Abordagem desagregada de distribuição de viagens urbanas: uma análise comparativa entre redes neurais e artificiais e modelos de escolha discreta

Autores

DOI:

https://doi.org/10.14295/transportes.v30i2.2686

Palavras-chave:

Escolhas de destinos, Logit Multinomial, Logit Aninhado, Redes Neurais e Artificiais

Resumo

Este artigo propõe uma análise comparativa entre Redes Neurais Artificiais (RNAs), Logit Multinomial e Aninhado para uma previsão desagregada de distribuição de viagens urbanas.  O estudo de caso foi a cidade de Santa Maria (RS). Os dados utilizados foram originados da pesquisa domiciliar, realizada para elaboração do Plano Diretor de Mobilidade Urbana. As comparações entre abordagens foram realizadas através de taxas de acertos e frequências de distâncias de viagens, mostrando que RNAs podem ser tão eficientes quanto os modelos de escolha discreta, sem assumir algumas restrições. Finalmente, com base nos resultados, pode-se afirmar que as RNAs são eficientes para previsão de alternativas com baixo número de observações. São importantes ferramentas para obtenção de matrizes O/D a partir de matrizes incompletas ou com baixos números de observações. Contudo, vale ressaltar que modelos de escolha discreta fornecem informações importantes, como significância estatística dos parâmetros estimados, elasticidades, valores subjetivos de atributos, etc.  

Downloads

Não há dados estatísticos.

Referências

Ben-Akiva, M., D. Bolduc, J. Walker (2003) Specification, Identification, and Estimation of the Logit Kernel (Or Continuous Mixed Logit) Model. Working Paper, 5th Invitational Choice Symposium, Asilomar, California.

Ben-Akiva, M.; Lerman, S. R. (1985) Discrete Choice Analysis: Theory and Application to Travel Demand, Cambridge, MA: MIT Press.

Bishop, Christopher M. (1995) Neural networks for pattern recognition. Oxford University Press, Oxford.

Black, W. R. (1995) Spatial interaction modeling using artificial neural networks. Journal of Transport Geography, v. 3, n. 3, p. 159–166. DOI: 10.1016/0966-6923(95)00013-S.

Caldas, M. U. C.; Pitombo, C. S.; Assirati, L. (2021) Strategy to reduce the number of parameters to be estimated in discrete choice models: an approach to large choice sets. Travel Behaviour and Society, v. 25, p. 1-17. DOI: 10.1016/j.tbs.2021.05.001.

Cantarella, G. E.; De Luca, S. (2005) Multilayer feed forward networks fortransportation mode choice analysis: An analysis and a comparison with random utility models. Transportation Research Part C, v. 13, p. 121-155. DOI: 10.1016/j.trc.2005.04.002.

Carvalho, M. C. M.; Dougherty, M. S.; Fowkes, A. S.; Wardman, M. R. (1998) Forecasting travel demand: A comparison of logit and artificial neural network methods, Journal of the Operational Research Society, v. 49, p. 717-772. DOI: 10.1057/palgrave.jors.2600590.

Cascetta, E.; Pagliara, F.; Papola, A. (2007) Alternative approaches to trip distribution modelling: A retrospective review and suggestions for combining different approaches, Papers in Regional Science, v. 86, n. 4, p. 597-620. DOI: 10.1111/j.1435-5957.2007.00135.x.

Casey, H. J. (1955) Applications to traffic engineering of the law of retail gravitation. Traffic Quartely IX, p. 23-35.

Chow, L., Zhao, F., Li, M., Li, S. (2005) Development and evaluation of aggregate destination choice models for trip distribution in Florida, Transportation Research Record, v. 1931, n. 1, p. 18-27. DOI: 10.3141/1931-03.

Daly, A.J., Zachary, S., (1978) Improved multiple choice models. In: Hensher, D.A., Dalvi, M.Q. (Eds.), Determinants of Travel Choice. Saxon House, Westmead.

Dougherty, Mark. (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.

Evans, A.W. (1970) Some Properties of Trip Distribution Methods. Transportation Research, v. 4, n. 1, p. 19-36. DOI: 10.1016/0041-1647(70)90072-9.

Evans, S.P., Kirby, H.R. (1974) A three-dimensional furness procedure for calibrating gravity models. Transportation Research, v. 8, n. 2, p. 105-122. DOI: 10.1016/0041-1647(74)90037-9.

Faghri, A., Hua, J. (1992) Evaluation of Artificial Neural Network Applications in Transportation Engineering, Transportation Research Record, v. 1358, p. 71-80.

Fotheringham, A.S. (1983) Some theoretical aspects of destination choice and their relevance to production-constrained gravity models. Environment and Planning A: Economy and Space, v. 15, n. 8, p. 1121-1132. DOI: 10.1068/a151121.

Guerrero, E., Laguna, R., Damián, M., Ortíz, J., Zárate, R. (2020). Basic considerations for the application of discrete choice experiments: a review. Revista Mexicana de Ciencias Forestales, v. 11, n. 59, p. 4-30. DOI: 10.29298/rmcf.v11i59.676.

Hess, S., D. Palma (2019) Apollo: A Flexible, Powerful and Customisable Freeware Package for Choice Model Estimation and Application. Journal of Choice Modelling, v. 32. DOI: 10.1016/j.jocm.2019.100170.

IBGE - Instituto Brasileiro de Geografia e Estatística, 2010. Censo Demográfico 2010.

IBM Corp. Released 2016. IBM SPSS Statistics for Windows, Version 24.0. Armonk, NY: IBM Corp.

IPLAN (2013) Plano Diretor de Mobilidade Urbana de Santa Maria (1ª Edição). Santa Maria: Prefeitura Municipal de Santa Maria.

Luce, R. D., Suppes, P. (1965) Preference, utility, and subjective probability. In R. D. Lute, R. R. Bush, & E. Galanter (Fds.), Handbook of Mathematical Psychology, v. 111, p. 249-410.

McFadden, D. (1973) Conditional Logit Analysis of Qualitative Choice Behaviour. Frontiers in Econometrics, p. 105-142.

Mcfadden, D. (1974) The Measurement of Urban Travel Demand. Journal of Public Economics, v. 3, n. 4, p. 303-328. DOI: 10.1016/0047-2727(74)90003-6.

Mishra, S., Yanli, W., Xiaoyu, Z., Rolf, M, Subrat, M. (2013) Comparison between Gravity and Destination Choice Models for Trip Distribution in Maryland, Transportation Research Board 92nd Annual Meeting, p. 1-22.

Mozolin, M. J. C., Thilland, E. L. (2000) Trip distribution forecasting with multilayer perceptron neural networks: A critical evaluation. Transportation Research Part B, v. 34, n. 1, p. 53-73. DOI: 10.1016/S0191-2615(99)00014-4.

Ortúzar, J. D., Willumsen, L. G. (2011) Modelling Transport. Wiley, London.

Plaza, C.V., Rodrigues da Silva, A.N. (2021). Estimating intrazonal trip distances in a Brazilian medium-sized city. Case Studies on Transport Policy, v. 9, n. 2, p. 626-636. DOI: 10.1016/j.cstp.2021.03.001.

Pitombo, C. S., de Souza, A. D., Lindner, A. (2017) Comparing decision tree algorithms to estimate intercity trip distribution, Transportation Research Part C, v. 17, p. 16-32. DOI: 10.1016/j.trc.2017.01.009.

Pitombo, C. S.; Sousa, A. J.; Filipe, L. M. N. (2009) Classification and regression tree, principal components analysis and multiple linear regression to summarize data and understand travel behavior. Transportation Letters, v. 1, p. 295-308. DOI: 10.3328/TL.2009.01.04.295-308.

R Core Team (2020) R: A Language and Environment for Statistical Computing. Vienna, Austria: R Foundation for Statistical Computing.

Rasouli, M., Nikraz, H. (2013). Trip Distribution Modelling Using Neural Network. Transport Research Forum, Brisbane, Australia.

Schneider, M. (1959). Gravity model and trip distribution theory, Papers in Regional Science, v. 5, n. 1, p. 51-56. DOI: 10.1111/j.1435-5597.1959.tb01665.x.

Shmueli, D., Salomon, I., Shefer, D. (1996) Neural network analysis of travel behavior: Evaluating tools for prediction, Transportation Research Part C, v. 4, p. 151–166. DOI: 10.1016/S0968-090X(96)00007-1.

Smith, M. (1996) Neural Networks for Statistical Modeling. International Thomson Computer Press, Londres, Inglaterra.

Stouffer, S. A. (1940) Intervening Opportunities: A Theory Relating Mobility and Distance, American Sociological Review, v. 5, p. 845-867. DOI: 10.1016/S1003-6326(10)60620-6.

Subba Rao, P. V., Sikdar, P. K., Krishna Rao, K. V., Dhingra, S. L. (1998) Another insight into artificial neural networks through behavioural analysis of access mode choice. Computers, Environment and Urban Systems, v. 22, n. 5, p. 485-496. DOI: 10.1016/S0198-9715(98)00036-2.

Tavasszy, L.; De Jong, G. (2014) Modelling Freight Transport. 1ª. ed. London: Elsevier.

Thomas, R.W., Hugget, R.J. (1980) Modeling in Geography: A Mathematical Approach. Barnes and Noble, Totowa.

Tillema, F., Van Zuilekom, K. M., Van Maarseveen, M. F. (2006) Comparison of neural networks and gravity models in trip distribution. Computer-Aided Civil and Infrastructure Engineering, v. 21, n. 2, p. 104-119. DOI: 10.1111/j.1467-8667.2005.00421.x.

Williams, H.C.W.L. (1977) On the formation of travel demand models and economic evaluation measures of user benefit. Environment and Planning A: Economy and Space, v. 9, n. 3, 285–344. DOI: 10.1068/a090285.

Williams, I. (1976) A comparison of some calibration techniques for doubly constrained models with an exponential cost function, Transportation Research, v. 10, n. 2, p. 91-104. DOI: 10.1016/0041-1647(76)90045-9.

Wilson, A. G. (1967) A statistical theory of spatial distribution models, Transportation Research, v. 1, n. 3, p. 253–269. DOI: 10.1016/0041-1647(67)90035-4.

Zhao X, Yan X, Yu A, Van Hentenryck P. (2020) Prediction and behavioral analysis of travelmode choice: A comparison of machine learning and logit models. Travel Behaviour and Society, v. 20, p. 22-35. DOI: 10.1016/j.tbs.2020.02.003.

Downloads

Publicado

26-08-2022

Como Citar

Urano de Carvalho Caldas, M. ., Souza Pitombo, C. ., Lobo Umbelino de Souza, F. ., & Favero, R. (2022). Abordagem desagregada de distribuição de viagens urbanas: uma análise comparativa entre redes neurais e artificiais e modelos de escolha discreta. TRANSPORTES, 30(2). https://doi.org/10.14295/transportes.v30i2.2686

Edição

Seção

Artigos