Publicação

Ensemble classifiers in remote sensing: a comparative analysis

Ver documento

Detalhes bibliográficos
Resumo:Land Cover and Land Use (LCLU) maps are very important tools for understanding the relationships between human activities and the natural environment. Defining accurately all the features over the Earth's surface is essential to assure their management properly. The basic data which are being used to derive those maps are remote sensing imagery (RSI), and concretely, satellite images. Hence, new techniques and methods able to deal with those data and at the same time, do it accurately, have been demanded. In this work, our goal was to have a brief review over some of the currently approaches in the scientific community to face this challenge, to get higher accuracy in LCLU maps. Although, we will be focus on the study of the classifiers ensembles and the different strategies that those ensembles present in the literature. We have proposed different ensembles strategies based in our data and previous work, in order to increase the accuracy of previous LCLU maps made by using the same data and single classifiers. Finally, only one of the ensembles proposed have got significantly higher accuracy, in the classification of LCLU map, than the better single classifier performance with the same data. Also, it was proved that diversity did not play an important role in the success of this ensemble.
Autores principais:Rodríguez, Hernán Cortés
Assunto:Accuracy Bagging Boosting CART Classifiers Ensemble Land Cover and Land Use Maps Linear Discriminant Classifier Majority Voting Neural Networks Random Forest
Ano:2014
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Universidade Nova de Lisboa
Idioma:inglês
Origem:Repositório Institucional da UNL
_version_ 1868983138851487744
author Rodríguez, Hernán Cortés
author_facet Rodríguez, Hernán Cortés
author_role author
contributor_name_str_mv Rengel, Reyes
Caetano, Mário Sílvio Rochinha de Andrade
Henriques, Roberto André Pereira
RUN
country_str PT
creators_json_txt [{\"Person.name\":\"Rodríguez, Hernán Cortés\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Rengel, Reyes
Caetano, Mário Sílvio Rochinha de Andrade
Henriques, Roberto André Pereira
RUN
datacite.creators.creator.creatorName.fl_str_mv Rodríguez, Hernán Cortés
datacite.date.Accepted.fl_str_mv 2014-03-06T00:00:00Z
datacite.date.available.fl_str_mv 2014-03-18T13:34:25Z
datacite.date.embargoed.fl_str_mv 2014-03-18T13:34:25Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Accuracy
Bagging
Boosting
CART
Classifiers Ensemble
Land Cover and Land Use Maps
Linear Discriminant Classifier
Majority Voting
Neural Networks
Random Forest
datacite.titles.title.fl_str_mv Ensemble classifiers in remote sensing: a comparative analysis
dc.contributor.none.fl_str_mv Rengel, Reyes
Caetano, Mário Sílvio Rochinha de Andrade
Henriques, Roberto André Pereira
RUN
dc.creator.none.fl_str_mv Rodríguez, Hernán Cortés
dc.date.Accepted.fl_str_mv 2014-03-06T00:00:00Z
dc.date.available.fl_str_mv 2014-03-18T13:34:25Z
dc.date.embargoed.fl_str_mv 2014-03-18T13:34:25Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10362/11671
dc.language.none.fl_str_mv eng
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Accuracy
Bagging
Boosting
CART
Classifiers Ensemble
Land Cover and Land Use Maps
Linear Discriminant Classifier
Majority Voting
Neural Networks
Random Forest
dc.title.fl_str_mv Ensemble classifiers in remote sensing: a comparative analysis
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_bdcc
description Land Cover and Land Use (LCLU) maps are very important tools for understanding the relationships between human activities and the natural environment. Defining accurately all the features over the Earth's surface is essential to assure their management properly. The basic data which are being used to derive those maps are remote sensing imagery (RSI), and concretely, satellite images. Hence, new techniques and methods able to deal with those data and at the same time, do it accurately, have been demanded. In this work, our goal was to have a brief review over some of the currently approaches in the scientific community to face this challenge, to get higher accuracy in LCLU maps. Although, we will be focus on the study of the classifiers ensembles and the different strategies that those ensembles present in the literature. We have proposed different ensembles strategies based in our data and previous work, in order to increase the accuracy of previous LCLU maps made by using the same data and single classifiers. Finally, only one of the ensembles proposed have got significantly higher accuracy, in the classification of LCLU map, than the better single classifier performance with the same data. Also, it was proved that diversity did not play an important role in the success of this ensemble.
dirty 0
eu_rights_str_mv openAccess
format masterThesis
fulltext.url.fl_str_mv https://run.unl.pt/bitstreams/c6f831c0-51db-4581-b4e9-83124558742b/download
id run_ab7b33ad5d6cdc16d4e15da47d9f2bc1
identifier.url.fl_str_mv http://hdl.handle.net/10362/11671
inst_facet_str urn:organizationAcronym:unl{{{_:::_}}}Universidade Nova de Lisboa
instacron_str unl
institution Universidade Nova de Lisboa
instname_str Universidade Nova de Lisboa
language eng
network_acronym_str run
network_name_str Repositório Institucional da UNL
oai_identifier_str oai:run.unl.pt:10362/11671
organization_str_mv urn:organizationAcronym:unl
person_str_mv Rodríguez, Hernán Cortés
publishDate 2014
repo_facet_str urn:repositoryAcronym:run{{{_:::_}}}Repositório Institucional da UNL
reponame_str Repositório Institucional da UNL
repository_id_str urn:repositoryAcronym:run
service_str_mv urn:repositoryAcronym:run
spelling engporLand Cover and Land Use (LCLU) maps are very important tools for understanding the relationships between human activities and the natural environment. Defining accurately all the features over the Earth's surface is essential to assure their management properly. The basic data which are being used to derive those maps are remote sensing imagery (RSI), and concretely, satellite images. Hence, new techniques and methods able to deal with those data and at the same time, do it accurately, have been demanded. In this work, our goal was to have a brief review over some of the currently approaches in the scientific community to face this challenge, to get higher accuracy in LCLU maps. Although, we will be focus on the study of the classifiers ensembles and the different strategies that those ensembles present in the literature. We have proposed different ensembles strategies based in our data and previous work, in order to increase the accuracy of previous LCLU maps made by using the same data and single classifiers. Finally, only one of the ensembles proposed have got significantly higher accuracy, in the classification of LCLU map, than the better single classifier performance with the same data. Also, it was proved that diversity did not play an important role in the success of this ensemble.application/pdfporEnsemble classifiers in remote sensing: a comparative analysisRodríguez, Hernán CortésRengel, ReyesCaetano, Mário Sílvio Rochinha de AndradeHenriques, Roberto André PereiraHostingInstitutionOrganizationalRUNe-mailmailto:run@unl.ptrun@unl.ptURNurn:tid:2013925852014-03-18T13:34:25Z2014-03-062014-03-06T00:00:00ZHandlehttp://hdl.handle.net/10362/11671http://purl.org/coar/access_right/c_abf2open accessAccuracyBaggingBoostingCARTClassifiers EnsembleLand Cover and Land Use MapsLinear Discriminant ClassifierMajority VotingNeural NetworksRandom Forest2739937 bytesliteraturehttp://purl.org/coar/resource_type/c_bdccmaster thesishttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://run.unl.pt/bitstreams/c6f831c0-51db-4581-b4e9-83124558742b/download
spellingShingle Ensemble classifiers in remote sensing: a comparative analysis
Rodríguez, Hernán Cortés
Accuracy
Bagging
Boosting
CART
Classifiers Ensemble
Land Cover and Land Use Maps
Linear Discriminant Classifier
Majority Voting
Neural Networks
Random Forest
status SINGLETON
subject.fl_str_mv Accuracy
Bagging
Boosting
CART
Classifiers Ensemble
Land Cover and Land Use Maps
Linear Discriminant Classifier
Majority Voting
Neural Networks
Random Forest
title Ensemble classifiers in remote sensing: a comparative analysis
title_full Ensemble classifiers in remote sensing: a comparative analysis
title_fullStr Ensemble classifiers in remote sensing: a comparative analysis
title_full_unstemmed Ensemble classifiers in remote sensing: a comparative analysis
title_short Ensemble classifiers in remote sensing: a comparative analysis
title_sort Ensemble classifiers in remote sensing: a comparative analysis
topic Accuracy
Bagging
Boosting
CART
Classifiers Ensemble
Land Cover and Land Use Maps
Linear Discriminant Classifier
Majority Voting
Neural Networks
Random Forest
topic_facet Accuracy
Bagging
Boosting
CART
Classifiers Ensemble
Land Cover and Land Use Maps
Linear Discriminant Classifier
Majority Voting
Neural Networks
Random Forest
url http://hdl.handle.net/10362/11671
visible 1