The invention discloses a traffic speed short-term prediction method for road section classification based on topological similarity, and belongs to the field of intelligent traffic. The method comprises the following specific operation steps: 1, extracting upstream and downstream road section information of a road section, performing topological similarity analysis on the road section, generating a road section category identification code, and classifying the road section according to the identification code; 2, matching the vehicle GPS track data into an urban road network, preprocessing the track data corresponding to each type of road section set, and constructing a road traffic speed space-time matrix; and 3, constructing a long short-term memory (LSTM) network model for each type of road section set, and inputting trajectory data to carry out model training and testing. According to the invention, on the basis of analyzing the topological similarity of the road sections to classify the road sections, a scheme of carrying out traffic speed short-term prediction in combination with the LSTM model is proposed, and the characteristics of similar road section traffic flow modes are reserved, so that the model prediction precision is improved.
本发明公开了一种基于拓扑相似性进行路段分类的交通速度短时预测方法,属于智能交通领域。具体操作步骤如下:1,提取路段上下游路段信息,对路段进行拓扑相似性分析并生成路段类别标识码,根据标识码对路段进行分类;2,将车辆GPS轨迹数据匹配到城市路网中并将每类路段集合对应的轨迹数据进行预处理,构建道路交通速度时空矩阵;3、针对每类路段集合构建长短期记忆网络(LSTM)模型,输入轨迹数据进行模型训练和测试。本发明在提出在分析路段拓扑相似性进行路段分类的基础上结合LSTM模型进行交通速度短时预测的方案,保留了相似路段交通流模式的特性,从而提高模型预测精度。
Traffic speed short-term prediction method for road section classification based on topological similarity
一种基于路段拓扑结构分类的交通速度短时预测方法
2021-06-01
Patent
Elektronische Ressource
Chinesisch
Europäisches Patentamt | 2015
|Short-Term Traffic Speed Prediction for Multiple Road Segments
Springer Verlag | 2023
|