The invention relates to the technical field of traffic data processing, in particular to a space-time traffic flow missing data filling method and system, and the method comprises the steps: firstly obtaining traffic flow and weather data, then dividing a whole city into geographic units, carrying out the data processing, and respectively extracting time features and space features for obtaining; the method comprises the following steps: firstly, acquiring a time feature, then fusing the time feature and the space feature to obtain a space-time feature, and finally supplementing missing data by adopting a predictor of a missing value supplementing module to obtain a final complete traffic flow and effectively eliminate the problems of missing values and the like, thereby improving the accuracy of missing value filling under various traffic conditions.
本发明涉及交通数据处理技术领域,特别涉及一种时空交通流量缺失数据填充方法及系统,先获取交通流量和天气数据,再将整个城市划分为一个个地理单元进行数据处理后分别提取时间特征和空间特征获取,然后将时间特征与空间特征相融合得到时空特征,最后采用缺失值补充模块的预测器对缺失数据补充,得到最终的完整交通流量,有效消除缺失值等问题,从而在各种交通条件下提高缺失值填充的准确性。
Space-time traffic flow missing data filling method and system
一种时空交通流量缺失数据填充方法及系统
2024-05-31
Patent
Electronic Resource
Chinese
Missing traffic state data filling method based on generative adversarial network
European Patent Office | 2023
|Missing traffic flow interpolation method based on space-time Copula theory
European Patent Office | 2024
|Traffic flow prediction method and system containing missing data
European Patent Office | 2023
|VEHICLE TRAFFIC FLOW PREDICTION METHOD WITH MISSING DATA
European Patent Office | 2021
|Vehicle traffic flow prediction method with missing data
European Patent Office | 2023
|