An algorithm for traffic flow parameters estimation and prediction using composition of machine learning methods and time series models
A.A. Agafonov, V.V. Myasnikov

Image Processing Systems Institute, Russian Academy of Sciences,
Samara State Aerospace University

Full text of article: Russian language.

Abstract:
A problem of traffic flow analysis and prediction in city transport network is considered in this paper. The proposed algorithm uses GPS / GLONASS data of public transport location as input. Projecting this information on a transport network graph, as well as using additional filtering, we estimate traffic flow parameters. These parameters are used for short-term (up to 1 hour) prediction of road conditions in the city transport network. There is proposed a new method which consists of several steps to construct prediction. First, the transport graph is divided into a number of subgraphs by a territorial basis. Second, we use a dimension reduction method based on principal components analysis to describe the spatio-temporal distribution of traffic flow condition in the subgraphs. Third, an elementary prediction for each of the subgraphs is formed using the potential functions method with the measure of the subgraphs descriptions closeness introduced by analogy with bilateral filtering and support vector machine. Fourth, the additional elementary prediction is calculated using the known scalar and vector Box–Jenkins time series prediction models. Fifth, we construct the result prediction for each of the subgraphs using an adaptive linear composition of elementary predictions. At last, the traffic flow parameters are calculated as a linear combination of predictions for subgraphs of the city transport network. We have also made experimental investigations of transport network in Samara to evaluate the prediction accuracy of the proposed algorithm. The advantages of the proposed solution in comparison with existing ones are provided.

Key words:
transport network, traffic flow, traffic flow estimation, traffic flow prediction, algorithms composition, potential functions method, Box–Jenkins model, SVR.

References:

  1. Klein, L.A. Traffic Detector Handbook / L.A. Klein, D.R. Gibson, M.K. Mills // Federal Highway Administration, Turner-Fairbank Highway Research Center. – 2006. – 687p.
  2. Batty, M. Smart cities of the future / M. Batty, K.W. Axhausen, F. Giannotti, A. Pozdnoukhov, A. Bazzani, M. Wachowicz, G. Ouzounis, Y. Portugali // The European Physical Journal Special Topics. – 2012. – Vol. 214, Issue 1. – P. 481-518.
  3. Directive 2010/40/EU of the European Parliament and of the Council of 7 July 2010 on the framework for the deployment of Intelligent Transport Systems in the field of road transport and for interfaces with other modes of transport / Legislative acts // Official Journal of the European Union. – 2010. – P. 1-13.
  4. Hall, R. Handbook of transportation science / R.W. Hall. – Dordrecht: Kluwer Academic Publishers, 2003. – 737 p.
  5. Liu, X. Dynamic Graph Shortest Path Algorithm / X. Liu, H. Wang // Web-Age Information Management: Lecture Notes in Computer Science. – 2012. – Vol. 7418. – P. 296-307.
  6. Polychronopolulos, G. Stochastic shortest path problems with recourse / G. Polychronopolulos, J. Tsitsiklis // Networks. – 1996. – Vol. 27, Issue 2. – P. 133-143.
  7. Hoogendoorn, S.P. State-of-the-art of vehicular traffic flow modeling / S.P. Hoogendoorn, P.H.L. Bovy / Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering. – 2001. – Vol. 215(4). – P. 283-303.
  8. Agafonov, A.A. An algorithm for city transport arrival time estimation using adaptive elementary predictions composition // A.A. Agafonov, V.V. Myasnikov // Computer Optics. – 2014. – Vol. 38(2). – P. 356-369.
  9. Vlahogianni, E.I. Short-term traffic forecasting: Where we are and where we’re going / E.I. Vlahogianni, M.G. Karlaftis, J.C. Golias // Transportation Research Part C: Emerging Technologies. – 2014. – Vol. 43, Part 1. – P. 3-19.
  10. Bolshinsky, E. Traffic Flow Forecast Survey / E. Bolshinsky, R. Freidman // Technion – Israel Institute of Technology. – 2012. – Technical Report. – 15 p.
  11. Faouzi, N.E. Data fusion in intelligent transportation systems: Progress and challenges / N.E. Faouzi, H. Leung, A. Kurian // A survey, Information Fusion. – 2011. – Vol. 12, Issue 1. – P. 4-10.
  12. Sun, H. Short term traffic forecasting using the local linear regression model / H. Sun, H. Liu, H. Xiao, R. He, B. Ran // Journal of Transportation Research Board. – 2003. – Vol. 1836. – P. 143-150.
  13. Oswald, R. Traffic flow forecasting using approximate nearest neighbor nonparametric regression / R. Oswald, T. Scherer, B.L. Smith // The National ITS Implementation Research Center U.S. DOT University Transportation Center. – 2001. – Research Report. – 115 p.
  14. Box, G.E. Time Series Analysis: Forecasting and Control / G.E. Box, G.M. Jenkins, G.C. Reinsel. – 4th edition. – Wi­ley, 2008. – 784 p.
  15. Mai, T. Short-term traffic flow forecasting using dynamic linear models / T. Mai, B. Ghosh, S. Wilson // Irish Transport Research Network. – 2011.
  16. Stathopoulos, A. A multivariate state space approach for urban traffic flow modeling and prediction / A. Stathopoulos, M.G. Karlaftis // Transportation Research Part C: Emerging Technologies. – 2003. – Vol. 11, Issue 2. – P. 121-135.
  17. Lin, S.-H. The application of space-time ARIMA model on traffic flow forecasting / S.-H. Lin, H.-Q. Huang, D.-Q. Zhu, T.-Z. Wang // Machine Learning and Cybernetics, 2009 International Conference on. – 2009. – Vol. 6. – P. 3408-3412.
  18. Min, W. Real-time road traffic prediction with spatio-temporal correlations / W. Min, L. Wynter // Transportation Research Part C: Emerging Technologies. – 2011. – Vol. 19, Issue 4. – P. 606-616.
  19. Zheng, W. Short-term freeway traffic flow prediction: bayesian combined neural network approach / W. Zheng, D.-H. Lee, Q. Shi // Journal of Transportation Engineering. – 2006. – Vol. 132, N 2. – P. 114-121.
  20. Zhang, X. Forecasting Approach for Short-term Traffic Flow based on Principal Component Analysis and Combined Neural Network / X. Zhang, G. He // Systems Engineering: Theory & Practice. – 2007. – Vol. 27(8). – P. 167-171.
  21. Guorong, G. Traffic Flow Forecasting based on PCA and Wavelet Neural Network / G. Guorong, L. Yanping // Information Science and Management Engineering (ISME). – 2010. – Vol. 1. – P. 158-161.
  22. Jin, X. Simultaneously Prediction of Network Traffic Flow Based on PCA-SVR / X. Jin, Y. Zhang, D. Yao // Lecture Notes in Computer Science. – 2007. – Vol. 4492. – P. 1022-1031.
  23. How does the short-term forecast Yandex.Traffic. – http://habra­habr.ru/company/yandex/blog/153631/ – (In Russian).
  24. Lakhina, A. Structural analysis of network traffic flows / A. Lakhina, K. Papagiannaki, M. Crovella, C. Diot, E.D. Ko­laczyk, N. Taft // ACM SIGMETRICS Performance Evaluation Review. – 2004. – Vol. 32, Issue 1. – P. 61-72.
  25. Введение в математическое моделирование транспортных потоков / А.В. Гасников, С.Л. Кленов, Е.А. Нур­мин­ский, Я.А. Холодов, Н.Б. Шамрай; под ред. А.В. Гас­никова. – М.: МФТИ, 2010. – 362 с.
  26. Швецов, В.И. Математическое моделирование транспортных потоков / В.И. Швецов // Автоматика и телемеханика. – 2003. – № 11. – P. 3-46.
  27. Shvetsov, V.I. Mathematical modeling of traffic flows / V.I. Shvetsov // Automation and remote control. – 2003. – Vol. 64, Issue 11. – P. 1651-1689.
  28. Cascetta, E. Transportation Systems Analysis: Models and Ap­plications / E.  Cascetta. – New York: Springer, 2009. – 752 p.
  29. Копенков, В.Н. Оценка параметров транспортного потока на основе анализа данных видеорегистрации / В.Н. Копен­ков, В.В. Мясников // Компьютерная оптика. – 2014. – Т. 38, № 1. – С. 81-86.
  30. Jolliffe, I.T. Principal Component Analysis / I.T. Jolliffe. – 2nd edition. – New York: Springer, 2002. – 487 p.
  31. Aizerman, M. Theoretical foundations of the potential function method in machine learning theory / M. Aizerman, E. Braverman, L. Rozonoer. – Moscow: “Nauka” Publisher, 1970. – 384 p. – (In Russian).
    © 2009, IPSI RAS
    Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; e-mail: ko@smr.ru; Phones: +7 (846 2) 332-56-22, Fax: +7 (846 2) 332-56-20