16:48:26Z2018-11-26T16:48:26Z2016-06-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article2333-2342application/pdfhttp://dx.doi.org/10.1109/JSTARS.2016.2557584Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing. Piscataway: Ieee-inst Electrical Electronics Engineers Inc, v. 9, n. 6, p. 2333-2342, 2016.1939-1404http://hdl.handle.net/11449/16173610.1109/JSTARS.2016.2557584WOS:000379935100020WOS000379935100020.pdfWeb of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengIeee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing1,547info:eu-repo/semantics/openAccess2024-04-23T16:11:00Zoai:repositorio.unesp.br:11449/161736Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T22:39:16.673071Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv A Hyperheuristic Approach for Unsupervised Land-Cover Classification
title A Hyperheuristic Approach for Unsupervised Land-Cover Classification
spellingShingle A Hyperheuristic Approach for Unsupervised Land-Cover Classification
Papa, Joao Papa [UNESP]
Hyperheuristic
k-means
land-cover classification
title_short A Hyperheuristic Approach for Unsupervised Land-Cover Classification
title_full A Hyperheuristic Approach for Unsupervised Land-Cover Classification
title_fullStr A Hyperheuristic Approach for Unsupervised Land-Cover Classification
title_full_unstemmed A Hyperheuristic Approach for Unsupervised Land-Cover Classification
title_sort A Hyperheuristic Approach for Unsupervised Land-Cover Classification
author Papa, Joao Papa [UNESP]
author_facet Papa, Joao Papa [UNESP]
Papa, Luciene Patrici
Pereira, Danillo Roberto [UNESP]
Pisani, Rodrigo Jose
author_role author
author2 Papa, Luciene Patrici
Pereira, Danillo Roberto [UNESP]
Pisani, Rodrigo Jose
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
Sao Paulo State South West Coll
Univ Fed Alfenas
dc.contributor.author.fl_str_mv Papa, Joao Papa [UNESP]
Papa, Luciene Patrici
Pereira, Danillo Roberto [UNESP]
Pisani, Rodrigo Jose
dc.subject.por.fl_str_mv Hyperheuristic
k-means
land-cover classification
topic Hyperheuristic
k-means
land-cover classification
description Unsupervised land-use/cover classification is of great interest, since it becomes even more difficult to obtain high-quality labeled data. Still considered one of the most used clustering techniques, the well-known k-means plays an important role in the pattern recognition community. Its simple formulation and good results in a number of applications have fostered the development of new variants and methodologies to address the problem of minimizing the distance from each dataset sample to its nearest centroid (mean). In this paper, we present a genetic programming-based hyperheuristic approach to combine different metaheuristic techniques used to enhance k-means effectiveness. The proposed approach is evaluated in four satellite and one radar image showing promising results, while outperforming each individual metaheuristic technique.
publishDate 2016
dc.date.none.fl_str_mv 2016-06-01
2018-11-26T16:48:26Z
2018-11-26T16:48:26Z
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://dx.doi.org/10.1109/JSTARS.2016.2557584
Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing. Piscataway: Ieee-inst Electrical Electronics Engineers Inc, v. 9, n. 6, p. 2333-2342, 2016.
1939-1404
http://hdl.handle.net/11449/161736
10.1109/JSTARS.2016.2557584
WOS:000379935100020
WOS000379935100020.pdf
url http://dx.doi.org/10.1109/JSTARS.2016.2557584
http://hdl.handle.net/11449/161736
identifier_str_mv Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing. Piscataway: Ieee-inst Electrical Electronics Engineers Inc, v. 9, n. 6, p. 2333-2342, 2016.
1939-1404
10.1109/JSTARS.2016.2557584
WOS:000379935100020
WOS000379935100020.pdf
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing
1,547
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 2333-2342
application/pdf
dc.publisher.none.fl_str_mv Ieee-inst Electrical Electronics Engineers Inc
publisher.none.fl_str_mv Ieee-inst Electrical Electronics Engineers Inc
dc.source.none.fl_str_mv Web of Science
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808129447329529856