Neural network models for classification and forecasting of freeway traffic flow stability

Artificial Neural Networks (ANN) have been shown to perform well in classifying and prediction problems. Such a peculiarity was exploited to evaluate the flow-density relationship of a motorway section so as to define the time and spacing stability or instability of its traffic flow. The data base used in this study was built up on the basis ofthe data collected over the ltalian motorway running between Padua and Mestre. These data are suitable for the present study be cause they provi de a sample of t ime an d space, along with the collection of data on weather conditions.