Application of neural networks to estimate AADT on low-volume roads

Citation
S. Sharma et al., Application of neural networks to estimate AADT on low-volume roads, J TRANSP E, 127(5), 2001, pp. 426-432
Citations number
22
Categorie Soggetti
Civil Engineering
Journal title
JOURNAL OF TRANSPORTATION ENGINEERING-ASCE
ISSN journal
0733947X → ACNP
Volume
127
Issue
5
Year of publication
2001
Pages
426 - 432
Database
ISI
SICI code
0733-947X(200109/10)127:5<426:AONNTE>2.0.ZU;2-5
Abstract
Artificial neural networks are applied as a means of estimating the average annual daily traffic (AADT) volume from short-period traffic counts. Fifty -five automatic traffic recorder sites located on low-volume rural roads in Alberta, Canada are studied. The neural network models used in this study are based on a multilayered, feedforward, and back-propagation design for s upervised learning. The AADT estimation errors resulting from various durat ions and frequencies of counts are analyzed by computing average and percen tile errors. The results of this study indicate a clear preference for two 48-h counts as compared to other frequencies (one or three) or durations (2 4- or 72-h) of counts. In fact, the 95th percentile error values of about 2 5% for the neural network models compare favorably with the values reported in the literature for low-volume roads using the traditional factor approa ch. A number of advantages of the neural network approach over the traditio nal factor approach of AADT estimation are also included in the paper.