Previs??o de demanda na fase de planejamento antecipado de projetos de transporte de passageiros: uma abordagem por redes neurais artificiais
Autor(a) principal: | |
---|---|
Data de Publicação: | 2015 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Biblioteca Digital de Teses e Dissertações da Uninove |
Texto Completo: | http://bibliotecatede.uninove.br/tede/handle/tede/151 |
Resumo: | Considering that passenger demand is a major risk in passenger rail infrastructure projects, this study aims to validate a demand forecasting model based on artificial neural networks (ANN), in order to contribute to the project management of this type of projects, it is still in front-end planning of these projects. For this, the design of the type ex-post facto was used in a descriptive research with quantitative approach where the research group was formed by subway and train stations in the metropolitan region of S??o Paulo (RMSP). The data for training, testing and validation of the neural model demand forecast were obtained from secondary sources, which are: the Urban Mobility Research 2012 in the RMSP; and the data base of entry passenger at subway and train stations. Proposed were 12 architectures of the ANN with 15 different configurations, totaling 180 training processes, testing and validation. For each of the architectures, the lowest mean square error (MSE) obtained was identified; and the best architecture, with a hidden layer was performed relevance analysis by Garson method, the model 4 input variables: the population; the school enrollment; the number of jobs; and per capita income. The main results of this study demonstrate the validity of the proposed architectures, presenting MSE% from 0.045% ~ 0.109%. The practical contribution this study is to serve as an aid tool for organizations and project managers in the study of economic and financial viability of these projects, still in its early planning stages, serving as an investment decision-making tool. |
id |
NOVE_1beafb1b114227ba1945f42cb6db9e9e |
---|---|
oai_identifier_str |
oai:localhost:tede/151 |
network_acronym_str |
NOVE |
network_name_str |
Biblioteca Digital de Teses e Dissertações da Uninove |
repository_id_str |
|
spelling |
Silva, Filipe Quevedo Pires de Oliveira eCPF:02852070162http://lattes.cnpq.br/8912994803481178Rovai, Ricardo Leonardohttp://lattes.cnpq.br/9510041230174906Cattini Junior, Orlandohttp://lattes.cnpq.br/9702371847442365CPF:16887312883http://lattes.cnpq.br/1224575380290426Vasconcelos, Vagner Sanches2015-04-07T21:08:52Z2015-03-052015-02-12VASCONCELOS, Vagner Sanches. Demand forecast in the front-end planning stages passenger transport projects: an approach by artificial neural networks. 2015. 200 f. Disserta????o (Mestrado em Administra????o) - Universidade Nove de Julho, S??o Paulo, 2015.http://bibliotecatede.uninove.br/tede/handle/tede/151Considering that passenger demand is a major risk in passenger rail infrastructure projects, this study aims to validate a demand forecasting model based on artificial neural networks (ANN), in order to contribute to the project management of this type of projects, it is still in front-end planning of these projects. For this, the design of the type ex-post facto was used in a descriptive research with quantitative approach where the research group was formed by subway and train stations in the metropolitan region of S??o Paulo (RMSP). The data for training, testing and validation of the neural model demand forecast were obtained from secondary sources, which are: the Urban Mobility Research 2012 in the RMSP; and the data base of entry passenger at subway and train stations. Proposed were 12 architectures of the ANN with 15 different configurations, totaling 180 training processes, testing and validation. For each of the architectures, the lowest mean square error (MSE) obtained was identified; and the best architecture, with a hidden layer was performed relevance analysis by Garson method, the model 4 input variables: the population; the school enrollment; the number of jobs; and per capita income. The main results of this study demonstrate the validity of the proposed architectures, presenting MSE% from 0.045% ~ 0.109%. The practical contribution this study is to serve as an aid tool for organizations and project managers in the study of economic and financial viability of these projects, still in its early planning stages, serving as an investment decision-making tool.Considerando que a demanda de passageiros ?? um dos principais riscos nos empreendimentos de infraestrutura de transporte de passageiros sobre trilhos, este trabalho objetiva validar um modelo de previs??o de demanda, baseado em redes neurais artificiais (RNA), de forma a contribuir com a gest??o de projetos dessa modalidade de empreendimentos, isso ainda em sua fase de planejamento antecipado do projeto. Para isso, foi utilizado o delineamento do tipo ex-post facto, numa pesquisa do tipo descritiva com abordagem quantitativa, onde o grupo de investiga????o foi formado pelas esta????es de metr?? e de trem da Regi??o Metropolitana de S??o Paulo (RMSP). Os dados para o treinamento, teste e valida????o do modelo neural de previs??o de demanda foram obtidos de fontes secund??rias, sendo elas: a Pesquisa de Mobilidade Urbana 2012 na RMSP; e a base de dados de entrada de passageiros nas esta????es de metr?? e trem. Foram propostos 12 arquiteturas de RNA com 15 configura????es diferentes, totalizando assim 180 processos de treinamento, teste e valida????o. Para cada uma das arquiteturas, foi identificado o menor erro m??dio quadrado percentual (EQM%) obtido; e para a melhor arquitetura, com uma camada oculta, foi realizado a an??lise de relev??ncia, pelo m??todo de Garson, das 4 vari??veis de entrada do modelo: a popula????o; o n??mero de matr??culas escolares; o n??mero de empregos; e a renda per capita. Os principais resultados obtidos desta pesquisa demonstram a validade das arquiteturas propostas, que apresentaram EQM% entre 0,045% ~ 0,109%. A contribui????o para a pr??tica deste estudo ?? servir como ferramenta de auxilio das organiza????es e dos gerentes de projeto nos estudos de viabilidade econ??mico-financeiro desses empreendimentos, ainda em sua fase de planejamento antecipado, servindo como uma ferramenta de tomada de decis??o de investimento.Made available in DSpace on 2015-04-07T21:08:52Z (GMT). No. of bitstreams: 1 Vagner Sanches Vasconcelos.pdf: 2902125 bytes, checksum: 225aca89417650de8eb91a507dbd2584 (MD5) Previous issue date: 2015-02-12application/pdfporUniversidade Nove de JulhoPrograma de P??s-Gradua????o em Gest??o de ProjetosUninoveBRAdministra????ogerenciamento de projetosplanejamento antecipado do projetoempreendimentos de transporte de passageiros sobre trilhosprevis??o de demandaredes neurais artificiaisproject managementfront-end planningproject passenger on railsdemand forecastingartificial neural networksCIENCIAS SOCIAIS APLICADAS::ADMINISTRACAOPrevis??o de demanda na fase de planejamento antecipado de projetos de transporte de passageiros: uma abordagem por redes neurais artificiaisDemand forecast in the front-end planning stages passenger transport projects: an approach by artificial neural networksinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesis8024035432632778221600info:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da Uninoveinstname:Universidade Nove de Julho (UNINOVE)instacron:UNINOVEORIGINALVagner Sanches Vasconcelos.pdfapplication/pdf2902125http://localhost:8080/tede/bitstream/tede/151/1/Vagner+Sanches+Vasconcelos.pdf225aca89417650de8eb91a507dbd2584MD51tede/1512019-06-19 16:39:39.648oai:localhost:tede/151Biblioteca Digital de Teses e Dissertaçõeshttp://bibliotecatede.uninove.br/PRIhttp://bibliotecatede.uninove.br/oai/requestbibliotecatede@uninove.br||bibliotecatede@uninove.bropendoar:2019-06-19T19:39:39Biblioteca Digital de Teses e Dissertações da Uninove - Universidade Nove de Julho (UNINOVE)false |
dc.title.por.fl_str_mv |
Previs??o de demanda na fase de planejamento antecipado de projetos de transporte de passageiros: uma abordagem por redes neurais artificiais |
dc.title.alternative.eng.fl_str_mv |
Demand forecast in the front-end planning stages passenger transport projects: an approach by artificial neural networks |
title |
Previs??o de demanda na fase de planejamento antecipado de projetos de transporte de passageiros: uma abordagem por redes neurais artificiais |
spellingShingle |
Previs??o de demanda na fase de planejamento antecipado de projetos de transporte de passageiros: uma abordagem por redes neurais artificiais Vasconcelos, Vagner Sanches gerenciamento de projetos planejamento antecipado do projeto empreendimentos de transporte de passageiros sobre trilhos previs??o de demanda redes neurais artificiais project management front-end planning project passenger on rails demand forecasting artificial neural networks CIENCIAS SOCIAIS APLICADAS::ADMINISTRACAO |
title_short |
Previs??o de demanda na fase de planejamento antecipado de projetos de transporte de passageiros: uma abordagem por redes neurais artificiais |
title_full |
Previs??o de demanda na fase de planejamento antecipado de projetos de transporte de passageiros: uma abordagem por redes neurais artificiais |
title_fullStr |
Previs??o de demanda na fase de planejamento antecipado de projetos de transporte de passageiros: uma abordagem por redes neurais artificiais |
title_full_unstemmed |
Previs??o de demanda na fase de planejamento antecipado de projetos de transporte de passageiros: uma abordagem por redes neurais artificiais |
title_sort |
Previs??o de demanda na fase de planejamento antecipado de projetos de transporte de passageiros: uma abordagem por redes neurais artificiais |
author |
Vasconcelos, Vagner Sanches |
author_facet |
Vasconcelos, Vagner Sanches |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Silva, Filipe Quevedo Pires de Oliveira e |
dc.contributor.advisor1ID.fl_str_mv |
CPF:02852070162 |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/8912994803481178 |
dc.contributor.referee1.fl_str_mv |
Rovai, Ricardo Leonardo |
dc.contributor.referee1Lattes.fl_str_mv |
http://lattes.cnpq.br/9510041230174906 |
dc.contributor.referee2.fl_str_mv |
Cattini Junior, Orlando |
dc.contributor.referee2Lattes.fl_str_mv |
http://lattes.cnpq.br/9702371847442365 |
dc.contributor.authorID.fl_str_mv |
CPF:16887312883 |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/1224575380290426 |
dc.contributor.author.fl_str_mv |
Vasconcelos, Vagner Sanches |
contributor_str_mv |
Silva, Filipe Quevedo Pires de Oliveira e Rovai, Ricardo Leonardo Cattini Junior, Orlando |
dc.subject.por.fl_str_mv |
gerenciamento de projetos planejamento antecipado do projeto empreendimentos de transporte de passageiros sobre trilhos previs??o de demanda redes neurais artificiais |
topic |
gerenciamento de projetos planejamento antecipado do projeto empreendimentos de transporte de passageiros sobre trilhos previs??o de demanda redes neurais artificiais project management front-end planning project passenger on rails demand forecasting artificial neural networks CIENCIAS SOCIAIS APLICADAS::ADMINISTRACAO |
dc.subject.eng.fl_str_mv |
project management front-end planning project passenger on rails demand forecasting artificial neural networks |
dc.subject.cnpq.fl_str_mv |
CIENCIAS SOCIAIS APLICADAS::ADMINISTRACAO |
description |
Considering that passenger demand is a major risk in passenger rail infrastructure projects, this study aims to validate a demand forecasting model based on artificial neural networks (ANN), in order to contribute to the project management of this type of projects, it is still in front-end planning of these projects. For this, the design of the type ex-post facto was used in a descriptive research with quantitative approach where the research group was formed by subway and train stations in the metropolitan region of S??o Paulo (RMSP). The data for training, testing and validation of the neural model demand forecast were obtained from secondary sources, which are: the Urban Mobility Research 2012 in the RMSP; and the data base of entry passenger at subway and train stations. Proposed were 12 architectures of the ANN with 15 different configurations, totaling 180 training processes, testing and validation. For each of the architectures, the lowest mean square error (MSE) obtained was identified; and the best architecture, with a hidden layer was performed relevance analysis by Garson method, the model 4 input variables: the population; the school enrollment; the number of jobs; and per capita income. The main results of this study demonstrate the validity of the proposed architectures, presenting MSE% from 0.045% ~ 0.109%. The practical contribution this study is to serve as an aid tool for organizations and project managers in the study of economic and financial viability of these projects, still in its early planning stages, serving as an investment decision-making tool. |
publishDate |
2015 |
dc.date.accessioned.fl_str_mv |
2015-04-07T21:08:52Z |
dc.date.available.fl_str_mv |
2015-03-05 |
dc.date.issued.fl_str_mv |
2015-02-12 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
VASCONCELOS, Vagner Sanches. Demand forecast in the front-end planning stages passenger transport projects: an approach by artificial neural networks. 2015. 200 f. Disserta????o (Mestrado em Administra????o) - Universidade Nove de Julho, S??o Paulo, 2015. |
dc.identifier.uri.fl_str_mv |
http://bibliotecatede.uninove.br/tede/handle/tede/151 |
identifier_str_mv |
VASCONCELOS, Vagner Sanches. Demand forecast in the front-end planning stages passenger transport projects: an approach by artificial neural networks. 2015. 200 f. Disserta????o (Mestrado em Administra????o) - Universidade Nove de Julho, S??o Paulo, 2015. |
url |
http://bibliotecatede.uninove.br/tede/handle/tede/151 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.cnpq.fl_str_mv |
8024035432632778221 |
dc.relation.confidence.fl_str_mv |
600 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Nove de Julho |
dc.publisher.program.fl_str_mv |
Programa de P??s-Gradua????o em Gest??o de Projetos |
dc.publisher.initials.fl_str_mv |
Uninove |
dc.publisher.country.fl_str_mv |
BR |
dc.publisher.department.fl_str_mv |
Administra????o |
publisher.none.fl_str_mv |
Universidade Nove de Julho |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações da Uninove instname:Universidade Nove de Julho (UNINOVE) instacron:UNINOVE |
instname_str |
Universidade Nove de Julho (UNINOVE) |
instacron_str |
UNINOVE |
institution |
UNINOVE |
reponame_str |
Biblioteca Digital de Teses e Dissertações da Uninove |
collection |
Biblioteca Digital de Teses e Dissertações da Uninove |
bitstream.url.fl_str_mv |
http://localhost:8080/tede/bitstream/tede/151/1/Vagner+Sanches+Vasconcelos.pdf |
bitstream.checksum.fl_str_mv |
225aca89417650de8eb91a507dbd2584 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações da Uninove - Universidade Nove de Julho (UNINOVE) |
repository.mail.fl_str_mv |
bibliotecatede@uninove.br||bibliotecatede@uninove.br |
_version_ |
1811016859083866112 |