交通事故的多维关联规则分析  

THE ANALYSIS OF MULTIDIMENSIONAL ASSOCIATION RULE IN TRAFFIC ACCIDENTS

作　　者：尚威[1] 尚宁[2] 覃明贵[3] 崔中发[3] 崔岩[3] 朱扬勇[2] 

机构地区：[1]复旦大学软件学院,上海200433 [2]复旦大学计算机与信息技术系,上海200433 [3]上海宝信软件股份有限公司,上海201203

出　　处：《计算机应用与软件》2006年第2期40-42,65,共4页Computer Applications and Software

基　　金：上海信息专业资金项目基金编号:信部运[2003]446号

摘　　要：城市机动车数量的增加已经导致城市交通事故的频繁发生,能否对已发生事故作出正确的分析将直接影响到能否对未来类似事故的成功避免。本文提出一种使用数据挖掘领域中的多维关联规则技术分析大量交通事故记录的方法,通过找出可能导致交通事故发生的频繁因素组合来发现某些事故发生的规律,并将这些规律作为现实中作出预防举措的依据。The increase in the number of urban vehicles has led to the frequent occurrence of traffic accidents. Whether we can analyze those accidents correctly in the past will directly determine the avoidance of future ones of the similar kind. In this paper, we introduce a famous method in the field of data mining, called muhidimensional association rule method, helps analyze the large amounts of traffic accident records. With this method ,we are able to find out the underlying rules in traffic accidents through searching the combination of frequent factors that probably lead to traffic accidents. In addition, armed with these rules discovered, we will be able to take effective actions to prohibit the anticipated accidents in real world.

关 键 词：数据挖掘 多维关联规则 交通事故 关联规则分析 城市机动车 事故发生 技术分析 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论] U491.31[自动化与计算机技术—计算机科学与技术]