A nature-inspired feature selection approach based on hypercomplex information
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.asoc.2020.106453 http://hdl.handle.net/11449/197275 |
Resumo: | Feature selection for a given model can be transformed into an optimization task. The essential idea behind it is to find the most suitable subset of features according to some criterion. Nature-inspired optimization can mitigate this problem by producing compelling yet straightforward solutions when dealing with complicated fitness functions. Additionally, new mathematical representations, such as quaternions and octonions, are being used to handle higher-dimensional spaces. In this context, we are introducing a meta-heuristic optimization framework in a hypercomplex-based feature selection, where hypercomplex numbers are mapped to real-valued solutions and then transferred onto a boolean hypercube by a sigmoid function. The intended hypercomplex feature selection is tested for several meta-heuristic algorithms and hypercomplex representations, achieving results comparable to some state-of-the-art approaches. The good results achieved by the proposed approach make it a promising tool amongst feature selection research. (C) 2020 Elsevier B.V. All rights reserved. |
id |
UNSP_2de7f81ca646f2c8bdc639296df84315 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/197275 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A nature-inspired feature selection approach based on hypercomplex informationMeta-heuristic optimizationHypercomplex spacesFeature selectionFeature selection for a given model can be transformed into an optimization task. The essential idea behind it is to find the most suitable subset of features according to some criterion. Nature-inspired optimization can mitigate this problem by producing compelling yet straightforward solutions when dealing with complicated fitness functions. Additionally, new mathematical representations, such as quaternions and octonions, are being used to handle higher-dimensional spaces. In this context, we are introducing a meta-heuristic optimization framework in a hypercomplex-based feature selection, where hypercomplex numbers are mapped to real-valued solutions and then transferred onto a boolean hypercube by a sigmoid function. The intended hypercomplex feature selection is tested for several meta-heuristic algorithms and hypercomplex representations, achieving results comparable to some state-of-the-art approaches. The good results achieved by the proposed approach make it a promising tool amongst feature selection research. (C) 2020 Elsevier B.V. All rights reserved.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Sao Paulo State Univ, Dept Comp, Ave Eng Luiz Edmundo Carrijo Coube 14-01, BR-17033360 Bauru, SP, BrazilMiddlesex Univ, Sch Sci & Technol, London NW4 4BT, EnglandSao Paulo State Univ, Dept Comp, Ave Eng Luiz Edmundo Carrijo Coube 14-01, BR-17033360 Bauru, SP, BrazilFAPESP: 2013/07375-0FAPESP: 2014/12236-1FAPESP: 2016/19403-6FAPESP: 2017/02286-0FAPESP: 2017/25908-6FAPESP: 2018/219345FAPESP: 2019/02205-5CNPq: 307066/2017-7CNPq: 427968/2018-6Elsevier B.V.Universidade Estadual Paulista (Unesp)Middlesex UnivRosa, Gustavo H. de [UNESP]Papa, Joao P. [UNESP]Yang, Xin-She2020-12-10T20:11:45Z2020-12-10T20:11:45Z2020-09-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article11http://dx.doi.org/10.1016/j.asoc.2020.106453Applied Soft Computing. Amsterdam: Elsevier, v. 94, 11 p., 2020.1568-4946http://hdl.handle.net/11449/19727510.1016/j.asoc.2020.106453WOS:000565708500003Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengApplied Soft Computinginfo:eu-repo/semantics/openAccess2024-04-23T16:10:46Zoai:repositorio.unesp.br:11449/197275Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-04-23T16:10:46Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A nature-inspired feature selection approach based on hypercomplex information |
title |
A nature-inspired feature selection approach based on hypercomplex information |
spellingShingle |
A nature-inspired feature selection approach based on hypercomplex information Rosa, Gustavo H. de [UNESP] Meta-heuristic optimization Hypercomplex spaces Feature selection |
title_short |
A nature-inspired feature selection approach based on hypercomplex information |
title_full |
A nature-inspired feature selection approach based on hypercomplex information |
title_fullStr |
A nature-inspired feature selection approach based on hypercomplex information |
title_full_unstemmed |
A nature-inspired feature selection approach based on hypercomplex information |
title_sort |
A nature-inspired feature selection approach based on hypercomplex information |
author |
Rosa, Gustavo H. de [UNESP] |
author_facet |
Rosa, Gustavo H. de [UNESP] Papa, Joao P. [UNESP] Yang, Xin-She |
author_role |
author |
author2 |
Papa, Joao P. [UNESP] Yang, Xin-She |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Middlesex Univ |
dc.contributor.author.fl_str_mv |
Rosa, Gustavo H. de [UNESP] Papa, Joao P. [UNESP] Yang, Xin-She |
dc.subject.por.fl_str_mv |
Meta-heuristic optimization Hypercomplex spaces Feature selection |
topic |
Meta-heuristic optimization Hypercomplex spaces Feature selection |
description |
Feature selection for a given model can be transformed into an optimization task. The essential idea behind it is to find the most suitable subset of features according to some criterion. Nature-inspired optimization can mitigate this problem by producing compelling yet straightforward solutions when dealing with complicated fitness functions. Additionally, new mathematical representations, such as quaternions and octonions, are being used to handle higher-dimensional spaces. In this context, we are introducing a meta-heuristic optimization framework in a hypercomplex-based feature selection, where hypercomplex numbers are mapped to real-valued solutions and then transferred onto a boolean hypercube by a sigmoid function. The intended hypercomplex feature selection is tested for several meta-heuristic algorithms and hypercomplex representations, achieving results comparable to some state-of-the-art approaches. The good results achieved by the proposed approach make it a promising tool amongst feature selection research. (C) 2020 Elsevier B.V. All rights reserved. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-10T20:11:45Z 2020-12-10T20:11:45Z 2020-09-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1016/j.asoc.2020.106453 Applied Soft Computing. Amsterdam: Elsevier, v. 94, 11 p., 2020. 1568-4946 http://hdl.handle.net/11449/197275 10.1016/j.asoc.2020.106453 WOS:000565708500003 |
url |
http://dx.doi.org/10.1016/j.asoc.2020.106453 http://hdl.handle.net/11449/197275 |
identifier_str_mv |
Applied Soft Computing. Amsterdam: Elsevier, v. 94, 11 p., 2020. 1568-4946 10.1016/j.asoc.2020.106453 WOS:000565708500003 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Applied Soft Computing |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
11 |
dc.publisher.none.fl_str_mv |
Elsevier B.V. |
publisher.none.fl_str_mv |
Elsevier B.V. |
dc.source.none.fl_str_mv |
Web of Science reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1799964770793684992 |