The purpose of the present research is to conduct a comparative study on the dynamic estimation of network origin-destination (OD) demands using two statistical methods, that is least squares and Kalman filtering (KF) methods, and an artificial intelligence (AI) approach, i.e., Artificial Neural Network (ANN) model. The numerical test results based on field data collection and simulation experiments indicate that the ordinary least squares(OLS) method with nonnegative constraint provides a satisfactory result in solving the intersection turning proportions problem. Besides, in the freeway / expressway and general network cases, both the KF and ANN methods show statistically acceptable results, even though the ANN method providesa more stable and better result. In accordance with the above model evaluation results, one can design beneficial traffic control and / or management strategies to achieve some system-wide objectives. For the covering abstract see ITRD E134653.
Abstract