Nature-inspired optimum-path forest
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1007/s12065-021-00664-0 http://hdl.handle.net/11449/233469 |
Resumo: | The Optimum-Path Forest (OPF) is a graph-based classifier that models pattern recognition problems as a graph partitioning task. The OPF learning process is performed in a competitive fashion where a few key samples (i.e., prototypes) try to conquer the remaining training samples to build optimum-path trees (OPT). The task of selecting prototypes is paramount to obtain high-quality OPTs, thus being of great importance to the classifier. The most used approach computes a minimum spanning tree over the training set and promotes the samples nearby the decision boundary as prototypes. Although such methodology has obtained promising results in the past year, it can be prone to overfitting. In this work, it is proposed a metaheuristic-based approach (OPFmh) for the selection of prototypes, being such a task modeled as an optimization problem whose goal is to improve accuracy. The experimental results showed the OPFmh can reduce overfitting, as well as the number of prototypes in many situations. Moreover, OPFmh achieved competitive accuracies and outperformed OPF in the experimental scenarios. |
id |
UNSP_19fdc22b72ff3b7a8a9873988ebc59d4 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/233469 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Nature-inspired optimum-path forestMeta-heuristicsOptimum-Path ForestPattern ClassificationThe Optimum-Path Forest (OPF) is a graph-based classifier that models pattern recognition problems as a graph partitioning task. The OPF learning process is performed in a competitive fashion where a few key samples (i.e., prototypes) try to conquer the remaining training samples to build optimum-path trees (OPT). The task of selecting prototypes is paramount to obtain high-quality OPTs, thus being of great importance to the classifier. The most used approach computes a minimum spanning tree over the training set and promotes the samples nearby the decision boundary as prototypes. Although such methodology has obtained promising results in the past year, it can be prone to overfitting. In this work, it is proposed a metaheuristic-based approach (OPFmh) for the selection of prototypes, being such a task modeled as an optimization problem whose goal is to improve accuracy. The experimental results showed the OPFmh can reduce overfitting, as well as the number of prototypes in many situations. Moreover, OPFmh achieved competitive accuracies and outperformed OPF in the experimental scenarios.School of Sciences UNESP - São Paulo State UniversitySchool of Sciences UNESP - São Paulo State UniversityUniversidade Estadual Paulista (UNESP)Afonso, Luis Claudio Sugi [UNESP]Rodrigues, Douglas [UNESP]Papa, João Paulo [UNESP]2022-05-01T08:45:01Z2022-05-01T08:45:01Z2021-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1007/s12065-021-00664-0Evolutionary Intelligence.1864-59171864-5909http://hdl.handle.net/11449/23346910.1007/s12065-021-00664-02-s2.0-85114109403Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengEvolutionary Intelligenceinfo:eu-repo/semantics/openAccess2024-04-23T16:11:00Zoai:repositorio.unesp.br:11449/233469Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-04-23T16:11Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Nature-inspired optimum-path forest |
title |
Nature-inspired optimum-path forest |
spellingShingle |
Nature-inspired optimum-path forest Afonso, Luis Claudio Sugi [UNESP] Meta-heuristics Optimum-Path Forest Pattern Classification |
title_short |
Nature-inspired optimum-path forest |
title_full |
Nature-inspired optimum-path forest |
title_fullStr |
Nature-inspired optimum-path forest |
title_full_unstemmed |
Nature-inspired optimum-path forest |
title_sort |
Nature-inspired optimum-path forest |
author |
Afonso, Luis Claudio Sugi [UNESP] |
author_facet |
Afonso, Luis Claudio Sugi [UNESP] Rodrigues, Douglas [UNESP] Papa, João Paulo [UNESP] |
author_role |
author |
author2 |
Rodrigues, Douglas [UNESP] Papa, João Paulo [UNESP] |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Afonso, Luis Claudio Sugi [UNESP] Rodrigues, Douglas [UNESP] Papa, João Paulo [UNESP] |
dc.subject.por.fl_str_mv |
Meta-heuristics Optimum-Path Forest Pattern Classification |
topic |
Meta-heuristics Optimum-Path Forest Pattern Classification |
description |
The Optimum-Path Forest (OPF) is a graph-based classifier that models pattern recognition problems as a graph partitioning task. The OPF learning process is performed in a competitive fashion where a few key samples (i.e., prototypes) try to conquer the remaining training samples to build optimum-path trees (OPT). The task of selecting prototypes is paramount to obtain high-quality OPTs, thus being of great importance to the classifier. The most used approach computes a minimum spanning tree over the training set and promotes the samples nearby the decision boundary as prototypes. Although such methodology has obtained promising results in the past year, it can be prone to overfitting. In this work, it is proposed a metaheuristic-based approach (OPFmh) for the selection of prototypes, being such a task modeled as an optimization problem whose goal is to improve accuracy. The experimental results showed the OPFmh can reduce overfitting, as well as the number of prototypes in many situations. Moreover, OPFmh achieved competitive accuracies and outperformed OPF in the experimental scenarios. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-01-01 2022-05-01T08:45:01Z 2022-05-01T08:45:01Z |
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/10.1007/s12065-021-00664-0 Evolutionary Intelligence. 1864-5917 1864-5909 http://hdl.handle.net/11449/233469 10.1007/s12065-021-00664-0 2-s2.0-85114109403 |
url |
http://dx.doi.org/10.1007/s12065-021-00664-0 http://hdl.handle.net/11449/233469 |
identifier_str_mv |
Evolutionary Intelligence. 1864-5917 1864-5909 10.1007/s12065-021-00664-0 2-s2.0-85114109403 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Evolutionary Intelligence |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus 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_ |
1797790065345167360 |