| Résumé | A grade crossing is defined as an intersection between a roadway and a railway at the same elevation or grade. Multiple new prevention measures have been implemented to reduce the number of train-vehicle collisions; however, crossing safety remains a major issue as accidents still frequently occur. The push for machine learning-based model to analyze risks at grade crossings has also increased to keep up with new technologies. There are many different protection types (gates with bells, cross-buck, stop-sign, mirrors and etc.) that serve to warn or stop oncoming traffic. Many attributes have an inherent impact on accident frequency, including the protection type, train speed, traffic volume and etc. To find out which factors are most important, we propose a machine learning-based method to effectively analyze the impact of multiple factors that affect crossing safety and subsequently provide scientific insight for key factors for enhancing crossing safety. In this work, the Canadian crossing accident database from 2004 to 2013 was used with additional generated features to enhance the performance of models. These include features that were computed using geographical information systems (GIS) and sightline measurements. Based on the performance, the machine learning algorithm, RandomForest is used to rank and analyze 21 attributes for each protection type. From the analysis results it is possible to identify which key factors have the highest influence on improving safety and collision prediction at grade crossings. |
|---|
