2026-04-23T00:07:27Zhttps://riubu.ubu.es/oai/request

oai:riubu.ubu.es:10259/100322025-01-25T01:05:24Zcom_10259_4219com_10259_5086com_10259_2604col_10259_4220

Rodríguez Diez, Juan José 477 600 0000-0002-3291-2739 Juez Gil, Mario 747 600 0000-0002-2510-6421 Arnaiz González, Álvar 39 600 0000-0001-6965-0237 Kuncheva, Ludmila I. . 37a0866d-eced-4e47-913c-cdc9943f0a48 600 2025-01-24T09:21:02Z 2025-01-24T09:21:02Z 2020-08 0957-4174 http://hdl.handle.net/10259/10032 10.1016/j.eswa.2020.113376 Over the past few decades, the remarkable prediction capabilities of ensemble methods have been used within a wide range of applications. Maximization of base-model ensemble accuracy and diversity are the keys to the heightened performance of these methods. One way to achieve diversity for training the base models is to generate artificial/synthetic instances for their incorporation with the original instances. Recently, the mixup method was proposed for improving the classification power of deep neural networks (Zhang, Cissé, Dauphin, and Lopez-Paz, 2017). Mixup method generates artificial instances by combining pairs of instances and their labels, these new instances are used for training the neural networks promoting its regularization. In this paper, new regression tree ensembles trained with mixup, which we will refer to as Mixup Regression Forest, are presented and tested. The experimental study with 61 datasets showed that the mixup approach improved the results of both Random Forest and Rotation Forest. This work was supported through project TIN2015-67534-P (MINECO/FEDER, UE) of the Ministerio de Economía y Competitividad of the Spanish Government, project BU085P17 (JCyL/FEDER, UE) of the Junta de Castilla y León (both projects co-financed through European Union FEDER funds), and by the Consejería de Educación of the Junta de Castilla y León and the European Social Fund through a pre-doctoral grant (EDU/1100/2017). The third author is grateful for a Mobility Grant (CAS19/00100) from the Ministerio de Ciencia, Innovación y Universidades of the Spanish Government. The authors gratefully acknowledge the support of NVIDIA Corporation and its donation of the TITAN Xp GPUs that facilitated this research. application/pdf eng Elsevier Expert Systems with Applications. 2020, V. 151, 113376 https://doi.org/10.1016/j.eswa.2020.113376 info:eu-repo/grantAgreement/MINECO//TIN2015-67534-P/ES/ALGORITMOS DE ENSEMBLES PARA PROBLEMAS DE SALIDAS MULTIPLES. NUEVOS DESARROLLOS Y APLICACIONES/ info:eu-repo/grantAgreement/Junta de Castilla y León//BU085P17//Minería de datos para le mejora del mantenimiento y disponibilidad de máquinas de altas presiones/ info:eu-repo/grantAgreement/MICIU/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/CAS19%2F00100/ES/ Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess Mixup Regression Random forest Rotation forest Redes neuronales artificiales Neural networks (Computer science) An experimental evaluation of mixup regression forests info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Expert Systems with Applications 151 113376 THUMBNAIL Rodriguez-esa_2020.pdf.jpg Rodriguez-esa_2020.pdf.jpg IM Thumbnail image/jpeg 3841 https://riubu.ubu.es/bitstream/10259/10032/4/Rodriguez-esa_2020.pdf.jpg 72589984d740d82f10f27d1b236c4fe5 MD5 4 LICENSE license.txt license.txt text/plain; charset=utf-8 999 https://riubu.ubu.es/bitstream/10259/10032/3/license.txt b295bcbce42e2caabeb0c623d3860c06 MD5 3 CC-LICENSE license_rdf license_rdf application/rdf+xml; charset=utf-8 805 https://riubu.ubu.es/bitstream/10259/10032/2/license_rdf 4460e5956bc1d1639be9ae6146a50347 MD5 2 ORIGINAL Rodriguez-esa_2020.pdf Rodriguez-esa_2020.pdf application/pdf 2183277 https://riubu.ubu.es/bitstream/10259/10032/1/Rodriguez-esa_2020.pdf f1350b52898073a844f878e27bdf6a8a MD5 1 10259/10032 oai:riubu.ubu.es:10259/10032 2025-01-25 02:05:24.898 Repositorio Institucional de la Universidad de Burgos bubrep@ubu.es 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