Refinement of Pattern-Matching Method for Travel Time Prediction

详细信息    查看全文

• 作者：Makoto Kasai (1)
  Hiroshi Warita (2)
  
  1. Tokyo University of Science ; 2641 Yamazaki ; Noda ; Chiba ; Japan
  2. Tokyo Metropolitan Expressway Company Limited ; 1-4-1 Kasumigaseki ; Chiyoda-ku ; Tokyo ; Japan
  
• 关键词：Travel time prediction ; Pattern matching ; Data ; driven approach
• 刊名：International Journal of Intelligent Transportation Systems Research
• 出版年：2015
• 出版时间：May 2015
• 年：2015
• 卷：13
• 期：2
• 页码：84-94
• 全文大小：1,888 KB
• 参考文献：1. Bajwa, S.I., Chung, E., Kuwahara, M.: 鈥淎n adaptive travel time prediction model based on pattern matching鈥? Proceedings of 11th World Congress on Intelligent transport systems. 12pages (2004)
  2. Warita, H, Ueno, H, Chung, E, Tanaka, A (2004) A study on the method of travel time prediction using pattern matching. Rep. Traff. Eng. Assem. 24: pp. 129-132
  3. Bajwa, S.I., Chung, E., Kuwahara, M.: 鈥淧erformance evaluation of an adaptive travel time prediction model鈥? Proceedings of the 8th International IEEE Conference on Intelligent Transportation Systems. pp. 1000鈥?005 (2005)
  4. Kasai, M., Rokutan, M., Uchiyama, H.: 鈥淎n application of Bayesian statistics to estimating travel time on an urban expressway鈥? Proceedings of the 15th World Congress on Intelligent Transport Systems. 10pages (2008)
  5. Kasai, M., Uchiyama, H.: 鈥淎 study on estimation of probabilistic changing travel time based on Bayesian statistics鈥? Selected Proceedings of the 12th World Conference on Transport Research (WCTRs). 15pages (2010)
  6. Vlahogianni, EI, Karlaftis, MG, Golias, JC (2006) Statistical methods for detecting nonlinearity and non-stationarity in univariate short-term time-series of traffic volume. Transp. Res. C 14: pp. 351-367 CrossRef
  7. Billings, D., Yangt, J.: 鈥淎pplication of the ARIMA models to urban roadway travel time prediction鈥攁 case study鈥? 2006 I.E. International Conference on Systems, Man, and Cybernetics. pp. 2529鈥?534 (2006)
  8. Guin, A.: 鈥淭ravel time prediction using a seasonal autoregressive integrated moving average time series model鈥? Proceedings of the IEEE Intelligent Transportation Systems Conference 2006. pp. 493鈥?98 (2006)
  9. Wen, Y., Lee, T., Cho, H.: 鈥淗ybrid models toward traffic detector data treatment and data fusion鈥? Proceedings of Networking, Sensing and Control 2005. pp. 525鈥?30 (2005)
  10. Lint, JWC (2008) Online learning solutions for freeway travel time prediction. IEEE Trans. Intell. Transp. Syst. 9: pp. 38-47 CrossRef
  11. Yu, J., Chang, G., Ho, H.W., Liu, Y.: 鈥淰ariation based online travel time prediction using clustered neural networks鈥? Proceedings of the 11th International IEEE Conference on Intelligent Transportation Systems. pp. 85鈥?0 (2008)
  12. Zhu, G., Wang, X.: 鈥淪tudy on route travel time prediction based on RBF neural network鈥? 2009 First International Workshop on Education Technology and Computer Science. pp. 1118鈥?122 (2009)
  13. Hinsbergen, CPIJ, Lint, JWC, Zuylen, HJ (2009) Bayesian committee of neural networks to predict travel times with confidence intervals. Transp. Res. C 17: pp. 498-509 CrossRef
  14. Vanajakshi, L, Subramanian, SC, Sivanandan, R (2009) Travel time prediction under heterogeneous traffic conditions using global positioning system data from buses. IET Intell. Transp. Syst. 3: pp. 1-9 CrossRef
  15. Jou, Y., Lee, T., Lan, C., Hsu, C.: 鈥淭he implementation of Markov bias corrected grey system in freeway travel time prediction鈥? Proceedings of Intelligent Transportation Systems 2003. pp. 832鈥?35 (2003)
  16. Yeon, J, Elefteriadou, L, Lawphongpanich, S (2008) Travel time estimation on a freeway using Discrete Time Markov Chains. Transp. Res. B 42: pp. 325-338 CrossRef
  17. Zhang, X, Rice, JA (2003) Short-term travel time prediction. Transp. Res. C 11: pp. 187-210 CrossRef
  18. Rice, J, Zwet, E (2004) A simple and effective method for predicting travel times on freeways. IEEE Trans. Intell. Transp. Syst. 5: pp. 200-207 CrossRef
  19. Huang, L., Barth, M.: 鈥淎 novel loglinear model for freeway travel time prediction鈥? Proceedings of the 11th International IEEE Conference on Intelligent Transportation Systems. pp. 210鈥?15 (2008)
  20. Zou, N., Wang, J., Chang, G.: 鈥淎 reliable hybrid prediction model for real-time travel time prediction with widely spaced detectors鈥? Proceedings of the 11th International IEEE Conference on Intelligent Transportation Systems. pp. 91鈥?6 (2008)
  21. Winkler, RL (1972) An introduction to Bayesian inference and decision. Holt, Rinehart and Winston, INC., New York
  22. Kasai, M., Uesugi, R., Takasawa, S., Terabe, S.: 鈥淎n experimental study on learning effects on mode choice behavior in dynamic park and ride鈥? Proceedings of the 14th International IEEE Conference on Intelligent Transportation Systems. pp. 1096鈥?102 (2011)
  23. Matsuba, K, Matsumoto, Y, Sugihara, Y (2004) Estimation of vehicle trajectories and travel times on urban expressway from traffic counts. Infrastruct. Plan. Rev. 21: pp. 899-906 CrossRef
  24. Jacoby, SLS, Kowalik, JS, Pizzo, JT (1972) Iterative methods for nonlinear optimization problems. Prentice-Hall, Englewood Cliffs
  
• 刊物类别：Engineering
• 刊物主题：Electrical Engineering
  Civil Engineering
  Computer Imaging, Vision, Pattern Recognition and Graphics
  User Interfaces and Human Computer Interaction
  Automotive Engineering
  Robotics and Automation
  
• 出版者：Springer New York
• ISSN：1868-8659

文摘

This paper reconsiders how to define the similarity between historical and current day travel time data in pattern matching for travel time prediction. The core idea of pattern matching is designing a measurement of similarity, and the similarity function is intuitively presumed to have a negative exponential distribution. Here, a gamma distribution that includes this exponential distribution is introduced as an alternative. Complimentary mechanisms are also tried. The results of application to data from an urban expressway are summarized as follows: although the prediction accuracy of the refined method is only slightly better than pattern matching based on previous pattern matching, marginally better fitness is found.