Research on Influencing Factors of Urban Road Traffic Casualties through Support Vector Machine

Urban road traffic safety has always been vital in transportation research. This paper analyzed the factors influencing degree of accident casualties on Jinan Jingshi Road and its branch roads, taking them as study area for urban problems. Additionally, it used application Particle Swarm Optimization (PSO), a Support Vector Machine (SVM) model, recursive feature elimination (RFE) to rank contribution factors. The results showed that driving rainy days high probability casualties, while type collision was minimum influence factor. days, cars were accident-prone vehicles, 8:00–12:00 18:00–22:00 periods. Based results, preventive measures further put forward regarding driver, drainage capacity, policy management, autopilot technology. aimed guide planning provide basis developing measures.