Hierarchical clustering analysis framework of mutually exclusive crash causation parameters for regional road safety strategies

Hierarchical clustering analysis framework is developed to identify benchmark and critical regions for effective road safety strategies. The regions are grouped based on agglomeration coefficient of mutually exclusive crash causation parameters. Subsequently, regions from groups with lower than a threshold index value are selected as benchmark for the poorly performing critical counterparts. Euclidean distance-based Ward's, median and centroid clustering techniques are explored through a case study of Indian states and Union Territories. As per data between 2006 and 2015, fatal crash percentages of driving under influence of drug and alcohol, excessive speeding, vehicle malfunction and road conditions related crash causation parameters, severity index and its growth rate are assessed based on respective threshold values of 6.35%, 43.28%, 2.42%, 1.79%, 26.7 and 3.1%. These are the national average of respective indices. It demonstrated the unique application of hierarchical clustering analysis in benchmark and critical region identification.     

Predictability and interpretability of hybrid link-level crash frequency models for urban arterials compared to cluster-based and general negative binomial regression models

Machine learning (ML) techniques have higher prediction accuracy compared to conventional statistical methods for crash frequency modelling. However, their black-box nature limits the interpretability. The objective of this research is to combine both ML and statistical methods to develop hybrid link-level crash frequency models with high predictability and interpretability. For this purpose, M5′ model trees method (M5′) is introduced and applied to classify the crash data and then calibrate a model for each homogenous class. The data for 1134 and 345 randomly selected links on urban arterials in the city of Charlotte, North Carolina was used to develop and validate models, respectively. The outputs from the hybrid approach are compared with the outputs from cluster-based negative binomial regression (NBR) and general NBR models. Findings indicate that M5' has high predictability and is very reliable to interpret the role of different attributes on crash frequency compared to other developed models.