Imbalanced learning in land cover classification

Bibliographic Details
Main Author: Douzas, Georgios
Publication Date: 2019
Other Authors: Bacao, Fernando, Fonseca, Joao, Khudinyan, Manvel
Format: Article
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/10362/91747
Summary: Douzas, G., Bacao, F., Fonseca, J., & Khudinyan, M. (2019). Imbalanced learning in land cover classification: Improving minority classes' prediction accuracy using the geometric SMOTE algorithm. Remote Sensing, 11(24), [3040]. https://doi.org/10.3390/rs11243040
id RCAP_6a26e8239fd365d914fa1ea82fdc2cb7
oai_identifier_str oai:run.unl.pt:10362/91747
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Imbalanced learning in land cover classificationImproving minority classes' prediction accuracy using the geometric SMOTE algorithmClass imbalanceGeometric-SMOTEImbalanced learningLULC classificationOversamplingEarth and Planetary Sciences(all)SDG 15 - Life on LandDouzas, G., Bacao, F., Fonseca, J., & Khudinyan, M. (2019). Imbalanced learning in land cover classification: Improving minority classes' prediction accuracy using the geometric SMOTE algorithm. Remote Sensing, 11(24), [3040]. https://doi.org/10.3390/rs11243040The automatic production of land use/land cover maps continues to be a challenging problem, with important impacts on the ability to promote sustainability and good resource management. The ability to build robust automatic classifiers and produce accurate maps can have a significant impact on the way we manage and optimize natural resources. The difficulty in achieving these results comes from many different factors, such as data quality and uncertainty. In this paper, we address the imbalanced learning problem, a common and difficult conundrum in remote sensing that affects the quality of classification results, by proposing Geometric-SMOTE, a novel oversampling method, as a tool for addressing the imbalanced learning problem in remote sensing. Geometric-SMOTE is a sophisticated oversampling algorithm which increases the quality of the instances generated in previous methods, such as the synthetic minority oversampling technique. The performance of Geometric- SMOTE, in the LUCAS (Land Use/Cover Area Frame Survey) dataset, is compared to other oversamplers using a variety of classifiers. The results show that Geometric-SMOTE significantly outperforms all the other oversamplers and improves the robustness of the classifiers. These results indicate that, when using imbalanced datasets, remote sensing researchers should consider the use of these new generation oversamplers to increase the quality of the classification results.Information Management Research Center (MagIC) - NOVA Information Management SchoolNOVA Information Management School (NOVA IMS)RUNDouzas, GeorgiosBacao, FernandoFonseca, JoaoKhudinyan, Manvel2020-01-24T23:37:26Z2019-12-012019-12-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10362/91747eng2072-4292PURE: 16503950https://doi.org/10.3390/rs11243040info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-22T17:43:07Zoai:run.unl.pt:10362/91747Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:14:34.544007Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Imbalanced learning in land cover classification
Improving minority classes' prediction accuracy using the geometric SMOTE algorithm
title Imbalanced learning in land cover classification
spellingShingle Imbalanced learning in land cover classification
Douzas, Georgios
Class imbalance
Geometric-SMOTE
Imbalanced learning
LULC classification
Oversampling
Earth and Planetary Sciences(all)
SDG 15 - Life on Land
title_short Imbalanced learning in land cover classification
title_full Imbalanced learning in land cover classification
title_fullStr Imbalanced learning in land cover classification
title_full_unstemmed Imbalanced learning in land cover classification
title_sort Imbalanced learning in land cover classification
author Douzas, Georgios
author_facet Douzas, Georgios
Bacao, Fernando
Fonseca, Joao
Khudinyan, Manvel
author_role author
author2 Bacao, Fernando
Fonseca, Joao
Khudinyan, Manvel
author2_role author
author
author
dc.contributor.none.fl_str_mv Information Management Research Center (MagIC) - NOVA Information Management School
NOVA Information Management School (NOVA IMS)
RUN
dc.contributor.author.fl_str_mv Douzas, Georgios
Bacao, Fernando
Fonseca, Joao
Khudinyan, Manvel
dc.subject.por.fl_str_mv Class imbalance
Geometric-SMOTE
Imbalanced learning
LULC classification
Oversampling
Earth and Planetary Sciences(all)
SDG 15 - Life on Land
topic Class imbalance
Geometric-SMOTE
Imbalanced learning
LULC classification
Oversampling
Earth and Planetary Sciences(all)
SDG 15 - Life on Land
description Douzas, G., Bacao, F., Fonseca, J., & Khudinyan, M. (2019). Imbalanced learning in land cover classification: Improving minority classes' prediction accuracy using the geometric SMOTE algorithm. Remote Sensing, 11(24), [3040]. https://doi.org/10.3390/rs11243040
publishDate 2019
dc.date.none.fl_str_mv 2019-12-01
2019-12-01T00:00:00Z
2020-01-24T23:37:26Z
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://hdl.handle.net/10362/91747
url http://hdl.handle.net/10362/91747
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2072-4292
PURE: 16503950
https://doi.org/10.3390/rs11243040
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.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833596545093599232

Similar Items