Search

The subjectivity of selecting training parameters is an important factor affecting the accuracy of short‐term passenger flow prediction of rail transit by long short‐term memory (LSTM) neural network. In order to improve the prediction accuracy, an improved particle swarm optimization (IPSO) algorithm is proposed to optimize the LSTM. The size of the learning factor of the particle swarm optimization (PSO) algorithm is controlled by dynamic adjustment method to improve the global optimization and convergence ability of the algorithm. The number of hidden layer nodes, learning rate and iteration times of the LSTM are optimized by IPSO. The passenger flow data of Dongjiekou station of Fuzhou Metro Line 1 are selected for verification, and the proposed model is compared with the traditional prediction model. The results show that the LSTM optimized by the improved particle swarm optimization algorithm can effectively predict the short‐term passenger flow of rail transit. Compared with the PSO‐LSTM model, the root mean square error predicted by the IPSO‐LSTM model decreases by 10.87% in the peak period and by 26% in the off‐peak period. The results can provide theoretical and technical support for the optimization of rail transit operation scheme. [ABSTRACT FROM AUTHOR]

Accurate and stable short‐term passenger flow prediction is an indispensable part of current intelligent transportation systems. This paper proposes two deep learning prediction models based on convolutional neural networks (CNN) and long short‐term memory neural network (LSTM). Combining the CNN characteristics and the LSTM, the ConvXD‐LSTM extracts passenger flow features through CNN and then inputs the time series into the LSTM. The ConvLSTM converts the weight calculation of the LSTM into convolution operation to realize short‐term passenger flow prediction. Fuzhou Metro Line 1 passenger flow data was used for verification. The models were used to predict the passenger flow of subway stations and cross‐sections and compared with the traditional prediction models. In terms of prediction accuracy, ConvLSTM has the highest accuracy, followed by ConvXD‐LSTM. In terms of running time, ConvXD is the fastest and LSTM takes the longest. ConvXD‐LSTM and ConvLSTM are in the middle of the two models, achieving a good balance between accuracy and efficiency. Compared with ConvXD‐LSTM, ConvLSTM has a relatively simple network structure, which reduces the computational burden and improves the prediction accuracy. [ABSTRACT FROM AUTHOR]