Evaluating the Operational Performance of Road Intersections by Mining Trajectory Data Streams

点击翻译按钮获取中文摘要

Traffic congestion describes a situation on transport networks that occurs when demand approaches thecapacity of a road (or of the intersections along the road). It is characterized by slower speeds, longer trip times,and increased vehicle queues and is associated to significant social, economic and environmental costs. Roadintersections represent one of the most complex configurations encountered when traversing road networks anda high percentage of accidents occur at these locations. It is therefore of vital importance to improve theiroperational performance, as that can significantly contribute towards the efficiency of the whole transportnetwork. Traditional approaches to improve the efficiency of intersections are based on analysis of static dataor expert opinions. However, today's vehicles are no longer stand-alone transportation means. Due to theadvancements on Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication technologies itis possible to enhance safety and improve road intersection efficiency by continuously monitoring trafficinformation and enabling situational awareness of vehicle drivers.In this project, in collaboration with Fortran Traffic Systems Limited, we aim to leverage big data mining andmachine learning techniques to continuously monitor the operational performance of road intersections throughmining real-time V2I data. A key to the success of these methods is the quality and timeliness of the analysisprovided. The anticipated outcome of the research is twofold: (i) an increased safety and efficiency of roadintersections, and (ii) a data-driven approach to evaluate road intersection operational performance.The proposed research collaboration aligns with Canada's Innovation Agenda. Conducting research in theintersection of big data analytics and machine learning has the potential to attract the brightest students fromaround the world, while keeping domestic talent here.