Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE

Detalhes bibliográficos
Autor(a) principal: Douzas, Georgios
Data de Publicação: 2019
Outros Autores: Bacao, Fernando
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Texto Completo: http://hdl.handle.net/10362/158370
Resumo: Douzas, G., & Bacao, F. (2019). Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE. Information Sciences, 501, 118-135. https://doi.org/10.1016/j.ins.2019.06.007
id RCAP_674fd1816cfc13aeffedb07bca47ee32
oai_identifier_str oai:run.unl.pt:10362/158370
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 Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTEClassificationData generationImbalanced learningOversamplingSMOTESupervised learningSoftwareControl and Systems EngineeringTheoretical Computer ScienceComputer Science ApplicationsInformation Systems and ManagementArtificial IntelligenceDouzas, G., & Bacao, F. (2019). Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE. Information Sciences, 501, 118-135. https://doi.org/10.1016/j.ins.2019.06.007Classification of imbalanced datasets is a challenging task for standard algorithms. Although many methods exist to address this problem in different ways, generating artificial data for the minority class is a more general approach compared to algorithmic modifications. SMOTE algorithm, as well as any other oversampling method based on the SMOTE mechanism, generates synthetic samples along line segments that join minority class instances. In this paper we propose Geometric SMOTE (G-SMOTE) as a enhancement of the SMOTE data generation mechanism. G-SMOTE generates synthetic samples in a geometric region of the input space, around each selected minority instance. While in the basic configuration this region is a hyper-sphere, G-SMOTE allows its deformation to a hyper-spheroid. The performance of G-SMOTE is compared against SMOTE as well as baseline methods. We present empirical results that show a significant improvement in the quality of the generated data when G-SMOTE is used as an oversampling algorithm. An implementation of G-SMOTE is made available in the Python programming language.Information Management Research Center (MagIC) - NOVA Information Management SchoolNOVA Information Management School (NOVA IMS)RUNDouzas, GeorgiosBacao, Fernando2023-09-27T22:18:14Z2019-10-012019-10-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article18application/pdfhttp://hdl.handle.net/10362/158370eng0020-0255PURE: 13784337https://doi.org/10.1016/j.ins.2019.06.007info: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:RCAAP2024-05-22T18:14:42Zoai:run.unl.pt:10362/158370Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:45:14.715561Repositórios 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 Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE
title Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE
spellingShingle Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE
Douzas, Georgios
Classification
Data generation
Imbalanced learning
Oversampling
SMOTE
Supervised learning
Software
Control and Systems Engineering
Theoretical Computer Science
Computer Science Applications
Information Systems and Management
Artificial Intelligence
title_short Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE
title_full Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE
title_fullStr Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE
title_full_unstemmed Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE
title_sort Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE
author Douzas, Georgios
author_facet Douzas, Georgios
Bacao, Fernando
author_role author
author2 Bacao, Fernando
author2_role 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
dc.subject.por.fl_str_mv Classification
Data generation
Imbalanced learning
Oversampling
SMOTE
Supervised learning
Software
Control and Systems Engineering
Theoretical Computer Science
Computer Science Applications
Information Systems and Management
Artificial Intelligence
topic Classification
Data generation
Imbalanced learning
Oversampling
SMOTE
Supervised learning
Software
Control and Systems Engineering
Theoretical Computer Science
Computer Science Applications
Information Systems and Management
Artificial Intelligence
description Douzas, G., & Bacao, F. (2019). Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE. Information Sciences, 501, 118-135. https://doi.org/10.1016/j.ins.2019.06.007
publishDate 2019
dc.date.none.fl_str_mv 2019-10-01
2019-10-01T00:00:00Z
2023-09-27T22:18:14Z
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/10362/158370
url http://hdl.handle.net/10362/158370
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 0020-0255
PURE: 13784337
https://doi.org/10.1016/j.ins.2019.06.007
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 18
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_ 1833596938162798592

Registros relacionados