基于生存分析的城市道路交通拥堵持续时间研究  被引量:12

Survival Analysis Approach for Estimating Urban Traffic Congestion Duration

在线阅读下载全文

作  者:周映雪[1] 杨小宝[1] 环梅[1] 四兵锋[1] 

机构地区:[1]北京交通大学交通运输学院,北京100044

出  处:《应用数学和力学》2013年第1期98-106,共9页Applied Mathematics and Mechanics

基  金:国家重点基础研究发展计划973资助项目(2012CB725400);国家自然科学基金资助项目(70901005;71071016;71131001)

摘  要:根据北京市二环快速路的交通流数据,研究了城市道路交通拥堵持续时间的分布特性.采用生存分析方法,建立基于风险的交通拥堵持续时间模型,运用非参数方法对交通拥堵的持续时间进行估计,并对其时空分布规律进行了研究.结果表明二环各路段的拥堵持续时间70%在4 min以内,89%在12 min之内;当拥堵持续时间超过12 min之后拥堵结束的可能性小于10%.工作日比双休日更容易发生拥堵;早高峰比晚高峰更容易发生拥堵,且当拥堵发生的前提下早高峰的拥堵持续时间更长;内环比外环更容易发生拥堵,但外环的拥堵持续时间更长;二环的4个方向上,西二环最容易发生拥堵,北二环的拥堵持续时间最长.Based on the empirical traffic flow data on the second Ring Road in Beijing, the dis- tribution characteristic of traffic congestion duration was analyzed. The hazard-based traffic congestion duration model was established through survival analysis method. The duration time of traffic congestion was estimated and the temporal-spatial distribution was studied using non- parametric method. The results show that 70% of the congestion durations of road segments on the second Ring Road are not longer than four minutes. 89% of the congestion durations are not longer than 12 minutes. The hazard rate is less than 10% when the duration is longer than 12 minutes. The occurrence frequency of congestion on weekday is longer than that on week- end. Both the occurrence frequency and the duration of traffic congestion at morning peak are longer than those at evening peak. The occurrence frequency of congestion on the inner ring is longer than that on the outer ring while the congestion duration on the outer ring is longer than the duration on the inner ring. In the four directions of the second Ring Road, the occurrence frequency of congestion in the west is longest. The congestion duration in the north is longest.

关 键 词:城市道路 交通拥堵 持续时间 生存分析 

分 类 号:U491[交通运输工程—交通运输规划与管理]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象