With the continuous increase in the number of motor vehicles and the frequent occurrence of road congestion problems, it has become an important research topic to carry out comprehensive collection of traffic road network status information, processing analysis, prediction, and decision-making recommendation to effectively solve urban traffic problems. The traffic flow is one of the main parameters reflecting the road operation status. It is of great significance to timely and accurately grasp and predict the road traffic situation, which is of great significance for diverting vehicles in advance and improving the operation capacity and efficiency of the road network. Due to the complex spatial structure of the road network, the road traffic flow is non-Euclidean, non-directional, and the change over time is non-stationary, which has a strong time dependence, which leads to greater challenges in traffic flow prediction. This paper comprehensively considers the characteristics of the temporal and spatial correlation of traffic flow, and provides a city traffic flow prediction method based on graph convolutional neural network, which can effectively mine the temporal and spatial dynamic patterns of urban road network traffic flow and realize accurate traffic flow prediction.
Research on City Traffic Flow Forecast Based on Graph Convolutional Neural Network
2021-03-26
1444887 byte
Conference paper
Electronic Resource
English
Multi-scale traffic flow prediction method based on graph convolutional neural network
European Patent Office | 2021
|Urban Taxi Demand Forecast Based on Graph Convolutional Network
Springer Verlag | 2022
|European Patent Office | 2023
|Short-term traffic flow prediction method based on integrated graph convolutional neural network
European Patent Office | 2024
|Urban traffic flow space-time prediction scheme based on graph convolutional neural network
European Patent Office | 2021
|