摘要
采用随机生存森林模型开展交通事件持续时间分析,克服了传统决策树模型易过度拟合和传统生存分析需限制性假定及识别协变量交互作用的缺陷.该研究基于上海城市快速路网交通事件数据,结合道路几何线形、交通运行、天气状况等数据.原始数据库分为训练数据(80%)和测试数据(20%).分析结果表明事件类型、路段长度、发生地点、剩余车道数、交通流量等变量对交通事件持续时间有显著影响;影响时间预测准确率结果表明随机生存森林模型预测精度显著优于随机森林的预测精度.
A random survival forests model was employed instead of the decision tree and survival analysis method to establish the incident duration analysis model. The random survival forests model could not only overcome the disadvantage of over-fitting problems of decision tree algorithm, but also break through the limitation of restrictive assumptions and solve the problem of identifying interaction of the covariates in traditional survival analysis. This study was conducted based on traffic incident data of Shanghai urban expressways in combiafion with the road geometry data, traffic operation data and the weather condition information, where 80% data was used as training dataset and the remaining 20% as testing dataset. The results show that the incident type, the length of road, the location, the remained lane number and the traffic volume have significant impacts on incident duration, and the prediction results based on testing dataset indicate that in comparison with the random forests model the random survival forests modelis is more accurate.
作者
高珍
柯阿香
余荣杰
王雪松
GAO Zhen KE Axiang YU Rongjie WANG Xuesong(College of Software Engineering, Tongji University, Shanghai 201804, China Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai 201804, China)
出处
《同济大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
2017年第9期1304-1310,共7页
Journal of Tongji University:Natural Science
基金
上海市科学技术委员会(15DZ1204800)
国家自然科学基金(71401127)
关键词
交通运行管理
交通事件持续时间预测
随机生存森林
城市快速路
durationtransportation management
traffic incidentprediction
random survival forests
urban expressway