A Novel Learning-Based Binarization Scheme Selector for Swarm Algorithms Solving Combinatorial Problems

Currently, industry is undergoing an exponential increase in binary-based combinatorial problems. In this regard, metaheuristics have been a common trend in the field in order to design approaches to successfully solve them. Thus, a well-known strategy includes the employment of continuous swarm-bas...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	José Lemus-Romani, Marcelo Becerra-Rozas, Broderick Crawford, Ricardo Soto, Felipe Cisternas-Caneo, Emanuel Vega, Mauricio Castillo, Diego Tapia, Gino Astorga, Wenceslao Palma, Carlos Castro, José García
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	combinatorial problems metaheuristics binarization scheme SARSA Q-learning machine learning Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/8ca18ce3021a4d73bff5c1776622d0a9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8ca18ce3021a4d73bff5c1776622d0a9
record_format	dspace
spelling	oai:doaj.org-article:8ca18ce3021a4d73bff5c1776622d0a92021-11-25T18:16:52ZA Novel Learning-Based Binarization Scheme Selector for Swarm Algorithms Solving Combinatorial Problems10.3390/math92228872227-7390https://doaj.org/article/8ca18ce3021a4d73bff5c1776622d0a92021-11-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/22/2887https://doaj.org/toc/2227-7390Currently, industry is undergoing an exponential increase in binary-based combinatorial problems. In this regard, metaheuristics have been a common trend in the field in order to design approaches to successfully solve them. Thus, a well-known strategy includes the employment of continuous swarm-based algorithms transformed to perform in binary environments. In this work, we propose a hybrid approach that contains discrete smartly adapted population-based strategies to efficiently tackle binary-based problems. The proposed approach employs a reinforcement learning technique, known as SARSA (State–Action–Reward–State–Action), in order to utilize knowledge based on the run time. In order to test the viability and competitiveness of our proposal, we compare discrete state-of-the-art algorithms smartly assisted by SARSA. Finally, we illustrate interesting results where the proposed hybrid outperforms other approaches, thus, providing a novel option to tackle these types of problems in industry.José Lemus-RomaniMarcelo Becerra-RozasBroderick CrawfordRicardo SotoFelipe Cisternas-CaneoEmanuel VegaMauricio CastilloDiego TapiaGino AstorgaWenceslao PalmaCarlos CastroJosé GarcíaMDPI AGarticlecombinatorial problemsmetaheuristicsbinarization schemeSARSAQ-learningmachine learningMathematicsQA1-939ENMathematics, Vol 9, Iss 2887, p 2887 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	combinatorial problems metaheuristics binarization scheme SARSA Q-learning machine learning Mathematics QA1-939
spellingShingle	combinatorial problems metaheuristics binarization scheme SARSA Q-learning machine learning Mathematics QA1-939 José Lemus-Romani Marcelo Becerra-Rozas Broderick Crawford Ricardo Soto Felipe Cisternas-Caneo Emanuel Vega Mauricio Castillo Diego Tapia Gino Astorga Wenceslao Palma Carlos Castro José García A Novel Learning-Based Binarization Scheme Selector for Swarm Algorithms Solving Combinatorial Problems
description	Currently, industry is undergoing an exponential increase in binary-based combinatorial problems. In this regard, metaheuristics have been a common trend in the field in order to design approaches to successfully solve them. Thus, a well-known strategy includes the employment of continuous swarm-based algorithms transformed to perform in binary environments. In this work, we propose a hybrid approach that contains discrete smartly adapted population-based strategies to efficiently tackle binary-based problems. The proposed approach employs a reinforcement learning technique, known as SARSA (State–Action–Reward–State–Action), in order to utilize knowledge based on the run time. In order to test the viability and competitiveness of our proposal, we compare discrete state-of-the-art algorithms smartly assisted by SARSA. Finally, we illustrate interesting results where the proposed hybrid outperforms other approaches, thus, providing a novel option to tackle these types of problems in industry.
format	article
author	José Lemus-Romani Marcelo Becerra-Rozas Broderick Crawford Ricardo Soto Felipe Cisternas-Caneo Emanuel Vega Mauricio Castillo Diego Tapia Gino Astorga Wenceslao Palma Carlos Castro José García
author_facet	José Lemus-Romani Marcelo Becerra-Rozas Broderick Crawford Ricardo Soto Felipe Cisternas-Caneo Emanuel Vega Mauricio Castillo Diego Tapia Gino Astorga Wenceslao Palma Carlos Castro José García
author_sort	José Lemus-Romani
title	A Novel Learning-Based Binarization Scheme Selector for Swarm Algorithms Solving Combinatorial Problems
title_short	A Novel Learning-Based Binarization Scheme Selector for Swarm Algorithms Solving Combinatorial Problems
title_full	A Novel Learning-Based Binarization Scheme Selector for Swarm Algorithms Solving Combinatorial Problems
title_fullStr	A Novel Learning-Based Binarization Scheme Selector for Swarm Algorithms Solving Combinatorial Problems
title_full_unstemmed	A Novel Learning-Based Binarization Scheme Selector for Swarm Algorithms Solving Combinatorial Problems
title_sort	novel learning-based binarization scheme selector for swarm algorithms solving combinatorial problems
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8ca18ce3021a4d73bff5c1776622d0a9
work_keys_str_mv	AT joselemusromani anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT marcelobecerrarozas anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT broderickcrawford anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT ricardosoto anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT felipecisternascaneo anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT emanuelvega anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT mauriciocastillo anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT diegotapia anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT ginoastorga anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT wenceslaopalma anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT carloscastro anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT josegarcia anovellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT joselemusromani novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT marcelobecerrarozas novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT broderickcrawford novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT ricardosoto novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT felipecisternascaneo novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT emanuelvega novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT mauriciocastillo novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT diegotapia novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT ginoastorga novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT wenceslaopalma novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT carloscastro novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems AT josegarcia novellearningbasedbinarizationschemeselectorforswarmalgorithmssolvingcombinatorialproblems
_version_	1718411394781544448

A Novel Learning-Based Binarization Scheme Selector for Swarm Algorithms Solving Combinatorial Problems

Ejemplares similares