摘要
基于检测器数据的时空相关性,为缺失数据修复模型动态地选择解释变量,在综合考虑检测器数据的周期性趋势和实时变化特性的基础上,提出了一种改进的缺失数据修复方法.对上海市南北高架的线圈流量数据进行数据修复精度测试.结果表明,相较于传统的支持向量回归(SVR)模型,该方法在3个测试检测器上的数据修复平均绝对误差分别减小了3.80%、3.40%、25.23%,并且在数据连续缺失1~10个时平均绝对百分比误差均低于6%.
Based on the temporal and spatial correlation of detector data, the explanatory variables were dynamically selected for data repair model, and an improved modification method of missing data was proposed considering periodic trend and real-time variability comprehensively. The proposed method was assessed with the data of location-specific detectors in Shanghai, China. Compared with support vector regression(SVR) model, the mean absolute error of three detectors are reduced by 3.80%, 3.40%, 25.23%, and the mean absolute percentage error is less than 6% under different data missing conditions.
作者
苗旭
王忠宇
邹亚杰
吴兵
MIAO Xu;WANG Zhongyu;ZOU Yajie;WU Bing(Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai 201804, China;College of Transport and Communications, Shanghai Maritime University, Shanghai 201306, China)
出处
《同济大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2019年第10期1477-1484,共8页
Journal of Tongji University:Natural Science
基金
国家自然科学基金(51608386)
关键词
交通运输系统工程
缺失数据修复
周期性
支持向量回归(SVR)
engineering of communications and transportation system
missing data modification
periodic pattern
support vector regression(SVR)
