Short-term passenger flow prediction is one key prerequisite of decision making in daily operations. Subway operators concentrate on both the efficiency of the prediction model and the accuracy of the prediction results. In this study, the authors explore a deep learning-based hybrid model, which integrates a long–short-term memory neural network (LSTM NN) and stacked auto-encoders (SAEs), for predicting short-term passenger flows of each station in a subway network simultaneously. SAEs are employed to extract network passenger flow data features, which involves mapping high-dimensionality data to low-dimensionality data at the first stage. Then, LSTM NN is trained using low-dimensionality data. Finally, SAEs restore the predicted data output by LSTM NN to predict the network passenger flow data. By employing automatic fare collection data of the Guangzhou subway, the proposed hybrid model was evaluated. The experimental results show that the average mean relative error of the proposed hybrid model is 4.6%, which is much better than other current prediction models.
Deep learning-based hybrid model for short-term subway passenger flow prediction using automatic fare collection data
IET Intelligent Transport Systems ; 13 , 11 ; 1708-1716
2019-08-05
9 pages
Article (Journal)
Electronic Resource
English
backpropagation , prediction results , current prediction models , learning (artificial intelligence) , stacked auto-encoders , Guangzhou subway , predicted data output , subway network , LSTM NN , neural nets , short-term subway passenger flow prediction , subway operators , short-term passenger flow prediction , daily operations , traffic engineering computing , automatic fare collection data , mapping high-dimensionality data , short-term passenger flows , prediction model , SAEs , deep learning-based hybrid model , network passenger flow data features , low-dimensionality data
Metadata by IET is licensed under CC BY 3.0
Short-term Passenger Flow Prediction of Subway Station Based on PSO_LSTM
British Library Conference Proceedings | 2022
|Short-term Passenger Flow Prediction of Subway Station Based on PSO_LSTM
Springer Verlag | 2022
|