Publicação

Stability condition identification of rock and soil cutting slopes based on soft computing

Ver documento

Detalhes bibliográficos
Resumo:For transportation infrastructure, one of the greatest challenges today is to keep large-scale transportation networks, such as railway networks, operational under all conditions. This task becomes even more difficult to accomplish if one takes into account budget limitations for maintenance and repair works. This paper presents a tool aimed at helping in management tasks related to maintenance and repair work for a particular element of this infrastructure, the slopes. The highly flexible learning capabilities of artificial neural networks (ANNs) and support vector machines (SVMs) were applied in the development of a tool able to identify the stability condition of rock and soil cutting slopes, keeping in mind the use of information usually collected during routine inspection activities (visual information) to feed the models. This task was addressed following two different strategies: nominal classification and regression. Moreover, to overcome the problem of imbalanced data, three training sampling approaches were explored: no resampling, synthetic minority oversampling technique (SMOTE), and oversampling. The achieved results are presented and discussed, comparing the performance of ANN and SVM algorithms as well as the effect of the sampling approaches. A comparison between nominal classification and regression strategies for both rock and soil cutting slopes is also carried out, highlighting the different performance observed in the study of the two different types of slope.
Autores principais:Tinoco, Joaquim Agostinho Barbosa
Outros Autores:Correia, A. Gomes; Cortez, Paulo; Toll, David G.
Ano:2018
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso restrito
Instituição associada:Universidade do Minho
Idioma:inglês
Origem:RepositóriUM - Universidade do Minho
_version_ 1866877028985208832
author Tinoco, Joaquim Agostinho Barbosa
author2 Correia, A. Gomes
Cortez, Paulo
Toll, David G.
author2_role author
author
author
author_facet Tinoco, Joaquim Agostinho Barbosa
Correia, A. Gomes
Cortez, Paulo
Toll, David G.
author_role author
contributor_name_str_mv Universidade do Minho
country_str PT
creators_json_txt [{\"Person.name\":\"Tinoco, Joaquim Agostinho Barbosa\"},{\"Person.name\":\"Correia, A. Gomes\"},{\"Person.name\":\"Cortez, Paulo\"},{\"Person.name\":\"Toll, David G.\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Universidade do Minho
datacite.creators.creator.creatorName.fl_str_mv Tinoco, Joaquim Agostinho Barbosa
Correia, A. Gomes
Cortez, Paulo
Toll, David G.
datacite.date.Accepted.fl_str_mv 2018-03-01T00:00:00Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_16ec
datacite.titles.title.fl_str_mv Stability condition identification of rock and soil cutting slopes based on soft computing
dc.contributor.none.fl_str_mv Universidade do Minho
dc.creator.none.fl_str_mv Tinoco, Joaquim Agostinho Barbosa
Correia, A. Gomes
Cortez, Paulo
Toll, David G.
dc.date.Accepted.fl_str_mv 2018-03-01T00:00:00Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv https://hdl.handle.net/1822/50258
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv American Society of Civil Engineers (ASCE)
dc.rights.cclincense.fl_str_mv http://creativecommons.org/licenses/by/4.0/
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_16ec
dc.rights.rights.copyright.fl_str_mv restrictedAccess
dc.title.fl_str_mv Stability condition identification of rock and soil cutting slopes based on soft computing
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description For transportation infrastructure, one of the greatest challenges today is to keep large-scale transportation networks, such as railway networks, operational under all conditions. This task becomes even more difficult to accomplish if one takes into account budget limitations for maintenance and repair works. This paper presents a tool aimed at helping in management tasks related to maintenance and repair work for a particular element of this infrastructure, the slopes. The highly flexible learning capabilities of artificial neural networks (ANNs) and support vector machines (SVMs) were applied in the development of a tool able to identify the stability condition of rock and soil cutting slopes, keeping in mind the use of information usually collected during routine inspection activities (visual information) to feed the models. This task was addressed following two different strategies: nominal classification and regression. Moreover, to overcome the problem of imbalanced data, three training sampling approaches were explored: no resampling, synthetic minority oversampling technique (SMOTE), and oversampling. The achieved results are presented and discussed, comparing the performance of ANN and SVM algorithms as well as the effect of the sampling approaches. A comparison between nominal classification and regression strategies for both rock and soil cutting slopes is also carried out, highlighting the different performance observed in the study of the two different types of slope.
dirty 0
eu_rights_str_mv restrictedAccess
format article
fulltext.url.fl_str_mv https://prod-dspace.uminho.pt/bitstreams/1d3c90c8-2a8b-4ddb-aa7c-6a9f21e20af4/download
id rum_19e79d9769ab99aaba2003d09080d6b3
identifier.url.fl_str_mv https://hdl.handle.net/1822/50258
instacron_str repositorium
institution Universidade do Minho
instname_str Universidade do Minho
language eng
network_acronym_str rum
network_name_str RepositóriUM - Universidade do Minho
oai_identifier_str oai:repositorium.uminho.pt:1822/50258
organization_str_mv urn:organizationAcronym:repositorium
person_str_mv Tinoco, Joaquim Agostinho Barbosa
Correia, A. Gomes
Cortez, Paulo
Toll, David G.
publishDate 2018
publisher.none.fl_str_mv American Society of Civil Engineers (ASCE)
reponame_str RepositóriUM - Universidade do Minho
repository_id_str urn:repositoryAcronym:rum
service_str_mv urn:repositoryAcronym:rum
spelling engAmerican Society of Civil Engineers (ASCE)porFor transportation infrastructure, one of the greatest challenges today is to keep large-scale transportation networks, such as railway networks, operational under all conditions. This task becomes even more difficult to accomplish if one takes into account budget limitations for maintenance and repair works. This paper presents a tool aimed at helping in management tasks related to maintenance and repair work for a particular element of this infrastructure, the slopes. The highly flexible learning capabilities of artificial neural networks (ANNs) and support vector machines (SVMs) were applied in the development of a tool able to identify the stability condition of rock and soil cutting slopes, keeping in mind the use of information usually collected during routine inspection activities (visual information) to feed the models. This task was addressed following two different strategies: nominal classification and regression. Moreover, to overcome the problem of imbalanced data, three training sampling approaches were explored: no resampling, synthetic minority oversampling technique (SMOTE), and oversampling. The achieved results are presented and discussed, comparing the performance of ANN and SVM algorithms as well as the effect of the sampling approaches. A comparison between nominal classification and regression strategies for both rock and soil cutting slopes is also carried out, highlighting the different performance observed in the study of the two different types of slope.application/pdfporStability condition identification of rock and soil cutting slopes based on soft computingTinoco, Joaquim Agostinho BarbosaCorreia, A. GomesCortez, PauloToll, David G.HostingInstitutionOrganizationalUniversidade do Minhoe-mailmailto:repositorium@usdb.uminho.ptrepositorium@usdb.uminho.ptISSNIsPartOf0887-3801DOIIsPartOf10.1061/(ASCE)CP.1943-5487.00007392018-032018-03-01T00:00:00ZHandlehttps://hdl.handle.net/1822/50258http://purl.org/coar/access_right/c_16ecrestricted access313258 bytesliteraturehttp://purl.org/coar/resource_type/c_6501journal article2018-03http://creativecommons.org/licenses/by/4.0/restrictedAccesshttp://purl.org/coar/access_right/c_16ecapplication/pdffulltexthttps://prod-dspace.uminho.pt/bitstreams/1d3c90c8-2a8b-4ddb-aa7c-6a9f21e20af4/download
spellingShingle Stability condition identification of rock and soil cutting slopes based on soft computing
Tinoco, Joaquim Agostinho Barbosa
status SINGLETON
title Stability condition identification of rock and soil cutting slopes based on soft computing
title_full Stability condition identification of rock and soil cutting slopes based on soft computing
title_fullStr Stability condition identification of rock and soil cutting slopes based on soft computing
title_full_unstemmed Stability condition identification of rock and soil cutting slopes based on soft computing
title_short Stability condition identification of rock and soil cutting slopes based on soft computing
title_sort Stability condition identification of rock and soil cutting slopes based on soft computing
url https://hdl.handle.net/1822/50258
visible 1