摘要
现有道路交通事故统计分析技术存在数据字段缺失、分析维度单一以及实战应用性弱等问题,难以支撑交通安全系统改善对策的提出。首先,对交通事故信息要素进行细分,优化了面向事故成因分析的道路交通事故数据采集项;其次,提出了基于事故严重程度的GIS事故多发点段动态分析模型,并建立了面向人、车、路、环境不同主体和事故发生不同阶段的多维事故成因分析方法;最后,以深圳市2018年交通事故数据为例,挖掘分析事故多发点段,开展多维事故成因分析。技术方法和结论可有效支撑公安交管部门开展道路交通事故预防工作,指导交通安全系统改善行动计划开展。
The existing statistical analysis methods for road traffic accidents is problematic because of missing data items,over simplistic and weak in applications,which make it hard to be useful for proposing systematic strategies.Firstly,this article subdivides the traffic accident information elements and optimizes road traffic accident data collection items for accident cause analysis.Secondly,a dynamic analysis model has been developed based on the severity that can identify accident-prone locations using GIS.Moreover,a multi-dimensional accident cause analysis method covering different subjects of people,vehicles,roads,environments and covering different stages of accidents was established.Lastly,using Shenzhen accident data in 2018,accident-prone locations by data mining were identified and multi-dimensional accident causes was analyzed.The study methods and results can assist traffic management departments in road traffic accident prevention as well as promoting the development of systematic road safety action plan.
作者
毛应萍
于丰泉
孙烨垚
汤左淦
MAO Yingping;YU Fengquan;SUN Yeyao;TANG Zuogan(Shenzhen Urban Transport Planning Center Co.,Ltd,Shenzhen 518000,China)
出处
《交通与运输》
2020年第S02期106-111,共6页
Traffic & Transportation
关键词
道路交通安全
数据挖掘
事故多发点段
事故成因分析
GIS
Road traffic safety
Data mining
Accident-prone locations
Cause analysis of traffic accidents
GIS