Modeling Individual Travel Time with Back Propagation Neural Network Approach for Advanced Traveler Information Systems

Abstract

The heterogeneous driving behaviors from different travelers are not considered in current advanced traveler information systems (ATIS) such as Google Maps and 511 systems, which leads the systems to generate the same travel time for everyone who inputs the same origin and destination. This paper explores the modeling of individualized travel time based on the individual behavior of each driver as opposed to average traffic information, with the ultimate goal of enabling individualized traffic information provision for the ATIS and subsequently reducing travel-time prediction errors. A back propagation neural network model was built to quantitatively estimate the driving behavior differences (i.e., the delta) between individual drivers and the surrounding traffic, with both roadway geometrics and dynamic traffic conditions considered in the modeling process. A travel-time estimation algorithm is then proposed to derive link-level traffic information that considers individual behavioral difference. Finally, individualized route travel time is computed for each traveler based on the derived link-level traffic information and individual behavioral difference. The proposed model is implemented and tested on an open-source Next Generation Simulation (NGSIM) dataset, which demonstrated the feasibility and effectiveness of the proposed model. The proposed model has the potential of being directly applied to enhance existing ATIS travel-time prediction accuracies.