The invention discloses an urban traffic flow prediction method, system and device based on a generative adversarial network, and relates to the field of urban traffic flow prediction.The method comprises the steps that according to travel demand data of each traffic flow area in a research city in the current stage, a Node2Vec graph embedding algorithm is adopted, and an embedding matrix of the research city in the current stage is determined; and inputting the embedded matrix of the research city in the current stage and the random noise conforming to Gaussian distribution into the trained generator as input values, and predicting the traffic flow of the research city in the future stage. According to the invention, the basic mode of how the traffic flow evolves along with the change of the travel demand can be captured, so that the traffic flow can be accurately predicted.
本发明公开了一种基于生成对抗网络的城市交通流量预测方法、系统及设备,涉及城市交通流量预测领域,该方法包括:根据当前阶段研究城市中每个交通流量区域的出行需求数据,采用Node2Vec图嵌入算法,确定当前阶段研究城市的嵌入矩阵;将当前阶段研究城市的嵌入矩阵和符合高斯分布的随机噪声作为输入值,输入到训练好的生成器中,预测未来阶段研究城市的交通流量。本发明能够捕捉交通流量如何随着出行需求的变化而演化的基本模式,从而实现准确预测交通流量。
Urban traffic flow prediction method, system and equipment based on generative adversarial network
基于生成对抗网络的城市交通流量预测方法、系统及设备
2023-10-31
Patent
Elektronische Ressource
Chinesisch
Urban traffic flow prediction method based on generative adversarial network
Europäisches Patentamt | 2020
|Traffic flow prediction method based on generative adversarial network
Europäisches Patentamt | 2021
|SATP-GAN: self-attention based generative adversarial network for traffic flow prediction
Taylor & Francis Verlag | 2021
|Road traffic network state prediction based on a generative adversarial network
IET | 2020
|Prediction of Urban Traffic Flow Based on Generative Neural Network Model
British Library Conference Proceedings | 2018
|