摘要
依托上海市南北高架西侧的交通流数据,引入生存分析方法,建立基于风险的交通拥堵持续时间模型.其根据大量交通拥堵样本的时间属性,采用Kaplan-Meyer非参数回归模型定量估计拥堵持续时间,并按星期数、高峰时段、数据年限、样本位置和天气划分五类影响因素,从生存函数和危险函数两个方面,分析拥堵持续时间的时空分布特性.结果表明上海市南北高架西侧的交通拥堵持续时间70%能在1小时内消散,在不同类别的影响因素下分布特性存在明显差异.
Based on the historical traffic data of the west-side North-South Viaduct in Shanghai ,this paper introduces survival analysis into the analysis of traffic congestion mechnism ,and a hazard-based traffic congestion duration time model is presentd .This model analyzes the time attributes of many traffic congestion samples ,and employs nonparametric regression-based Kaplan-Meyer model to esti-mate traffic congestion duration time .Then ,the key influence factors of traffic congestion are divided into five types including weekdays ,peak time ,data year ,location and weather ,and the spatial-tem-poral distribution characteristics of traffic congestion duration time is analyzed .Analsis results has shown that the 70% of traffic congestion durations on road segments of west-side North-South Via-duct are no longer than an hour ,and there exists significant difference of distribution characteristics under different influence factors .
出处
《武汉理工大学学报（交通科学与工程版）》
2014年第1期1-6,共6页
Journal of Wuhan University of Technology（Transportation Science & Engineering）
基金
国家863计划项目(批准号:2012AA112307)
上海市创新基金项目(批准号:11ZZ27)资助
关键词
智能交通系统
交通拥堵
持续时间
生存分析
非参数回归
intelligent transportation
traffic congestion
duration time
survival analysis
non-para-metric regression
