The invention discloses a traffic state prediction integration method, and belongs to the technical field of public traffic passenger flow detection. The method comprises the following steps: constructing a robust integrated model which maximizes diversity among components, and inputting each training data subset into a corresponding sub-model for training; and updating each sub-model through a designed iterative algorithm, after iteration is finished, generating an optimal prediction model, inputting a to-be-predicted data set into the generated sub-model so as to obtain a prediction result of each sub-model, and giving a final prediction value on the basis of the prediction result. The method can effectively improve the short-time traffic state prediction precision in complex scenes (such as weather conditions, traffic jams or traffic accidents).
本发明公开了一种交通状态预测集成方法,属于公共交通客流检测技术领域。本发明构建鲁棒的且最大化各组件之间多样性的集成模型,将每个训练数据子集输入相应的子模型进行训练;通过设计的迭代算法更新每个子模型,当迭代结束后,生成最优的预测模型,把待预测数据集输入至生成的子模型,从而获得每个子模型的预测结果,在此基础上给出最终的预测值。通过本发明可有效地提高复杂场景(如天气情况、交通拥堵或交通事故等)下的短时交通状态预测精度。
Traffic state prediction integration method
一种交通状态预测集成方法
2023-04-28
Patent
Elektronische Ressource
Chinesisch
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
TRAFFIC STATE PREDICTION DEVICE AND TRAFFIC STATE PREDICTION METHOD
Europäisches Patentamt | 2020
|TRAFFIC STATE PREDICTION DEVICE AND TRAFFIC STATE PREDICTION METHOD
Europäisches Patentamt | 2022
|TRAFFIC STATE PREDICTION DEVICE AND TRAFFIC STATE PREDICTION METHOD
Europäisches Patentamt | 2021
|