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

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