基于数据挖掘的路面交通信息预警模型分析  

Analysis of Road Traffic Information Early Warning Model Based on Data Mining

作　　者：李博逸 谢颖欣 但文涛 唐中屹 陈银银 Li Boyi;Xie Yingxin;Dan Wentao;Tang Zhongyi;Chen Yinyin(Hope College,Southwest Jiaotong University,Chengdu,China)

机构地区：[1]西南交通大学希望学院,四川成都

出　　处：《科学技术创新》2024年第8期33-37,共5页Scientific and Technological Innovation

基　　金：四川省2023年省级大学生创新创业训练计划(文件编号:川教函[2023]242号)。

摘　　要：为减少道路交通事故的发生,基于近年交通事故数据分析道路交通事故规律及成因,以照明条件、能见度和天气等5个因素为自变量,以无伤害、轻伤、重伤3种交通事故严重程度为因变量,采用多元Logistic回归模型和有序多分类Logistic回归模型,分析影响交通事故严重程度的重要因素。对交通事故数据进行验证,结果表明:多元Logistic回归模型和有序多分类Logistic回归模型对交通事故严重程度的正确预测率分别为73.1%、75.0%。基于数据挖掘的道路交通事故成因分析可为交通管理部门治理交通环境、降低交通事故提供依据。In order to reduce the occurrence of road traffic accidents,this paper analyzes the rules and causes of road traffic accidents based on traffic accident data in recent years.Five factors,including lighting conditions,visibility and weather,are taken as independent variables,and the severity of three traffic accidents,namely no injury,minor injury and serious injury,are taken as dependent variables.Multiple Logistic regression model and ordered multiple Logistic regression model were used to analyze the important factors affecting the severity of traffic accidents.The results show that the correct prediction rates of traffic accident severity by multiple Logistic regression model and ordered multiple Logistic regression model are 73.1% and 75.0%,respectively.The cause analysis of road traffic accidents based on data mining can provide basis for traffic management departments to control traffic environment and reduce traffic accidents.

关 键 词：数据挖掘 事故成因 事故严重程度 多元LOGISTIC回归 有序多分类Logistic回归 

分 类 号：U491.31[交通运输工程—交通运输规划与管理]