基于可视分析的交通事故致因挖掘研究  

Research on Traffic Accident Causation Based on Visual Analysis

作　　者：吴昌述 廖竞[1] 熊建华 寇露彦 陈永辉[1] WU Changshu;LIAO Jing;XIONG Jianhua;KOU Luyan;CHEN Yonghui(School of Computer Science and Technology,Southwest University of Science and Technology,Mianyang 621010)

机构地区：[1]西南科技大学计算机科学与技术学院,绵阳621010

出　　处：《计算机与数字工程》2024年第8期2384-2392,共9页Computer & Digital Engineering

基　　金：国防基础计划科研项目(编号:JCKY2019204B007,JCKY2018404C001)资助。

摘　　要：研究交通事故的特征和致因分析是交通安全分析中的核心问题。现有主流方法中基于Apriori的交通事故挖掘分析过程中会产生大量无效的规则,对致因分析存在较大的干扰,影响分析效率。论文将可视化与关联规则挖掘方法结合,可视化构建事故挖掘约束集,引导用户设置合理的挖掘约束。以2019年加利福利亚州的交通事故数据为研究对象,对交通事故进行可视分析,提取事故的主要特征,构建事故挖掘约束集,运用优化Apriori挖掘事故深层致因。实验表明,该方法能够有效降低无效规则的产生,提高挖掘效率。The study of traffic accident characteristics and causation analysis is the core problem in traffic safety analysis.The existing mainstream methods of Apriori-based traffic accident mining analysis process will generate a large number of invalid rules,which will interfere with the causation analysis and affect the analysis efficiency.In this paper,it combines visualization with association rule mining methods to visually construct accident mining constraint sets and guide users to set reasonable mining constraints.Using the traffic accident data of California in 2019 as the research object,the visual analysis of traffic accidents is conducted,the main features of accidents are extracted,the accident mining constraint sets are constructed,and the optimized Apriori is used to mine the deep causative factors of accidents.The experiments show that the method can effectively reduce the generation of invalid rules and improve the mining efficiency.

关 键 词：致因挖掘 APRIORI 可视分析 交通事故 

分 类 号：TP391.7[自动化与计算机技术—计算机应用技术]