Creating classifier ensembles through meta-heuristic algorithms for aerial scene classification
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/ICPR48806.2021.9412938 http://hdl.handle.net/11449/233280 |
Resumo: | Convolutional Neural Networks (CNN) have been being widely employed to solve the challenging remote sensing task of aerial scene classification. Nevertheless, it is not straightforward to find single CNN models that can solve all aerial scene classification tasks, allowing the development of a better alternative, which is to fuse CNN-based classifiers into an ensemble. However, an appropriate choice of the classifiers that will belong to the ensemble is a critical factor, as it is unfeasible to employ all the possible classifiers in the literature. Therefore, this work proposes a novel framework based on meta-heuristic optimization for creating optimized ensembles in the context of aerial scene classification. The experimental results were performed across nine meta-heuristic algorithms and three aerial scene literature datasets, being compared in terms of effectiveness (accuracy), efficiency (execution time), and behavioral performance in different scenarios. Our results suggest that the Univariate Marginal Distribution Algorithm shows more effective and efficient results than other commonly used meta-heuristic algorithms, such as Genetic Programming and Particle Swarm Optimization. |
id |
UNSP_9ad41397d3cd2184d4b38c7b0d62465a |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/233280 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Creating classifier ensembles through meta-heuristic algorithms for aerial scene classificationConvolutional Neural Networks (CNN) have been being widely employed to solve the challenging remote sensing task of aerial scene classification. Nevertheless, it is not straightforward to find single CNN models that can solve all aerial scene classification tasks, allowing the development of a better alternative, which is to fuse CNN-based classifiers into an ensemble. However, an appropriate choice of the classifiers that will belong to the ensemble is a critical factor, as it is unfeasible to employ all the possible classifiers in the literature. Therefore, this work proposes a novel framework based on meta-heuristic optimization for creating optimized ensembles in the context of aerial scene classification. The experimental results were performed across nine meta-heuristic algorithms and three aerial scene literature datasets, being compared in terms of effectiveness (accuracy), efficiency (execution time), and behavioral performance in different scenarios. Our results suggest that the Univariate Marginal Distribution Algorithm shows more effective and efficient results than other commonly used meta-heuristic algorithms, such as Genetic Programming and Particle Swarm Optimization.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Institute of Science and Technology Universidade Federal de São PauloAustralian Institute for Machine Learning The University of AdelaideDepartment of Computing São Paulo State UniversityDepartment of Computing São Paulo State UniversityFAPESP: #2013/07375-0FAPESP: #2014/12236-1FAPESP: #2017/25908-6FAPESP: #2018/23908-1FAPESP: #2019/02205-5FAPESP: #2019/07665-4Universidade Federal de São Paulo (UNIFESP)The University of AdelaideUniversidade Estadual Paulista (UNESP)Ferreira, Álvaro R.de Rosa, Gustavo H. [UNESP]Papa, João P. [UNESP]Carneiro, GustavoFaria, Fabio A.2022-05-01T06:02:37Z2022-05-01T06:02:37Z2020-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject415-422http://dx.doi.org/10.1109/ICPR48806.2021.9412938Proceedings - International Conference on Pattern Recognition, p. 415-422.1051-4651http://hdl.handle.net/11449/23328010.1109/ICPR48806.2021.94129382-s2.0-85110546434Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings - International Conference on Pattern Recognitioninfo:eu-repo/semantics/openAccess2024-04-23T16:11:27Zoai:repositorio.unesp.br:11449/233280Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T20:44:40.467534Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Creating classifier ensembles through meta-heuristic algorithms for aerial scene classification |
title |
Creating classifier ensembles through meta-heuristic algorithms for aerial scene classification |
spellingShingle |
Creating classifier ensembles through meta-heuristic algorithms for aerial scene classification Ferreira, Álvaro R. |
title_short |
Creating classifier ensembles through meta-heuristic algorithms for aerial scene classification |
title_full |
Creating classifier ensembles through meta-heuristic algorithms for aerial scene classification |
title_fullStr |
Creating classifier ensembles through meta-heuristic algorithms for aerial scene classification |
title_full_unstemmed |
Creating classifier ensembles through meta-heuristic algorithms for aerial scene classification |
title_sort |
Creating classifier ensembles through meta-heuristic algorithms for aerial scene classification |
author |
Ferreira, Álvaro R. |
author_facet |
Ferreira, Álvaro R. de Rosa, Gustavo H. [UNESP] Papa, João P. [UNESP] Carneiro, Gustavo Faria, Fabio A. |
author_role |
author |
author2 |
de Rosa, Gustavo H. [UNESP] Papa, João P. [UNESP] Carneiro, Gustavo Faria, Fabio A. |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de São Paulo (UNIFESP) The University of Adelaide Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Ferreira, Álvaro R. de Rosa, Gustavo H. [UNESP] Papa, João P. [UNESP] Carneiro, Gustavo Faria, Fabio A. |
description |
Convolutional Neural Networks (CNN) have been being widely employed to solve the challenging remote sensing task of aerial scene classification. Nevertheless, it is not straightforward to find single CNN models that can solve all aerial scene classification tasks, allowing the development of a better alternative, which is to fuse CNN-based classifiers into an ensemble. However, an appropriate choice of the classifiers that will belong to the ensemble is a critical factor, as it is unfeasible to employ all the possible classifiers in the literature. Therefore, this work proposes a novel framework based on meta-heuristic optimization for creating optimized ensembles in the context of aerial scene classification. The experimental results were performed across nine meta-heuristic algorithms and three aerial scene literature datasets, being compared in terms of effectiveness (accuracy), efficiency (execution time), and behavioral performance in different scenarios. Our results suggest that the Univariate Marginal Distribution Algorithm shows more effective and efficient results than other commonly used meta-heuristic algorithms, such as Genetic Programming and Particle Swarm Optimization. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-01-01 2022-05-01T06:02:37Z 2022-05-01T06:02:37Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1109/ICPR48806.2021.9412938 Proceedings - International Conference on Pattern Recognition, p. 415-422. 1051-4651 http://hdl.handle.net/11449/233280 10.1109/ICPR48806.2021.9412938 2-s2.0-85110546434 |
url |
http://dx.doi.org/10.1109/ICPR48806.2021.9412938 http://hdl.handle.net/11449/233280 |
identifier_str_mv |
Proceedings - International Conference on Pattern Recognition, p. 415-422. 1051-4651 10.1109/ICPR48806.2021.9412938 2-s2.0-85110546434 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Proceedings - International Conference on Pattern Recognition |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
415-422 |
dc.source.none.fl_str_mv |
Scopus 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_ |
1808129240609062912 |