基于决策树的水上交通事故影响因素耦合分析  

Analysis on influencing factor coupling of waterway traffic accidents based on decision tree

作　　者：张丽丽 吕靖[2] ZHANG Lili;LYU Jing(College of International Business, Shandong Jiaotong University, Weihai 264200, Shandong, China;Transportation Management College, Dalian Maritime University, Dalian 116026, Liaoning, China)

机构地区：[1]山东交通学院国际商学院,山东威海264200 [2]大连海事大学交通运输管理学院,辽宁大连116026

出　　处：《上海海事大学学报》2018年第4期63-69,共7页Journal of Shanghai Maritime University

基　　金：国家自然科学基金(71372086);山东交通学院博士科研启动基金

摘　　要：为深入探究重特大水上交通事故影响因素耦合机制,基于我国水上交通事故严重程度分类和影响因素数据的分布特征,采用C5. 0决策树算法,以从939份事故调查报告中获取的事故影响因素集为输入变量,以事故类型(一般事故、重特大事故)为输出,构建事故严重程度影响因素决策树模型。优化关键参数,从生成的推理规则集中提取9种易引发重特大事故的多因素耦合模式。结果显示,在"船员操作故意违规、浪为8级及以上、政府部门监督管理严重不足、航运企业安全管理严重不足、时段为0:00—3:59或20:00—23:59、事故造成船舶全损"耦合模式下,重特大事故样本数最多,应作为重点的事故防范情境。In order to explore the coupling mechanism of influencing factors of very serious waterway traffic accidents in depth,the C5.0decision tree algorithm is adopted to construct a decision tree model of accident severity influencing factors based on the severity classification of waterway traffic accidents in China and the data distribution characteristics of influencing factors.It takes the influencing factor set of the accidents as input variables and takes accident classification(general accidents and very serious accidents)as the output,where the influencing factor set is obtained from939accident investigation reports.Nine coupled modes of multiple influencing factors that may cause very serious accidents are extracted from the reasoning rule sets after optimizing key parameters.The results show that,in the coupled mode of“the intentional illegal operation of crew,the waves no less than level8,serious shortage of the government department management and the shipping enterprise safety management,the time from0:00to3:59or from20:00to23:59,and total loss of ships caused by accidents”,the number of very serious accident samples is maximal,so this mode should be regarded as the focus of accident prevention situations.

关 键 词：水上交通事故 影响因素 因素耦合 C5.0决策树 

分 类 号：U698.6[交通运输工程—港口、海岸及近海工程]