The invention provides a missing traffic flow interpolation method based on a space-time Copula theory, and the method comprises the steps: obtaining the traffic flow of a road section in a road network in a fixed sampling interval, and carrying out the correlation matching with the spatial position of a sampling point and the sampling time, and obtaining observation data; depicting edge distribution of a single traffic flow, and for observation data, obtaining a corresponding edge cumulative distribution function through a data distribution fitting mode; depicting a space-time dependency relationship of the traffic flow to obtain a space-time correlation matrix; and estimating parameters in the space-time correlation matrix according to a maximum likelihood method to obtain an estimated parameter set # imgabs0 #, and interpolating the missing traffic flow value at the n + 1 moment based on # imgabs1 # and # imgabs2 #. According to the method, the spatial statistical characteristics and the time sequence characteristics of the traffic flow are fused, the space-time dependence structure of the traffic flow is depicted, and the interpolation precision of missing traffic flow data is improved.
本发明提供了一种基于时空Copula理论的缺失交通流量插补方法,包括:获取路网中路段在固定采样间隔内的交通流量,并与采样点空间位置和采样时间关联匹配得到观测数据;刻画单个交通流量的边缘分布,对于观测数据,通过数据分布拟合的方式得到对应的边缘累计分布函数;刻画交通流量的时空依赖关系,得到时空相关矩阵;根据最大似然方法对时空相关矩阵中的参数进行估计,得到估计参数集#imgabs0#基于#imgabs1#和#imgabs2#对n+1时刻的缺失交通流量值进行插补。本发明实现了对交通流量的空间统计特征和时序特征融合,实现了对交通流量时空依赖结构的刻画,提高了缺失交通流量数据的插补精度。
Missing traffic flow interpolation method based on space-time Copula theory
一种基于时空Copula理论的缺失交通流量插补方法
2024-03-08
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Missing traffic flow data interpolation method of GAN network based on transmission periodicity
European Patent Office | 2024
|Space-time traffic flow missing data filling method and system
European Patent Office | 2024
|European Patent Office | 2024
|Vehicle traffic flow prediction method with missing data
European Patent Office | 2023
|