The invention provides an urban traffic prediction method and system based on spatio-temporal data flow fusion analysis. The method comprises the following steps: fitting a single-class traffic data flow based on a polynomial function, and predicting a traffic state according to a fitting result; fusing various traffic data streams based on a data envelope analysis model, and predicting the traffic state according to the fusion result; analyzing the continuous time interval of each transportation junction point based on a preset clustering algorithm, and predicting the traffic state accordingto a clustering result; and calculating center points of all the transportation junction points based on a preset method, and performing traffic state prediction according to the change amplitude of the center points. The traffic abnormal state reflected by the single traffic data flow and the multiple data flows in the coverage area of the single monitoring point and the urban regional traffic abnormality reflected by the multiple detection points can be identified, and the prediction accuracy can be improved based on traffic data analysis of different hierarchies.
本发明提供了一种基于时空数据流融合分析的城市交通预测方法和系统。所述方法包括:基于多项式函数拟合单类交通数据流,根据拟合结果对交通状态进行预测;基于数据包络分析模型对各类交通数据流进行融合,根据融合结果对交通状态进行预测;基于预设聚类算法对各交通枢纽点的连续时间间隔进行分析,根据聚类结果对交通状态进行预测;基于预设方法计算所有交通枢纽点的中心点,根据中心点变化幅度进行交通状态预测。本实施例可以识别单一监测点覆盖范围内由单一交通数据流和多数据流反应出的交通异常状态,以及由多个检测点共同反应出的城市区域性交通异常,基于不同层级的交通数据分析,可以提高预测的准确性。
Urban traffic prediction method and system based on spatio-temporal data flow fusion analysis
基于时空数据流融合分析的城市交通预测方法和系统
2020-05-19
Patent
Electronic Resource
Chinese
Urban traffic flow prediction: a spatio-temporal variable selection-based approach
Online Contents | 2016
|Traffic flow prediction method for multivariate traffic flow spatio-temporal data information
European Patent Office | 2024
|Traffic flow prediction method based on spatio-temporal information fusion and storage medium
European Patent Office | 2024
|Traffic flow spatio-temporal data prediction method, system, device and medium
European Patent Office | 2023
|Urban Traffic Flow Prediction Using a Spatio-Temporal Random Effects Model
Taylor & Francis Verlag | 2016
|