Principle of Demographic Gravitation to Estimate Annual Average Daily Traffic: Comparison of Statistical and Neural Network Models

This paper focuses on the application of the principle of demographic gravitation to estimate link-level annual average daily traffic (AADT) based on land-use characteristics. According to the principle, the effect of a variable on AADT of a link decreases with an increase in distance from the link. The spatial variations in land-use characteristics were captured and integrated for each study link using the principle of demographic gravitation. The captured land-use characteristics and on-network characteristics were used as independent variables. Traffic count data available from the permanent count stations in the city of Charlotte, North Carolina, were used as the dependent variable to develop statistical and neural network models. Negative binomial count statistical models (with log-link) were developed as data were observed to be over-dispersed while neural network models were developed based on a multilayered, feed-forward, back-propagation design for supervised learning. The results obtained indicate that statistical and neural network models ensured significantly lower errors when compared to outputs from traditional four-step method used by regional modelers. Overall, the neural network model yielded better results in estimating AADT than any other approach considered in this research. The neural network approach can be particularly suitable for their better predictive capability, whereas the statistical models could be used for mathematical formulation or understanding the role of explanatory variables in estimating AADT.

[1]  Dieter Wild,et al.  SHORT-TERM FORECASTING BASED ON A TRANSFORMATION AND CLASSIFICATION OF TRAFFIC VOLUME TIME SERIES , 1997 .

[2]  Shinya Kikuchi,et al.  Advances in Uncertainty Treatment in FHWA Procedure for Estimating Annual Average Daily Traffic Volume , 2012 .

[3]  Satish Sharma,et al.  Duration and Frequency of Seasonal Traffic Counts , 1993 .

[4]  Michael J Demetsky,et al.  SHORT-TERM TRAFFIC FLOW PREDICTION: NEURAL NETWORK APPROACH , 1994 .

[5]  M. Zhong,et al.  ESTIMATION OF MISSING TRAFFIC COUNTS USING FACTOR, GENETIC, NEURAL AND REGRESSION TECHNIQUES , 2004 .

[6]  John Q. Stewart,et al.  Demographic Gravitation: Evidence and Applications , 1948 .

[7]  W. Lam,et al.  Comparison of Four Modeling Techniques for Short-Term AADT Forecasting in Hong Kong , 2003 .

[8]  C Ledoux.  AN URBAN TRAFFIC CONTROL SYSTEM INTEGRATING NEURAL NETWORKS , 1996 .

[9]  Faming Liang,et al.  Bayesian neural networks for nonlinear time series forecasting , 2005, Stat. Comput..

[10]  Riccardo Rossi,et al.  Data Mining Methods for Traffic Monitoring Data Analysis: A Case study , 2011 .

[11]  Tao Wang,et al.  Improved Annual Average Daily Traffic (AADT) estimation for local roads using parcel-level travel demand modeling , 2012 .

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

[13]  Arun Chatterjee,et al.  Estimation of Traffic Volume on Rural Local Roads , 2000 .

[14]  Zhuojun Jiang,et al.  Incorporating image-based data in AADT estimation: methodology and numerical investigation of increased accuracy , 2005 .

[15]  T. Kuczek,et al.  Annual Average Daily Traffic Prediction Model for County Roads , 1998 .

[16]  Ardeshir Faghri,et al.  DEVELOPMENT OF NEURAL SIGNAL CONTROL SYSTEM--TOWARD INTELLIGENT TRAFFIC SIGNAL CONTROL , 1995 .

[17]  F. Zhao,et al.  Using Geographically Weighted Regression Models to Estimate Annual Average Daily Traffic , 2004 .

[18]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[19]  Jon D Fricker,et al.  Comparison of Annual Average Daily Traffic Estimates: Traditional Factor, Statistical, Artificial Neural Network, and Fuzzy Basis Neural Network Approach , 2008 .

[20]  Shing Chung Josh Wong,et al.  Urban traffic flow prediction using a fuzzy-neural approach , 2002 .

[21]  Dipti Srinivasan,et al.  Computational intelligence-based congestion prediction for a dynamic urban street network , 2009, Neurocomputing.

[22]  Satish Sharma,et al.  STATEWIDE TRAFFIC VOLUME STUDIES AND PRECISION OF AADT ESTIMATES. , 1996 .

[23]  S C Sharma,et al.  The precision of average annual daily traffic volume estimates from seasonal traffic counts: Alberta example , 1996 .

[24]  D. Schrank,et al.  THE 2004 URBAN MOBILITY REPORT , 2002 .

[25]  Zhuojun Jiang,et al.  Improved AADT Estimation by Combining Information in Image- and Ground-Based Traffic Data , 2006 .

[26]  Yuanchang Xie,et al.  Predicting motor vehicle collisions using Bayesian neural network models: an empirical analysis. , 2007, Accident; analysis and prevention.

[27]  Kara M. Kockelman,et al.  Quantifying the Uncertainty in Annual Average Daily Traffic (AADT) Count Estimates , 2007 .

[28]  Ivica Kostanic,et al.  Principles of Neurocomputing for Science and Engineering , 2000 .

[29]  Zhuojun Jiang,et al.  Estimating AADT from Satellite Imagery and Air Photos: Empirical Results , 2003 .

[30]  Terutoshi Kaku,et al.  DEVELOPMENT OF A SELF-ORGANIZING TRAFFIC CONTROL SYSTEM USING NEURAL NETWORK MODELS , 1991 .

[31]  Kara M. Kockelman,et al.  Forecasting Network Data , 2009 .

[32]  Yuanlu Bao,et al.  Efficient local AADT estimation via SCAD variable selection based on regression models , 2011, 2011 Chinese Control and Decision Conference (CCDC).

[33]  S Sellam,et al.  ON THE USE OF NEURAL NETWORKS TECHNIQUES FOR TRAFFIC FLOW MODELING , 1995 .

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

[35]  V. Clark,et al.  Computer-aided multivariate analysis , 1991 .

[36]  Fei Xu,et al.  Application of Neural Networks to Estimate AADT on Low-Volume Roads , 2001 .

[37]  Fei Xu,et al.  Estimation of Annual Average Daily Traffic on Low-Volume Roads: Factor Approach Versus Neural Networks , 2000 .

[38]  Fang Zhao,et al.  Estimation of Annual Average Daily Traffic for Nonstate Roads in a Florida County , 1999 .

[39]  S C Sharma,et al.  SEASONAL TRAFFIC COUNTS FOR A PRECISE ESTIMATION OF AADT , 1994 .

[40]  Faming Liang,et al.  An Effective Bayesian Neural Network Classifier with a Comparison Study to Support Vector Machine , 2003, Neural Computation.