Using principal curves to analyse traffic patterns on freeways

Scatterplots of traffic speed versus flow have received considerable attention over the past decades due to their characteristic half-moon shape. Modelling data of this type is difficult as both variables are actually not a function of each other in the sense of causality, but are rather jointly generated by a third latent variable, which is a monotone function of the traffic density. We propose local principal curves (LPCs) as a tool to describe and model speed–flow data, which takes this viewpoint into account. We introduce the concept of calibration curves to determine the relationship between the latent variable (represented by the parametrisation of the principal curve) and the traffic density. We apply LPCs to a variety of speed–flow diagrams from Californian freeways, including some so far unreported patterns.

[1]  Nathan H. Gartner,et al.  Traffic Flow Theory - A State-of-the-Art Report: Revised Monograph on Traffic Flow Theory , 2002 .

[2]  Dewang Chen,et al.  Freeway traffic stream modeling based on principal curves and its analysis , 2004, IEEE Transactions on Intelligent Transportation Systems.

[3]  James H Banks,et al.  SYNTHESIS OF RECENT WORK ON THE NATURE OF SPEED-FLOW AND FLOW-OCCUPANCY (OR DENSITY) RELATIONSHIPS ON FREEWAYS , 1992 .

[4]  Michael Z. F. Li.  A Generic Characterization of Equilibrium Speed-Flow Curves , 2008, Transp. Sci..

[5]  Ryan Fries,et al.  Development of a sensor system for traffic data collection , 2009 .

[6]  Joseph L. Schofer,et al.  A STATISTICAL ANALYSIS OF SPEED-DENSITY HYPOTHESES , 1965 .

[7]  Pedro Delicado,et al.  Principal Curves of Oriented Points: theoretical and computational improvements , 2003, Comput. Stat..

[8]  Markos Papageorgiou,et al.  Real-time merging traffic control with applications to toll plaza and work zone management , 2008 .

[9]  B D Greenshields,et al.  A study of traffic capacity , 1935 .

[10]  Kara M. Kockelman.  Modeling traffic's flow-density relation: Accommodation of multiple flow regimes and traveler types , 2001 .

[11]  Mei Chen,et al.  A Nested Clustering Technique for Freeway Operating Condition Classification , 2007, Comput. Aided Civ. Infrastructure Eng..

[12]  Tsu Chin,et al.  California Partners for Advanced Transit and Highways (PATH) , 2004 .

[13]  Gerhard Tutz,et al.  Exploring Multivariate Data Structures with Local Principal Curves , 2004, GfKl.

[14]  Chao Chen,et al.  The PeMS algorithms for accurate, real-time estimates of g-factors and speeds from single-loop detectors , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[15]  Lawrence W. Lan,et al.  Short-term prediction of traffic dynamics with real-time recurrent learning algorithms , 2009 .

[16]  Jochen Einbeck,et al.  Data Compression and Regression Based on Local Principal Curves , 2008, GfKl.

[17]  F. Hall.  TRAFFIC STREAM CHARACTERISTICS , 1997 .

[18]  Pravin Varaiya.  Freeway Performance Measurement System (PeMS) Version 4 , 2004 .

[19]  Dirk Helbing,et al.  Empirical Features of Congested Traffic States and Their Implications for Traffic Modeling , 2007, Transp. Sci..

[20]  T. Hastie,et al.  Principal Curves , 2007 .

[21]  Bin Ran,et al.  AN APPLICATION OF NEURAL NETWORK ON TRAFFIC SPEED PREDICTION UNDER ADVERSE WEATHER CONDITION , 2003 .

[22]  Gerhard Tutz,et al.  Local principal curves , 2005, Stat. Comput..

[23]  J. G. Wardrop,et al.  Some Theoretical Aspects of Road Traffic Research , 1952 .

[24]  G. Tutz,et al.  Generalized monotonic regression based on B-splines with an application to air pollution data. , 2007, Biostatistics.