Deep learning‐based hybrid model for short‐term subway passenger flow prediction using automatic fare collection data. Issue 11 (5th August 2019)

• Record Type: Journal Article
• Authors: Jia, Feifan; Li, Haiying; Jiang, Xi; Xu, Xinyue
• Is Part Of: IET intelligent transport systems. Volume 13:Issue 11(2019)
• Page Start: 1708
• Page End: 1716
• Publication Date: 2019-08-05
• Subjects: backpropagation -- learning (artificial intelligence) -- traffic engineering computing -- neural nets; deep learning‐based hybrid model -- LSTM NN -- stacked auto‐encoders -- SAEs -- short‐term passenger flows -- subway network -- network passenger flow data features -- mapping high‐dimensionality data -- low‐dimensionality data -- predicted data output -- automatic fare collection data -- Guangzhou subway -- current prediction models -- short‐term subway passenger flow prediction -- short‐term passenger flow prediction -- daily operations -- subway operators -- prediction model -- prediction results; Intelligent transportation systems -- Periodicals; Electronics in transportation -- Periodicals; 388.31205
• DOI: 10.1049/iet-its.2019.0112
• Languages: English
• ISSNs: 1751-956X

Abstract

Abstract : 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.