American Society of Civil Engineers


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


by Venkata Ramana Duddu, A.M.ASCE, (Graduate Student, Civil and Environmental Engineering, Univ. of North Carolina at Charlotte, 9201 University City Blvd., Charlotte, NC 28223-0001 E-mail: vduddu@student.uncc.edu) and Srinivas S. Pulugurtha, (corresponding author), M.ASCE, (Associate Professor, Civil and Environmental Engineering, Assistant Director of Center for Transportation Policy Studies, Univ. of North Carolina at Charlotte, 9201 University City Blvd., Charlotte, NC 28223-0001 E-mail: sspulugurtha@uncc.edu)

Journal of Transportation Engineering, Vol. 139, No. 6, June 2013, pp. 585-595, (doi:  http://dx.doi.org/10.1061/(ASCE)TE.1943-5436.0000537)

     Access full text
     Purchase Subscription
     Permissions for Reuse  

Document type: Journal Paper
Section Heading: Transportation Systems
Abstract: 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.


ASCE Subject Headings:
Traffic volume
Neural networks
Statistics
Geographic information systems

Author Keywords:
Average annual daily traffic (AADT)
Neural network
Statistical model
Four-step method
GIS