Pattern Recognition Approach for Road Collision Hotspots Analysis: Case Study of Northern Ireland

In order to address road safety effectively, it is essential to understand all the factors, which<br/>attribute to the occurrence of a road collision. This is achieved through road safety<br/>assessment measures, which are primarily based on historical crash data. Recent advances<br/>in uncertain reasoning technology have led to the development of robust machine learning<br/>techniques, which are suitable for investigating road traffic collision data. These techniques<br/>include supervised learning (e.g. SVM) and unsupervised learning (e.g. Cluster Analysis).<br/>This study extends upon previous research work, carried out in Coll et al. [3], which<br/>proposed a non-linear aggregation framework for identifying temporal and spatial hotspots.<br/>The results from Coll et al. [3] identified Lisburn area as the hotspot, in terms of road safety,<br/>in Northern Ireland. This study aims to use Cluster Analysis, to investigate and highlight any<br/>hidden patterns associated with collisions that occurred in Lisburn area, which in turn, will<br/>provide more clarity in the causation factors so that appropriate countermeasures can be put<br/>in place.