Expressway traffic accident risk identification based on association rules
The intricate relationship among the influencing factors of expressway traffic accidents is of great significance to reveal the mechanism and patterns behind these incidents.By employing methods such as social network analysis,the Apriori algorithm,and visualization,this study introduces a hierarchical association rule mining process that spans from macro to micro levels.It delves into the association rules derived from Apriori algorithm under clustering and multi-dimensional interaction,uncovering the association rules among various influencing factors of a expressway traffic accident.The results indicate significant variations in accident lane distributions and patterns across different road sections.Apriori algorithm can accurately deciphers multi-dimensional association rules,identify minibuses,the first lane and sunny days as the key risk factors affecting highway traffic accidents.It identifies guardrail collisions and rear-end collisions as prevalent accident types.Notably,the road section between markers K227 and K300,characterized by some curved stretches and multiple interchanges near urban areas,is recognized as a high-risk zone.The research proves that the process can effectively identify the accident risk,reveal the accident mechanism,and provide theoretical guidance for the improvement of expressway traffic safety.
traffic safetyexpressway traffic accidentsrisk identificationApriori Association Rule Algorithmcause of accident
万方数据
维普
