Logo do repositório
 
Publicação

Improving imbalanced land cover classification with k-means smote

2021-07-01Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorFonseca, Joao
dc.contributor.authorDouzas, Georgios
dc.contributor.authorBacao, Fernando
dc.contributor.institutionInformation Management Research Center (MagIC) - NOVA Information Management School
dc.contributor.institutionNOVA Information Management School (NOVA IMS)
dc.contributor.pblMDPI - Multidisciplinary Digital Publishing Institute
dc.date.accessioned2021-07-16T22:21:57Z
dc.date.available2021-07-16T22:21:57Z
dc.date.issued2021-07-01
dc.descriptionFonseca, J., Douzas, G., & Bacao, F. (2021). Improving imbalanced land cover classification with k-means smote: Detecting and oversampling distinctive minority spectral signatures. Information (Switzerland), 12(7), 1-20. [266]. https://doi.org/10.3390/info12070266
dc.description.abstractLand cover maps are a critical tool to support informed policy development, planning, and resource management decisions. With significant upsides, the automatic production of Land Use/Land Cover maps has been a topic of interest for the remote sensing community for several years, but it is still fraught with technical challenges. One such challenge is the imbalanced nature of most remotely sensed data. The asymmetric class distribution impacts negatively the performance of classifiers and adds a new source of error to the production of these maps. In this paper, we address the imbalanced learning problem, by using K-means and the Synthetic Minority Oversampling Technique (SMOTE) as an improved oversampling algorithm. K-means SMOTE improves the quality of newly created artificial data by addressing both the between-class imbalance, as traditional oversamplers do, but also the within-class imbalance, avoiding the generation of noisy data while effectively overcoming data imbalance. The performance of K-means SMOTE is compared to three popular oversampling methods (Random Oversampling, SMOTE and Borderline-SMOTE) using seven remote sensing benchmark datasets, three classifiers (Logistic Regression, K-Nearest Neighbors and Random Forest Classifier) and three evaluation metrics using a five-fold cross-validation approach with three different initialization seeds. The statistical analysis of the results show that the proposed method consistently outperforms the remaining oversamplers producing higher quality land cover classifications. These results suggest that LULC data can benefit significantly from the use of more sophisticated oversamplers as spectral signatures for the same class can vary according to geographical distribution.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent20
dc.format.extent3105198
dc.identifier.doi10.3390/info12070266
dc.identifier.issn2078-2489
dc.identifier.otherPURE: 32603681
dc.identifier.otherPURE UUID: 2816f083-b8be-413e-9afa-f807059fae92
dc.identifier.otherScopus: 85109407372
dc.identifier.otherWOS: 000676649900001
dc.identifier.otherORCID: /0000-0002-0834-0275/work/153306415
dc.identifier.urihttp://hdl.handle.net/10362/121176
dc.identifier.urlhttps://www.scopus.com/pages/publications/85109407372
dc.identifier.urlhttps://www.webofscience.com/wos/woscc/full-record/WOS:000676649900001
dc.language.isoeng
dc.peerreviewedyes
dc.relationinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/PCIF%2FSSI%2F0102%2F2017/PT
dc.relationinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/DSAIPA%2FAI%2F0100%2F2018/PT
dc.relationIPSTERS - IPSentinel Terrestrial Enhanced Recognition System
dc.relationhttps://doi.org/10.54499/DSAIPA/AI/0100/2018
dc.subjectClustering
dc.subjectData augmentation
dc.subjectImbalanced learning
dc.subjectLULC classification
dc.subjectOversampling
dc.subjectInformation Systems
dc.subjectSDG 15 - Life on Land
dc.titleImproving imbalanced land cover classification with k-means smoteen
dc.title.subtitleDetecting and oversampling distinctive minority spectral signaturesen
dc.typejournal article
degois.publication.firstPage1
degois.publication.issue7
degois.publication.lastPage20
degois.publication.titleInformation (Switzerland)
degois.publication.volume12
dspace.entity.typePublication
oaire.awardNumberPCIF/SSI/0102/2017
oaire.awardNumberDSAIPA/AI/0100/2018
oaire.awardTitleIPSTERS - IPSentinel Terrestrial Enhanced Recognition System
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/PCIF%2FSSI%2F0102%2F2017/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/DSAIPA%2FAI%2F0100%2F2018/PT
oaire.fundingStream3599-PPCDT
oaire.fundingStream3599-PPCDT
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccess
relation.isProjectOfPublication7f731199-68cf-46d5-b72b-1ae7819b7e3a
relation.isProjectOfPublication43e15b8d-4c9d-4c47-854f-e2eaa23788e9
relation.isProjectOfPublication.latestForDiscovery43e15b8d-4c9d-4c47-854f-e2eaa23788e9

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Improving_Land_Cover_Classification_K_Means_SMOTE.pdf
Tamanho:
2.96 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

NIMS: MagIC - Artigos em revista internacional com arbitragem científica (Peer-Review articles in international journals)