Abstract
This study aims to discover hidden patterns and potential relationships in risk factors in freight truck crash data. Existing studies mainly used parametric models to analyze the causes of freight vehicle crashes. However, predetermined assumptions and underlying relationships between independent and dependent variables have been cited as its limitations. To overcome these limitations and provide a better understanding of factors that lead to truck crashes on the expressways, we applied the Association Rules Mining (ARM) technique, which is a nonparametric method. ARM quantifies the interrelationships between the antecedents and consequents of truck-involved crashes and provides researchers with the most influential set of factors that leads to crashes. We utilized a freight vehicle-involved crash data consisting of 19,038 crashes that occurred on the Korean expressways from 2008 to 2017 for this investigation. From the data, 90,951 association rules were generated through ARM employing the Apriori algorithm. The lift values estimated by the Apriori algorithm showed the strength of association between risk factors, and based on the estimated lift values, we identified key crash contributory factors that lead to truck-involved crashes at various segment types, under different weather conditions, considering the driver’s age, crash type, driver’s faults, vehicle size, and roadway geometry type. From the generated rules, we demonstrated that overspeeding with medium-weight trucks was highly associated with crashes during the rainy weather, whereas drowsy driving during the evening was correlated with crashes during fine weather. Segment-related crashes were mainly associated with driver’s faults and roadway geometry. Our results present useful insights and suggestions that can be used by transport stakeholders, including policymakers and researchers, to create relevant policies that will help reduce freight truck crashes on the expressways.
Highlights
Due to the function of the expressways, they are characterized by unique features that contribute to increased crash severity and risk [10, 11]. e primary objective of this study is to identify patterns and relationships in expressway freight truck crash-risk factors that are usually unknown to researchers using association rules mining (ARM)
Following Agrawal et al [7], we define a rule as an implication of the form A ⟹ B, where A (Driver’s age group: 20s, Weather: Rainy) and B (Crash type: Vehicle-vehicle) are itemsets which belong to D, A is the antecedent on the left hand side (LHS), and B is the consequent on the right hand side (RHS) of the rule, and A ⊂ I, B ⊂ I, and A ∩ B { }
To concentrate on attaining meaningful analysis, we identify critical crash contributory factors that lead to truckinvolved crashes at various segment types, under different weather conditions, considering the drivers age (20s and 30s), crash type, driver’s faults, vehicle weight (
Summary
While there may be fewer crashes involving freight trucks on expressways, the unique features of trucks with respect to their size and weight, and their operational characteristics contribute to the signi cant increase in fatalities and loss of property [1, 3]. Journal of Advanced Transportation factors, they are to be studied thoroughly in order to find meaningful countermeasures for truck crashes [5]. Based on this recognition, recent studies have employed association rules mining (ARM), a data mining technique to identify interesting associations between contributory crash factors that simultaneously impact crashes [6]. E primary objective of this study is to identify patterns and relationships in expressway freight truck crash-risk factors that are usually unknown to researchers using ARM
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
