A Review of Applying Traditional Travel Demand Model for Improved Network-wide Traffic Estimation: Challenges and Opportunities

摘要

Traffic estimates are of great importance to transportation planners, traffic engineers, and policy makers. However, traditional factor approach, regression-based models, and artificial neural network models failed to present network-wide traffic/truck volume estimates because they rely on traffic counts for model development and they all have inherent weaknesses. A review to previous research work and the state-of-practice clearly indicates that the Travel Demand Model (TDM) was generally based on roadway networks which ignored low-class roads. Also, large traffic analysis zones used in the TDM yielded fairly high model estimation errors. The review then focuses on the challenges and the opportunities facing researchers and practitioners in achieving improved network-wide traffic volume estimates. This paper ends with conclusions and a few recommendations for future research.