Urban Traffic Congestion Prediction Study:Case Study of Xi'an City
With the development of the economy and the improvement of living standards,traveling and tourism have gradually become a popular way of leisure,especially during the National Day and other holidays.However,urban traffic congestion caused by concentrated travel demand not only affects travel efficiency and experience,but also increases the pressure of urban operation.This study takes Xi'an as an example to deeply analyze the traffic congestion patterns and characteristics during the holiday period,and proposes a deep learning-based congestion prediction model,ConstFormer.The model integrates the graph convolutional network(GCN)and Transformer architectures,which explores spatial adjacencies using the GCN,and the Transformer's self-attention mechanism to mine long spatial and temporal dependencies to effectively predict future traffic conditions.Comparison experiments show that the ConstFormer model achieves the best performance over the baseline model,which can help people avoid peak periods and rationalize their travel arrangements.
万方数据
维普
