基于改进兴趣度度量与Apriori算法的交通事故多发点成因分析  

The causes analysis of traffic accident black spots based on improved interest measurement and Apriori algorithm

作　　者：王颖志[1] 沈雅婕[1] 王立君 WANG Yingzhi;SHEN Yajie;WANG Lijun(Department of Traffic Management Engineering,Zhejiang Police College,Hangzhou 310053,China;Institute for Geography and Spatial Information,Zhejiang University,Hangzhou 310028,China)

机构地区：[1]浙江警察学院交通管理工程系,浙江杭州310053 [2]浙江大学地理与空间信息研究所,浙江杭州310028

出　　处：《浙江大学学报（理学版）》2021年第3期349-355,共7页Journal of Zhejiang University（Science Edition）

摘　　要：人、车、路、环境和交通管理构成了道路交通系统,造成道路交通事故的原因是综合、复杂的。正确快速地分析事故成因,有助于提升交通管理水平,减少交通事故的发生。近年来,关联规则模型及其扩展在事故多发点成因分析中备受关注。针对关联规则分析中传统的兴趣度度量方法和Apriori算法的局限,考虑小概率因子对交通事故的影响,提出了改进的交通事故多发点成因分析方法,明确评价因素和结果之间的关联程度,提高挖掘效率。基于浙江省某市交通事故数据,结合人、车、环境与时空因素对方法进行了验证,并对方法的分析效率和结果的有效性进行了讨论。The road traffic system is composed of people,vehicles,roads,environment and traffic managements.The causes of road traffic accidents are comprehensive and complex.Accurately analyzing the causes of accidents is helpful to improve the level of traffic management and reduce the occurrence of traffic accidents.In recent years,association rule model and its extension have attracted more and more attention in the cause analysis of accident black spots.In view of the limitation of traditional interest measure method and Apriori algorithm in traditional association rule analysis,accounting for the influence of small probability factor on traffic accident,this paper proposes an improved analysis method for explaining traffic accident black spots,clarifies the correlation degree between evaluation factors and the results.In this paper,the traffic accident data of one city in Zhejiang province is used to verify the method considering factors of people,vehicles,environment and space-time,the analysis efficiency of the method and the effectiveness of the results are discussed.

关 键 词：交通事故多发点 关联规则 成因分析 频数分析 APRIORI算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]