An analysis of heuristic metrics for classifier ensemble pruning based on ordered aggregation

Vista sencilla de ítem
dc.contributor.authorElsayed, Amgad Monir Mohamed
dc.contributor.authorOnieva Caracuel, Enrique
dc.contributor.authorWoźniak, Michał
dc.contributor.authorMartínez Muñoz, Gonzalo
dc.date.accessioned2024-11-22T08:00:46Z
dc.date.available2024-11-22T08:00:46Z
dc.date.issued2022-04
dc.date.updated2024-11-22T08:00:46Z
dc.description.abstractClassifier ensemble pruning is a strategy through which a subensemble can be identified via optimizing a predefined performance criterion. Choosing the optimum or suboptimum subensemble decreases the initial ensemble size and increases its predictive performance. In this article, a set of heuristic metrics will be analyzed to guide the pruning process. The analyzed metrics are based on modifying the order of the classifiers in the bagging algorithm, with selecting the first set in the queue. Some of these criteria include general accuracy, the complementarity of decisions, ensemble diversity, the margin of samples, minimum redundancy, discriminant classifiers, and margin hybrid diversity. The efficacy of those metrics is affected by the original ensemble size, the required subensemble size, the kind of individual classifiers, and the number of classes. While the efficiency is measured in terms of the computational cost and the memory space requirements. The performance of those metrics is assessed over fifteen binary and fifteen multiclass benchmark classification tasks, respectively. In addition, the behavior of those metrics against randomness is measured in terms of the distribution of their accuracy around the median. Results show that ordered aggregation is an efficient strategy to generate subensembles that improve both predictive performance as well as computational and memory complexities of the whole bagging ensemble.en
dc.description.sponsorshipThis project has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie grant agreement N 665959. Besides, this work was supported in part by the LOGISTAR project, funded by the European Union Horizon 2020 Research and Innovation Programme grant agreement No. 769142 . Michal Wozniak was partially supported by the Polish National Science Center under the grant No. 2017/27/B/ST6/01325. Gonzalo Martínez-Munoz was partially supported by PID2019-106827GB-I00 / AEI / 10.13039/501100011033.en
dc.identifier.citationMohammed, A. M., Onieva, E., Woźniak, M., & Martínez-Muñoz, G. (2022). An analysis of heuristic metrics for classifier ensemble pruning based on ordered aggregation. Pattern Recognition, 124. https://doi.org/10.1016/J.PATCOG.2021.108493
dc.identifier.doi10.1016/J.PATCOG.2021.108493
dc.identifier.issn0031-3203
dc.identifier.urihttp://hdl.handle.net/20.500.14454/2078
dc.language.isoeng
dc.publisherElsevier Ltd
dc.rights© 2021 The Authors
dc.subject.otherClassifier complementariness
dc.subject.otherClassifier ensemble
dc.subject.otherDifficult samples
dc.subject.otherEnsemble pruning
dc.subject.otherEnsemble selection
dc.subject.otherHeuristic optimization
dc.subject.otherMachine learning
dc.subject.otherOrdering-based pruning
dc.titleAn analysis of heuristic metrics for classifier ensemble pruning based on ordered aggregationen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.titlePattern Recognition
oaire.citation.volume124
oaire.licenseConditionhttps://creativecommons.org/licenses/by-nc-nd/4.0/
oaire.versionVoR
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
mohammed_analysis_2022.pdf
Tamaño:
883.43 KB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos