dc.contributor.author | Rosales Pérez, Alejandro | |
dc.contributor.author | García López, Salvador | |
dc.contributor.author | Herrera Triguero, Francisco | |
dc.date.accessioned | 2022-05-04T11:41:55Z | |
dc.date.available | 2022-05-04T11:41:55Z | |
dc.date.issued | 2022-04-21 | |
dc.identifier.citation | Published version: A. Rosales-Pérez, S. García and F. Herrera, "Handling Imbalanced Classification Problems With Support Vector Machines via Evolutionary Bilevel Optimization," in IEEE Transactions on Cybernetics, doi: [10.1109/TCYB.2022.3163974] | es_ES |
dc.identifier.uri | http://hdl.handle.net/10481/74696 | |
dc.description | This work was partially supported by Project PID2020-119478GBI00
funded by MICINN/AEI/10.13039/501100011033 and by
Project A-TIC-434-UGR20 funded by FEDER/Junta de Andaluc´ıa-
Consejer´ıa de Transformaci´on Econ´omica, Industria, Conocimiento
y Universidades. The authors acknowledge the support from “Laboratorio
de Superc´omputo del Baj´ıo” through project 300832 from
CONACyT. | es_ES |
dc.description.abstract | Support vector machines are popular
learning algorithms to deal with binary classification
problems. They traditionally assume equal misclassification
costs for each class; however, real-world problems
may have an uneven class distribution. This paper
introduces EBCS-SVM: Evolutionary Bilevel Costsensitive
Support Vector Machines. EBCS-SVM handles
imbalanced classification problems by simultaneously
learning the support vectors and optimizing the
SVM hyper-parameters, which comprise the kernel
parameter and misclassification costs. The resulting
optimization problem is a bilevel problem, where the
lower-level determines the support vectors and the
upper-level the hyper-parameters. This optimization
problem is solved using an evolutionary algorithm at
the upper-level and Sequential Minimal Optimization
at the lower-level. These two methods work in a nested
fashion, i.e., the optimal support vectors help guide
the search of the hyper-parameters, and the lower-level
is initialized based on previous successful solutions.
The proposed method is assessed using 70 datasets of
imbalanced classification and compared with several
state-of-the-art methods. The experimental results,
supported by a Bayesian test, provided evidence of the
effectiveness of EBCS-SVM when working with highly
imbalanced datasets. | es_ES |
dc.description.sponsorship | PID2020-119478GBI00
funded by MICINN/AEI/10.13039/501100011033 | es_ES |
dc.description.sponsorship | A-TIC-434-UGR20 funded by FEDER/Junta de Andaluc´ıa-
Consejer´ıa de Transformaci´on Econ´omica, Industria, Conocimiento
y Universidades | es_ES |
dc.description.sponsorship | 300832 from
CONACyT | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | IEEE | es_ES |
dc.rights | Atribución-NoComercial-SinDerivadas 3.0 España | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ | * |
dc.subject | Support Vector Machines | es_ES |
dc.subject | Imbalanced classification | es_ES |
dc.subject | Data Preprocessing | es_ES |
dc.subject | Evolutionary algorithms | es_ES |
dc.subject | Bilevel optimization | es_ES |
dc.title | Handling Imbalanced Classification Problems with Support Vector Machines via Evolutionary Bilevel Optimization | es_ES |
dc.type | journal article | es_ES |
dc.rights.accessRights | open access | es_ES |
dc.type.hasVersion | SMUR | es_ES |