Traffic Flow Prediction for Urban Network using Spatio-Temporal Random

1 Traffic prediction is critical to success of Intelligent Transportation Systems (ITS). Predicting 2 traffic on an urban traffic network using spatio-temporal models has become a popular research 3 area in the past decade. The model does not only rely on observation data at the detector of 4 interest but also takes advantage of neighboring detectors to provide better prediction capability. 5 However, most models suffer high mathematical complexity and low flexibility in tune-up. This 6 paper presents a novel Spatio-Temporal Random Effects (STRE) model that has a reduced 7 computational complexity due to mathematical dimension reduction, and additional tune-up 8 flexibility provided by the basis function that is able to take traffic patterns into account. The 9 City of Bellevue, WA is selected as the model test site due to the widespread locations of the 10 loop detector in the City. Data collected from 105 detectors in the downtown area during the first 11 two weeks of July, 2007 are used in the modeling process and the traffic volumes are predicted 12 for 14 detectors during the first week of July, 2008. The results not only show that the model can 13 effectively consider the neighboring detectors to accurately predict the traffic in locations with 14 regular traffic patterns, but also verify its temporal transferability. Except three special locations, 15 all experimental links have Mean Average Percentage Errors (MAPEs) between 8% and 15%. 16 Without further model tune-up, the results are encouraging. 17 18 19 20 Wu, Chen, Lu and Smith 2

[1]  Hashem R Al-Masaeid,et al.  Short-Term Prediction of Traffic Volume in Urban Arterials , 1995 .

[2]  Timothy C. Coburn,et al.  Statistical and Econometric Methods for Transportation Data Analysis , 2004, Technometrics.

[3]  Wanli Min,et al.  Real-time road traffic prediction with spatio-temporal correlations , 2011 .

[4]  Eleni I. Vlahogianni,et al.  Spatio‐Temporal Short‐Term Urban Traffic Volume Forecasting Using Genetically Optimized Modular Networks , 2007, Comput. Aided Civ. Infrastructure Eng..

[5]  Matthew G. Karlaftis,et al.  A multivariate state space approach for urban traffic flow modeling and prediction , 2003 .

[6]  Qingquan Li,et al.  A spatial analysis approach for describing spatial pattern of urban traffic state , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[7]  Brian Lee Smith,et al.  Meeting Real–Time Traffic Flow Forecasting Requirements with Imprecise Computations , 2003 .

[8]  Man-Chun Tan,et al.  An Aggregation Approach to Short-Term Traffic Flow Prediction , 2009, IEEE Transactions on Intelligent Transportation Systems.

[9]  Y. Kamarianakis,et al.  Forecasting Traffic Flow Conditions in an Urban Network: Comparison of Multivariate and Univariate Approaches , 2003 .

[10]  Zhirui Ye,et al.  Short‐Term Traffic Volume Forecasting Using Kalman Filter with Discrete Wavelet Decomposition , 2007, Comput. Aided Civ. Infrastructure Eng..

[11]  Matthias Katzfuss,et al.  Spatio‐temporal smoothing and EM estimation for massive remote‐sensing data sets , 2011 .

[12]  Yi Zhang,et al.  Short-term traffic flow forecasting of urban network based on dynamic STARIMA model , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[13]  Jiaqiu Wang,et al.  Spatio-temporal autocorrelation of road network data , 2012, J. Geogr. Syst..

[14]  Zuo Zhang,et al.  Urban traffic network modeling and short-term traffic flow forecasting based on GSTARIMA model , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[15]  N. Cressie,et al.  Fixed Rank Filtering for Spatio-Temporal Data , 2010 .

[16]  Yiannis Kamarianakis,et al.  Modeling Traffic Volatility Dynamics in an Urban Network , 2005 .

[17]  Tom Thomas,et al.  Predictions of Urban Volumes in Single Time Series , 2010, IEEE Transactions on Intelligent Transportation Systems.

[18]  Billy M. Williams,et al.  Comparison of parametric and nonparametric models for traffic flow forecasting , 2002 .

[19]  Michael J Demetsky,et al.  TRAFFIC FLOW FORECASTING: COMPARISON OF MODELING APPROACHES , 1997 .

[20]  Billy M. Williams,et al.  Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results , 2003, Journal of Transportation Engineering.

[21]  Brian W. Sloboda,et al.  Statistical and Econometric Methods for Transportation Data Analysis , 2012 .

[22]  Biswajit Basu,et al.  Multivariate Short-Term Traffic Flow Forecasting Using Time-Series Analysis , 2009, IEEE Transactions on Intelligent Transportation Systems.

[23]  Stephen Graham Ritchie,et al.  TRANSPORTATION RESEARCH. PART C, EMERGING TECHNOLOGIES , 1993 .

[24]  GhoshBidisha,et al.  Multivariate short-term traffic flow forecasting using time-series analysis , 2009 .

[25]  Eleni I. Vlahogianni,et al.  Enhancing Predictions in Signalized Arterials with Information on Short-Term Traffic Flow Dynamics , 2009, J. Intell. Transp. Syst..