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

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.