Previsão da demanda por viagens domiciliares através de método sequencial baseado em população sintética e redes neurais artificiais
DOI:
https://doi.org/10.14295/transportes.v27i4.1409Keywords:
Monte Carlo, Synthetic trips, Trip generation.Abstract
The estimation of trips per household is essential in the decision-making process related to transportation planning. However, to obtain this estimate, disaggregated data per household is needed, which is usually obtained by an Origin and Destination Survey. Most cities face problems to obtain this data, as this kind of survey needs an amount of time and money to plan and carry it out. Thus, tools for estimation, providing reliable data and low cost, are required. The aim of this paper is to present a sequential method for estimating trips per households using a synthetic population and Artificial Neural Networks (ANNs). The synthetic population was based on aggregated census data and the Monte Carlo Method. The results obtained with ANNs were compared to the results of a traditional linear model and the results were subtly better for ANNs, corroborating their potential in the use of travel demand modeling. The synthetic household trips were validated with the data from the Origin and Destination Survey and hypothesis tests to compare typical values and population distributions. In 71% of the census unit of areas, the synthetic trips were considered similar to the actual data, corroborating the efficiency of the proposed method. Thus, the main research gap is the proposal of the sequential method, capable of minimizing issues of data acquisition and mathematical constraints and assumptions inherent in traditional travel demand forecasting modelsDownloads
References
Adeli, H. (2001) Neural Network in Civil Engineering: 1989 – 2000. Computer-Aided Civil and Infrastructure Engineering, v. 16 (2), p. 126-146. DOI: 10.1111/0885-9507.00219.
Adiga, A., Agashe, A.; Arifuzzaman, S.; Barrett, C.L.; Beckman, R.J.; Bisset, K.R.; Chen, J.; Chungbaek, Y.; Eubank, S.G.; Gupta, S.; Khan, M., Kuhlman; C.J., Lofgren, E.; Lewis, B.L.; Marathe, A.; Marathe, M.V.; Mortveit, H.S.; Nordberg, E.; Rivers, C.; Stretz, P.; Swarup, S.; Wilson, A. e Xie, D. (2015) Generating a synthetic population of the United States. Tech. Rep. NDSSL 15-009, Network Dynamics and Simulation Science Laboratory. Disponível em: <https://pdfs.semanticscholar.org/391d/bcde4fda9186f03da174d6b7a4494d0bb6e4.pdf> (Acesso em: 07/08/2019).
Aguiar Júnior, S. R. (2004) Modelo RAPIDE: uma aplicação de mineração de dados e redes neurais artificiais para a estimativa da demanda por transporte rodoviário interestadual de passageiros no Brasil. Brasília. Dissertação (Mestrado em Gestão do conhecimento e da Tecnologia da informação), Universidade Católica de Brasília.
Al-Deek, H.M. (2001) Which method is Better for Developing Freight Planning Models at Seaports – neural Networks or Multiple Regression, Transportation Research Record, 1763, pp. 90-97, 2001. DOI: 10.3141/1763-14.
Atherton, T.J. and Ben-Akiva, M.E. (1976) Transferability and updating of disaggregate travel demand models. Transportation Research Record, 610, 12–18.
Disponível em: <http://onlinepubs.trb.org/Onlinepubs/trr/1976/610/610-003.pdf>. (Acesso em: 07/08/2019).
Ashley, D. J. (1978) The Regional Highway Traffic Model: the home based trip end model. Proceedings 6th PTRC. Summer Annual Meeting, University of Warwick, July 1978, England.
Banks, J.; Carson, J.S.; Nelson, B.L. e Nicol, D.M. (2005) Discrete-Event System Simulation (4ª ed.). Prentice Hall, Upper Saddle River, NJ.
Bates, J.J., Gunn, H.F. and Roberts, M. (1978) A model of household car ownership. Traffic Engineering and Control 19, 486–491, 562–566.
Batista; B. C. F. (2012) Soluções de Equações Diferenciais usando Redes Neurais de Múltiplas camadas com os métodos da Descida mais íngreme e Levenberg-Marquardt. Belém. 88p. Dissertação (Mestrado em Matemática), Universidade Federal do Pará.
Beckman, R. J.; Baggerly, K. A. e Mckay, M. D. (1996) Creating synthetic baseline populations. Transportation Research Part A: Policy and Practice. Elsevier, v.30, n.6, p.415–429. DOI: 10.1016/0965-8564(96)00004-3.
Birkin, M.; Clarke, M. (1988) Synthesis—a synthetic spatial information system for urban and regional analysis: methods and examples. Environment and planning A. SAGE Publications, v.20, n.12, p.1645–1671. DOI: 10.1068/a201645.
Bowman, J. L. (2004) A comparison of population synthesizers used in microsimulation models of activity and travel demand. Working paper. Disponível em: <https://pdfs.semanticscholar.org/3d1c/1fda84391752dfa520ccb08426eebf7c5da2.pdf>. Acesso em: 17.3.2019.
Bowman, John L. (2009) Population Synthesizers, Traffic Engineering and Control, Vol. 49. No. 9: 342.
Bruton, M. J. (1979) Introdução ao planejamento dos transportes. Rio de Janeiro: Interciência.
Chwif, L.; Medina, A. (2014) Modelagem e Simulação de Eventos Discretos: Teoria e Aplicações (4ª ed.). Elsevier, São Paulo, Bra-sil.
Clifton, K. J., K. M. Currans, A. C. Cutter, and R. Schneider (2012) Household travel surveys in a context-based approach for adjusting ITE trip generation rates in urban contexts. Transportation Research Record 2307: p.108–119. DOI: 10.3141/2307-12.
Deming, W. E.; Stephan, F. F. (1940) On a least squares adjustment of a sampled frequency table when the expected mar-ginal totals are known. The Annals of Mathematical Statistics, JSTOR, v.11, n.4, p.427–444. DOI: 10.1214/aoms/1177731829.
Dougherty, M. (1995) A review of neural networks applied to transport. Transportation Research, Part C, v.3, n.4. p.247-260. DOI: 10.1016/0968-090X(95)00009-8.
Ewing, R., M. DeAnna, and Li, S. C. (1996). Land use impacts on trip generation rates. Transportation Research Record 1518: 1–6. DOI: 10.1177/0361198196151800101.
Escudero, L. F. (1973) La simulatición en la empresa. Ed. Duesto, Bilbao.
Freedman, D. A. (2009) Statistical Models: Theory and Practice. Cambridge University Press.
Gonçalves D. N. S.; Lopes, L. A. S. Da Silva, M. A. V. (2014) Aplicação de Redes Neurais Artificiais para estimar matriz origem-destino de carga. Anais do 28º Congresso Brasileiro de Transporte e Trânsito – ANPET, Curitiba. Disponível em: <http://redpgv.coppe.ufrj.br/index.php/pt-BR/producao-da-rede/artigos-cientificos/2014-1/864-aplicacao-de-redes-neurais-artificiais-para-estimar-matriz-origem-destino-de-carga/file>. (Acesso em: 07/08/2019).
Goncalves, D. N. S.; Silva, M. A.V.; D'Agosto, M. A. Procedimento para uso de Redes Neurais Artificiais no planejamento estraté-gico de fluxo de carga no Brasil. J. Transp. Lit., Manaus, v. 9, n. 1, p. 45-49, Jan. 2015. DOI: 10.1590/2238-1031.jtl.v9n1a9.
Hair, J. F.; Black, W.C.; Babin, B.J.; Anderson, R.E.; Tatham, R.L. (2009) Análise multivariada de dados (6ª ed.). Ed. Bookman, Porto Alegre.
Hammersley, J.; Handscomb, D. (1964) Monte Carlo Methods, Methuen’s Monographs on Applied Probability.: Wiley, New York.
Haykin, S. (1999) Neural networks - a comprehensive foundation. Prentice Hall, Ontario, Canada.
Huang, Z.; Williamson, P. A. (2002) Comparison of synthetic reconstruction and combinatorial optimization approaches to the creation of small-area microdata. Working paper. Department of Geography, University of Liverpool. Disponível em: file:///C:/Users/manav/Desktop/ARTIGOS_Transportes/huang.pdf (Acesso em: 07/08/2019).
Huisken, G.; Coffa, A. (2000) Neural Networks and Fuzzy Logic to improve Trip Generation Modelling, Proceedings of the 9th International Association for Travel Behaviour Research Conference, Institute of Transport Studies, IATBR, Gold Coast, Queensland, Austália, 2000. Disponível em: https://research.utwente.nl/en/publications/neural-networks-and-fuzzy-logic-to-improve-trip-generation-modell (Acesso em: 07/08/2019).
IBGE (2010) - Instituto Brasileiro de Geografia e Estatística. Disponível em: <http://www.ibge.gov.br>. (Acesso em: 15.3.2017).
Ichikawa, S.M.; Pitombo, C.S.; Kawamoto, E. (2002) Aplicação de Minerador de dados na obtenção de relações entre padrões de viagens encadeadas e caracterı́sticas socioeconômicas. Anais do XVI do Congresso de Pesquisa e Ensino em Transportes, Anpet, Natal (RN), v. 2, p. 175-186.
Jain, S.; Ronald, N.; Winter, S. (2015) Creating a Synthetic Population: A Comparison of Tools. In Proceedings of the 3rd Confer-ence Transportation Reserch Group, Kolkata, India, 17–20 December 2015. Disponível em: https://www.researchgate.net/publication/291608775_Creating_a_Synthetic_Population_A_Comparison_of_Tools. (Acesso em:07/08/2019).
Kawamoto, E. (1994) Análise de sistemas de transporte. 2ª ed. (Apostila). Departamento de Transportes. Escola de Engenharia de São Carlos, Universidade de São Paulo. São Carlos, Brasil.
Lin, H.; Taylor, M.A.P.; Zito R. (2005) A Review of Travel-Time prediction in Transport and Logistics. Proceedings of the Eastern Asia Society for Transportation Studies, v. 5, p. 1433 – 1448. Disponível em: https://trove.nla.gov.au/work/179520839?q&versionId=223381176+224842764+245312661+253844472. (Aces-so em: 07/08/2019).
Lindner, A. (2019) Métodos heurísticos de desagregação de dados de demanda por transportes através de simulação geoes-tatística. São Carlos. 118p. Tese (Doutorado) – Programa de Pós-graduação em Engenharia de Transportes e Área de Concentração em Planejamento e Operação de Sistemas de Transportes – Escola de Engenharia de São Carlos da Univer-sidade de São Paulo.
Lindner, A. e Pitombo, C.S; (2019) Sequential Gaussian Simulation as a promising tool in travel demand modeling. Journal of Geovisualization and Spatial Analysis (disponível online). DOI: 10.1007/s41651-019-0038-x.
Ma, L. (2011) Generating disaggregate population characteristics for input to travel-demand models. Florida. 124p. Tese (Dou-torado) — University of Florida.
Ma, L. e Srinivasan, S. (2015) Synthetic population generation with multilevel controls: A fitness-based synthesis approach and validations. Computer-Aided Civil and Infrastructure Engineering. Wiley Online Library, v.30, n.2, p.135–150. DOI: 10.1111/mice.12085.
Mackay, D. J. C. (1996) Introduction to Monte Carlo Methods. Cambridge (Cambridgeshire).
Moeckel, R.; Spiekermann, K.; Wegener, M.. (2003) Creating a Synthetic Population”. In: Proceedings of the 8th International Conference on Computers in Urban Planning and Urban Management (CUPUM), Sendai, Japan: [s.n.], p. 1-18.
Mozolin, M.; Thill, J.C.; Linn, U.E. (2015) Trip distribution forecasting with multilayer perceptron neural networks: A critical evaluation. Transportation Research Part B: Methodological, v. 34, p. 53-73. DOI: 10.1016/S0191-2615(99)00014-4. Dis-ponível em: https://ideas.repec.org/a/eee/transb/v34y2000i1p53-73.html. (Acesso em: 07/08/2019).
Müller, K. e Axhausen, K. W. (2011) Hierarchical IPF: Generating a synthetic population for Switzerland. In: 51 st Congress of the European Regional Science Association. Barcelona. Disponível em: file:///C:/Users/manav/Desktop/ARTIGOS_Transportes/Muller%202011.pdf. (Acesso em: 08/08/2019).
Münnich, R.; Schürle, J.; Bihler, W.; Boonstra, H. J.; Eckmair, D. e Haslinger, A. (2003) Monte Carlo simulation Study of Europe-an Surveys. DACSEIS Deliverables D, v.3.
Namazi-rad, M. R.; Mokhtarian, P. e Perez, P. (2014) Generating a dynamic synthetic population–using an age-structured two-sex model for house hold dynamics. PloS one. Public Library of Science, v.9, n.4, p. e94761. DOI: 10.1371/journal.pone.0094761.
Novaes, A. G. (1986) Sistemas de Transportes. Volume 1: Análise da Demanda. São Paulo: Edgard Blucher.
Openshaw, S.; Openshaw, C. (1997) Artificial intelligence in Geography, John Wiley and Sons, Chichester, 1997.
Ortúzar, J.D.; Willumsen, L.G. (2011). Modelling Transport. Wiley, 4th Edition.
Papacostas C. S.; Provedouros, P. D. (1993) Transportation Engineering and Planning. 2.ed. New Jersey: Prentice Hall.
Pitombo, C. S.; De Souza, A.D.; Lindner, A. (2017) Comparing decision tree algorithms to estimate intercity trip distribution. Transportation Research Part C , v. 77, p. 16-32. DOI: 10.1016/j.trc.2017.01.009.
PNUD (2016) - Atlas do Desenvolvimento Humano no Brasil. Disponível em: http://http://www.pnud.org.br/atlas. Acesso em: 15.3.2017.
Pritchard, D. R. (2008) Synthesizing Agents and Relationships for Land Use/ transportation Modelling. 2008. Canadian theses, University of Toronto, Toronto.
Raymond, C. J. (1982) Adapting for Heteroscedasticity in Linear Models. The Annals of Statistics. 10 (4): 1224–1233. DOI:10.1214/aos/1176345987. JSTOR 2240725.
Schmöcker, J. D.; Quddus, M. A.; Noland, R. B.; Bell, Michael G.H. (2005) Estimating trip generation of elderly and disabled people: analysis of London data, Transportation Research Record, 9–18. DOI: 10.3141/1924-02.
Silva, A. N. (2008) Rodrigues da. Pesquisa Origem e Destino da cidade de São Carlos. Relatório. Universidade de São Paulo, Esco-la de Engenharia de São Carlos.
Smith, M. (1996) Neural Networks for Statistical Modeling. International Thomson Computer Press, Londres, Inglaterra.
Tillema, F., van Zuilekom, K. M.; van Maarseveen, M. F. A. M. (2004) Trip generation: comparison of neural networks and regression models. In C. A. Brebbia, & L. C. Wadhwa (Eds.), Urban Transport X : Urban transport and the environment in the 21st century (pp. 121-130). Southampton, UK: WIT Press. Disponível em: https://research.utwente.nl/en/publications/trip-generation-comparison-of-neural-networks-and-regression-mode. (Acesso em: 07/08/2019).
Turchenko, V.; Grandinetti, L.; Bosilca, G.; Dongarra, J. (2010). Improvement of parallelization efficiency of batch pattern BP training algorithm using Open MPI. Procedia CS. 1. 525-533. DOI: 10.1016/j.procs.2010.04.056.
Vickerman, R. W.; Barmby, T. A. (1985) Household trip generation choice: alternative empirical approaches. Transportation Research B, 19(6), 471-479. DOI: 10.1016/0191-2615(85)90042-6.
Voas, D. e Williamson, P. (2001) Evaluating goodness-of-fit measures for synthetic microdata. Geographic a land Environmental Modelling. Taylor & Francis, v.5, n.2, p.177–200. DOI: 10.1080/13615930120086078.
Xie, C.; Lu, J.; Parkany, E. (2003) Work travel mode choice modeling with data mining: decision trees and neural networks. Transportation Research Record: Journal of the Transportation Research Board, n. 1854, p. 50-61. DOI: 10.3141/1854-06.
Ye, X., K. Konduri, R. M. Pendyala, B. Sana and P. Waddell (2009) A methodology to match distributions of both household and person attributes in the generation of synthetic populations, paper presented at the 88th Annual Meeting of the Transportation Research Board, Washington, D.C., January 2009.
Wasserman P.D. (1989) Advanced methods in neural computing. New York, Van Nostrand Reinhold.
Williamson, P.; Birkin, M.; Rees, P.H. (1998) The estimation of population microdata by using data from small area statistics and samples of anonymized records. Environment and Planning A, SAGE Publications, v.30, n.5, p.785–816. DOI: 10.1068/a300785.
Downloads
Published
How to Cite
Issue
Section
License
Authors who submit papers for publication by TRANSPORTES agree to the following terms:
- Authors retain copyright and grant TRANSPORTES the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors may enter into separate, additional contractual arrangements for the non-exclusive distribution of this journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in TRANSPORTES.
- Authors are allowed and encouraged to post their work online (e.g., in institutional repositories or on their website) after publication of the article. Authors are encouraged to use links to TRANSPORTES (e.g., DOIs or direct links) when posting the article online, as TRANSPORTES is freely available to all readers.
- Authors have secured all necessary clearances and written permissions to published the work and grant copyright under the terms of this agreement. Furthermore, the authors assume full responsibility for any copyright infringements related to the article, exonerating ANPET and TRANSPORTES of any responsibility regarding copyright infringement.
- Authors assume full responsibility for the contents of the article submitted for review, including all necessary clearances for divulgation of data and results, exonerating ANPET and TRANSPORTES of any responsibility regarding to this aspect.
