Applying Association Rules Mining to Investigate Pedestrian Fatal and Injury Crash Patterns Under Different Lighting Conditions

Abstract

The pattern of pedestrian crashes varies greatly depending on lighting circumstances, emphasizing the need to examine pedestrian crashes in various lighting conditions. Using Louisiana pedestrian fatal and injury crash data (2010–2019), this study applied Association Rules Mining (ARM) to identify the hidden pattern of crash risk factors according to three different lighting conditions (daylight, dark-with-streetlight, and dark-no-streetlight). Based on the generated rules, the results show that daylight pedestrian crashes are associated with children (<15 years), senior pedestrians (>64 years), older drivers (>64 years), and other driving behaviors such as “failure to yield,”“inattentive/distracted,”“illness/fatigue/asleep.” Additionally, young drivers (15–24 years) are involved in severe pedestrian crashes in daylight conditions. This study also found pedestrian alcohol/drug involvement as the most frequent item in the dark-with-streetlight condition. This crash type is particularly associated with pedestrian action (crossing intersection/midblock), driver age (55–64 years), speed limit (30–35 mph), and specific area type (business with mixed residential area). Fatal pedestrian crashes are found to be associated with roadways with high speed limits (>50 mph) during the dark without streetlight condition. Some other risk factors linked with “high speed limit” related crashes are pedestrians walking with/against the traffic, presence of pedestrian dark clothing, and pedestrian alcohol/drug involvement. The research findings are expected to provide an improved understanding of the underlying relationships between pedestrian crash risk factors and specific lighting conditions. Highway safety experts can utilize these findings to conduct a decision-making process for selecting effective countermeasures to reduce pedestrian crashes strategically.

Identifying roadway departure crash patterns on rural two-lane highways under different lighting conditions: Association knowledge using data mining approach

“…It has become a more common approach to recognizing crash patterns in the highway safety research (A. Hossain, Sun, Thapa, & Codjoe, 2022;M. M. Hossain, Zhou, Das, Sun, & Hossain, 2022;Hsu & Chang, 2020;Rahman et al, 2021).…”

Applying Data Mining Methods to Explore Animal-Vehicle Crashes

“…ARM is a prominent technique in several disparate fields such as market basket analysis, product recommendation, and medical diagnostics for finding intriguing and nontrivial relationships between variables, and it has recently gained popularity in highway safety analysis (33)(34)(35)(36)(37). Transportation safety domains have been using ARM to explore underlying patterns.…”

Comparative analysis of regional variations in road traffic accident patterns with association rule mining

“…The Apriori algorithm was used to discover the patterns of vehicle-pedestrian crashes in Louisiana, and the significant patterns were analysed to formulate relevant strategies to raise awareness and mitigate future vehicle-pedestrian crashes. [15] also investigated the characteristics of pedestrian-involved crashes in Louisiana with RTA data between 2010 and 2019. The analysis focused on the RTA characteristics under different lighting conditions in which the Random Forest algorithm selected the significant variables, and the Apriori algorithm generated the association rules for the lighting conditions of daylight, dark with a streetlight, and dark without a streetlight.…”