Speeding and dangerous driving have consistently been recognized as important issues for the City of Edmonton. To improve drivers’ compliance with speeds, various passive/active countermeasures have been adopted by municipalities around the world. A Driver Feedback Sign (DFS) is one such countermeasure as it dynamically displays the speed of the driver and warns them if they are speeding. Acknowledging positive public response, the City has implemented DFSs at various accident-prone areas across the city. While DFS is deemed effective in voluntary speed reduction, high costs along with the need to cover Edmonton’s large road network necessitate a strategic and scientific approach to allocating signs.
This presentation will demonstrate how different modelling frameworks can be developed and applied to solve the following two specific problems using the City as a case study:
1) Estimation of safety benefits of DFS, and
2) Development of the optimal DFS implementation strategy.
About the Speakers
Dr. Tae J. Kwon joined the University of Alberta in 2016 after receiving his Ph.D. from the University of Waterloo. Dr. Kwon’s research focuses on winter road maintenance, location optimization of Intelligent Transportation System facilities, geomatics, spatial and temporal analyses of road traffic and safety using Big Data and Deep Learning. Dr. Kwon’s research has been supported by many organizations including NSERC, Alberta Transportation, Alberta EcoTrust, Iowa Department of Transportation, CIMA+, and others.
Mingjian Wu is a Ph.D. student at the University of Alberta under the supervision of Dr. Tae J. Kwon. During his M.Sc. studies, Mr. Wu focused on quantifying the safety effects of driver
feedback sign (DFS) and location allocation strategies under the co-supervision of Dr. Kwon and Dr. El-Basyouny. Mr. Wu’s current research interests lie primarily in the areas of Artificial Intelligence (AI) and Big Data analysis in winter transportation engineering (e.g., winter road maintenance), traffic safety and collision modelling, and facility location and allocation optimizations using various heuristic algorithms.