Resumen
Travel time is important information for management and planning of road traffic. In the past decades, automated vehicle identification (AVI) systems have been deployed in many cities for collecting reliable travel time data. The fast technology advance has made the budget cost of such data collection system much cheaper than before. For example, bluetooth and WiFi-based systems have become economically a more feasible way for collecting interval travel time information in urban area. Due to increasing availability of such type of data, this paper aims to develop a travel time prediction approach that may take into account both online and historical measurements. Indeed, a statistical prediction approach for real-time application is proposed, modeling the deviation of live travel time from historical distribution estimated per time interval. An extended Kalman Filter (EKF) based algorithm is implemented to combine online travel time with historical patterns. In particular, the system delay due to vehicle re-identification is considered in the algorithm development. The methods are evaluated using Automated Number Plate Recognition (ANPR) data collected in Stockholm. The results show that the prediction performance is good and reliable in capturing major trends during congestion buildup and dissipation.