Traffic condition estimation with pre-selection space time model

Abstract

A pre-selection space time model was proposed to estimate the traffic condition at poor-data-detector, especially non-detector locations. The space time model is better to integrate the spatial and temporal information comprehensibly. Firstly, the influencing factors of the “cause nodes” were studied, and then the pre-selection “cause nodes” procedure which utilizes the Pearson correlation coefficient to evaluate the relevancy of the traffic data was introduced. Finally, only the most relevant data were collected to compose the space time model. The experimental results with the actual data demonstrate that the model performs better than other three models.

Keywords

traffic condition / estimation / space time model / pre-selection

References

[1] LiuY., ShaMan.. Research on prediction of traffic flow at non-detector intersections based on ridge trace and fuzzy linear regression analysis [C]. Proceedings of International Conference on Computational Intelligence and Security, 2009, Washington D C, CPS: 571-575

[2] WangY.-b., PapageorgiouM., MessmerA.. Real-time freeway traffic state estimation based on extended kalman filter: A case study [J]. Transportation Science, 2007, 41(2): 167-181

[3] SMITH B L, DEMERTSKY M J. Short-term traffic flow prediction: Neural network approach [J]. Transportation Research Record, 1994(1453): 98–104.

[4] SmithB. L., WilliamsB. M., OswalsdR. K.. Comparison of parametric and nonparametric models for traffic flow forecasting [J]. Transportation Research Part C: Emerging Technologies, 2002, 10(4): 303-321

[5] WilliamsB. M., HoelL. A.. Modeling and forecasting vehicular traffic flow as a seasonal arima process: Theoretical basis and empirical results [J]. Journal of Transportation Engineering, 2003, 129(6): 642-672

[6] HanC., SongSu.. A review of some main models for traffic flow forecasting [C]. Proceedings of International IEEE Conference on Intelligent Transportation Systems, 2003, Shanghai, IEEE: 216-219

[7] ZhangH., WangW., GuH.-zhong.. Application of cluster analysis and stepwise regression in predicting the traffic volume of lanes [J]. Journal of Southeast University (English Edition), 2005, 21(3): 359-362

[8] KAMARIANAKIS Y. Spatial time series modeling: A review of the proposed methodologies [R]. The Regional Economics Applications Laboratory. 2003.

[9] KamarianakisY., PrastacosP.. Space-time modeling of traffic flow [J]. Computers and Geosciences, 2005, 31(2): 119-133

[10] MinW., WynterL., AmemiyaY.. Real time road traffic prediction with spatio-temporal correlations [J]. Transportation Research Part C: Emerging Technologies, 2011, 19(4): 606-616

[11] SunS.-l., ZhangC.-shui.. The selective random subspace predictor for traffic flow forecasting [J]. IEEE Transactions on Intelligent Transportation Systems, 2007, 8(2): 367-373

[12] PfeiferP. E., DeutschS. J.. Variance of the sample-time autocorrelation function of contemporaneously correlated variables [J]. SIAM Journal of Applied Mathematics: Series A, 1981, 40(1): 133-136

[13] PfeiferP. E., DeutschS. J.. A three-stage iterative procedure for space-time modeling [J]. Technometrics, 1980, 22(1): 35-47

[14] GiacominiR., GrangerC. W. J.. Aggregation of space time processes [J]. Journal of Econometrics, 2004, 118(1): 7-26

[15] JiaL.-min.Study on the novel and intelligent magnetic detectors [R], 2008, Beijing, Beijing Jiaotong University and Beijing Traffic Management Bureau Report

[16] KINDZERSKE M D, NI D H. Composite nearest neighbor nonparametric regression to improve traffic prediction [J]. Transportation Research Record: Journal of the Transportation Research Board, 2007(1993): 30–35.

[17] GUYON I, ELISSEEFF A. An introduction to variable and feature selection [J]. Journal of Machine Learning Research, 2003(3): 1157–1182.

[18] SunX.-liang.Research on traffic state forecasting towards urban freeway [D], 2009, Beijing, Beijing Jiaotong University