Subway Short-term Passenger Flow Prediction Based on Improved LSTM

An improved long short-term memory (LSTM) model based on ensemble empirical mode decomposition (EEMD) is designed for short-term passenger flow prediction in view of the complex dynamics, uncertainty and prediction difficulty of subway inbound passenger flow. First, the raw data is decomposed into several stationary components and a residue by EEMD method. Then, a combination of high-correlation components and a combination of low-correlation components obtained by calculating Pearson Correlation Coefficient between each component and the raw data are combined with date feature to form the input set of LSTM neural network. And the predicted passenger flow data is the output set. Finally, compared with the single LSTM model, the trained EEMD-LSTM model is better according to the metrics, and the absolute error of the EEMD-LSTM model is significantly lower during the peak passenger flows. The experimental results of Tiantongyuan Station of Beijing Metro Line 5 show that the improved model can effectively improve the prediction accuracy, which is conducive to the dynamic adjustment of station management plan.