基于互联网数据城市快速路地点安全分析方法  

Location Security Analysis of Urban Expressway Based on Internet Data

作　　者：张兴强[1,2] 刘雪 朱艺焱 宋勇刚 王欣 王学媛[1,2] ZHANG Xing-qiang;LIU Xue;ZHU Yi-yan;SONG Yong-gang;WANG Xin;WANG Xue-yuan(MOE Key Laboratory for Urban Transportation Complex Systems Theory and Technology,Beijing Jiaotong University,Beijing 100044,China;Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport,Ministry of Transport,Beijing Jiaotong University,Beijing 100044,China)

机构地区：[1]北京交通大学城市交通复杂系统理论与技术教育部重点实验室,北京100044 [2]北京交通大学综合交通运输大数据应用技术交通运输行业重点实验室,北京100044

出　　处：《交通运输系统工程与信息》2018年第5期53-59,共7页Journal of Transportation Systems Engineering and Information Technology

基　　金：国家自然科学基金(61473028)~~

摘　　要：现有的城市交通安全分析主要考虑人财物的直接损失,却忽略了事故产生的交通延误等间接损失,同时也较少利用互联网海量数据进行分析.本文建立了基于互联网文本数据的城市交通事故属性模型,采用模糊系统聚类法划分事故交通影响等级,构建了基于绝对事故次数、损害后果和交通影响的等效事故次数模型,并将其应用于累积频率曲线和K-means聚类的城市快速路地点安全组合评价方法中.北京市快速路地点安全评价结果表明,本文所提出的方法可有效地将互联网安全文本数据应用于城市交通安全分析中,分析结果可为城市交通安全管理提供有益的借鉴.Most urban traffic safety analysis considered accident’s direct losses,but neglected accident’s indirect losses such as traffic delay,and seldom used internet big data.Based on internet text data,a traffic accident attribute model of urban expressway is established,and the accident impact rank of traffic flow is classified by the fuzzy system clustering method.An equivalent accident frequency model considering absolute accident frequency,accident consequence and accident impact to traffic flow is proposed and used to location safety combined evaluation of urban expressway based on cumulative frequency curve and K-means clustering method.The evaluation results of Beijing expressway location safety show that the method could effectively apply the internet safety text data to urban traffic safety analysis and the evaluation conclusions could provide the beneficial references for urban traffic safety management.

关 键 词：城市交通 文本数据 事故属性 聚类 交通影响等级 等效事故数 组合评价 

分 类 号：U491.3[交通运输工程—交通运输规划与管理]