Bluetooth Traffic Data for Urban Travel Time Forecast

This paper investigates the problem of the network performance forecast by using traffic data acquired via Bluetooth devices in order to provide advanced models and tools for the prediction of congestion effects in urban areas. A data driven approach is adopted where different statistical models are tested within a methodology framework in which the above data are filtered, cleaned and fused for a better prediction of path travel times. The proposed approach has been applied to the city of Rome: performances that better fit observed traffic conditions have been obtained by adopting an ARIMA based model whose promising results of online forecast are presented and discussed.