Dynamic Travel Time Prediction using Pattern Recognition

21 Travel-time information is an essential part of Advanced Traveler Information Systems (ATISs) 22 and Advanced Traffic Management Systems (ATMSs). A key component of these systems is the 23 prediction of travel times. From the perspective of travelers such information may assist in 24 making better route choice and departure time decisions. For transportation agencies these data 25 provide criteria with which to better manage and control traffic to reduce congestion. This study 26 proposes a dynamic travel time prediction algorithm that matches current traffic patterns to 27 historical data. Unlike previous approaches that use travel time as the control variable, the 28 approach uses the temporal-spatial traffic state evolution to match traffic states and predict travel 29 times. The approach first identifies candidate historical time intervals by matching real-time 30 traffic state data against historical data for use in prediction purposes. Subsequently, the selected 31 candidates are used to predict the temporal-spatial evolution of traffic. Lastly, dynamic travel 32 times are constructed using the identified candidate historical data. The proposed algorithm is 33 tested on a 37-mile freeway segment from Newport News to Virginia Beach along the I-64 and I34 264 freeways using historical INRIX data. The prediction results indicate that the proposed 35 method produces predictions that are more accurate than the state-of-the-art K-Nearest Neighbor 36 methods reducing the prediction error by 15 percent to less than 3 minutes on a 50-minute trip. 37 38 Chen, Rakha and McGhee 2