A Clustering-Based Approach to Detecting Critical Traffic Road Segments in Urban Areas

This paper introduces a parameter-free clustering-based approach to detecting critical traffic road segments in urban areas, i.e., of spatially prolonged and high accident risk. In addition, it proposes novel domain-specific criterion for evaluating the clustering results, which promotes stability results through time inter-period spatial collocation, penalizes size selected clusters. To illustrate proposed approach, is applied data on accidents with injuries or death that occurred three largest cities Serbia over three-year period.