ABSTRACT
In the context of the rapid development of urban rail transit, accurate and real-time short-term passenger flow forecasting is of great importance for the operation of urban rail transit. Considering stations with different passenger flow characteristics require different prediction models, this paper uses the K-means algorithm to cluster the stations with the characteristics of inbound and outbound passenger flow time distribution. After that, to improve the accuracy of the short-term passenger flow prediction results of urban rail transit, based on the passenger flow prediction using GRU alone, the SSA-GRU model combining GRU and sparrow search algorithm (SSA) is proposed for the problems of difficult adjustment of its model hyperparameters and slow convergence, and the hyperparameters of GRU are used as the parameter optimization target of SSA to complete the modeling and prediction. The experiment proves that the SSA-GRU model has good prediction performance and can be effectively applied to short-term passenger flow prediction of urban rail transit.
