Publication:
Optimum Bayesian thresholds for rebalanced classification problems using class-switching ensembles

Simple item page
dc.affiliation.dptoUC3M. Departamento de Teoría de la Señal y Comunicacioneses
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Tratamiento de la Señal y Aprendizaje (GTSA)es
dc.contributor.authorGutiérrez López, Aitor
dc.contributor.authorGonzález Serrano, Francisco Javier
dc.contributor.authorFigueiras, Aníbal
dc.contributor.funderMinisterio de Ciencia e Innovación (España)es
dc.date.accessioned2023-09-28T12:31:36Z
dc.date.available2023-09-28T12:31:36Z
dc.date.issued2023-03
dc.description.abstractAsymmetric label switching is an effective and principled method for creating a diverse ensemble of learners for imbalanced classification problems. This technique can be combined with other rebalancing mechanisms, such as those based on cost policies or class proportion modifications. In this study, and under the Bayesian theory framework, we specify the optimal decision thresholds for the combination of these mechanisms. In addition, we propose using a gating network to aggregate the learners contributions as an additional mechanism to improve the overall performance of the system.en
dc.description.sponsorshipWe thank the anonymous reviewers for their valuable suggestions and comments. This work is partially funded by Project PID2021-125652OB-I00 from the Ministerio de Ciencia e Innovación of Spain. Funding for APC: Universidad Carlos III de Madrid (Read & Publish Agreement CRUE-CSIC 2022). In memoriam: Prof. Aníbal R. Figueiras-Vidal (1950-2022).en
dc.format.extent8
dc.identifier.bibliographicCitationGutiérrez-López, A., Gonzalez-Serrano, F., & Figueiras-Vidal, A. R. (2023). Optimum Bayesian thresholds for rebalanced classification problems using class-switching ensembles. Pattern Recognition, 135, 109158.en
dc.identifier.doihttps://doi.org/10.1016/j.patcog.2022.109158
dc.identifier.issn0031-3203
dc.identifier.publicationfirstpage1
dc.identifier.publicationissue109158
dc.identifier.publicationlastpage8
dc.identifier.publicationtitlePattern Recognitionen
dc.identifier.publicationvolume135
dc.identifier.urihttps://hdl.handle.net/10016/38469
dc.identifier.uxxiAR/0000031345
dc.language.isoengen
dc.publisherElsevieren
dc.relation.projectIDGobierno de España. PID2021-125652OB-I00es
dc.relation.projectIDAT-2022
dc.rights© 2022 The Author(s).en
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 España*
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subject.ecienciaTelecomunicacioneses
dc.subject.otherBayesian frameworken
dc.subject.otherEnsemblesen
dc.subject.otherRebalancing techniquesen
dc.subject.otherImbalanced classificationen
dc.subject.otherLabel switchingen
dc.titleOptimum Bayesian thresholds for rebalanced classification problems using class-switching ensemblesen
dc.typeresearch article*
dc.type.hasVersionVoR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Optimum_PR_2023.pdf
Size:
805.04 KB
Format:
Adobe Portable Document Format
Download
Collections
DTSC - GTSA - Artículos de Revistas