01153370

Component

This study developed a tool that can assist traffic engineers in selecting intersection signal plans that accommodate safely and efficiently both motorized and non-motorized users along urban arterials. A case study of a newly built bicycle facility in downtown Montreal, Quebec, was investigated using a microscopic traffic simulator, VISSIM. To account for the effect of signal timing plans on delay and perceived risk at intersection crossings a combined performance measure, DS, was used. A neural-network model was defined to identify out of three possible configurations (i.e. independent signals, coordinated for vehicle progression, and coordinated for bicycle progression) what the type of signal timing plan yields the best trade off between vehicle delay and safety of non-motorized users. Based on several levels of input flows from real-world and simulated traffic data a large pool of possible input/output combinations was used to train and test a MLP neural network with two hidden layers. It was found that for 99.8% of the tested cases the neural network identifies correctly the configuration of signal timing plan that yields the lowest DS value.

01147878

10-0536

English

17p

2010

Transportation Research Board 89th Annual Meeting

DVD

Figures (6) ; References (30) ; Tables (3)

Arterial highways; Case studies; Multimodal transportation; Neural networks; Pedestrian safety; Signalization; Signalized intersections; Traffic engineering; Traffic signal timing; Traffic simulation; Urban areas

Bicycle safety

Montreal (Canada)

Highways; Operations and Traffic Management; Safety and Human Factors; I73: Traffic Control

Transportation Research Board Annual Meeting 2010 Paper #10-0536

TRIS, TRB

Jan 25 2010 10:16AM