01663609

Component

Understanding vehicles users’ travel behaviors is necessary to make better Transportation Demand Management (TDM) measures. In this paper, the authors analyze the vehicle users’ travel behavior and investigate the influence of this TDM policy adjustment on travel patterns based on Automatic License Plate Recognition (ALPR) data. In order to explore the effect of the restriction policy, both the vehicles registered in Shanghai (VRIS) and VROS were studied. A pattern recognition method combined with unsupervised and supervised classifier was used to classify vehicle users with similar travel patterns. Then, according to the daily variation of travel demand, the impact of TDM policy adjustment was analyzed. The results show that the travel behaviors of VRIS and VROS, can be classified efficiently as four and five categories by the proposed method respectively: HME of VRIS, LA of VRIS, HA of VRIS, HUE of VRIS; HME of VROS, LA of VROS, HMU of VROS, HM of VROS, HU of VROS. And there are many differences between the behaviors of VRIS and VROS. Furthermore, all patterns of VRIS made little response to the policy adjustment. And the all patterns of VROS change the trip start time to fit the new restriction policy. The reduced demand after the policy adjustment reaches largest at the extended two hours, and accounts for 28.6 percent of the travel demand before the adjustment. It turns out that, among all patterns, VROS of LA and HU are impacted more deeply.

This paper was sponsored by TRB committee ABE50 Standing Committee on Transportation Demand Management.

18-02765

English

7p

2018

Transportation Research Board 97th Annual Meeting

Digital/other

Figures; References; Tables

Automatic license plate readers; Drivers; Traffic data; Travel behavior; Travel demand management

Shanghai (China)

Data and Information Technology; Highways; Operations and Traffic Management

Transportation Research Board Annual Meeting 2018 Paper #18-02765

TRIS, TRB, ATRI

Jan 8 2018 10:40AM