Bidirectional Long Short-Term Memory Model for Metro Passenger flow Prediction

Authors

  • Gu Huang
  • Guitang Mai
  • Tianxi Xiao

DOI:

https://doi.org/10.54097/d7qdc362

Keywords:

Metro; LSTM; BiLSTM; passenger flow prediction.

Abstract

To maximize metro operations, accurate short-term passenger flow projections are essential. The paper utilizes Bidirectional Long Short-Term Memory (BiLSTM) to forecast passenger flow based on data from January 16 to January 25, 2019. By contrasting BiLSTM with conventional models of Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN), the research highlights BiLSTM’s superior ability to capture temporal dependencies from both past and future data. The analysis reveals distinct patterns for weekdays and weekends, with double peaks during commute hours on weekdays and a continuous peak in the afternoon on weekends. The results indicate that BiLSTM outstandingly enhances the prediction's accuracy, with less Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) in contrast to RNN and LSTM. This enhanced predictive capability supports more effective scheduling and flow management in metro systems, ensuring better service and operational efficiency. The study underscores the practical benefits of BiLSTM in handling complex, dynamic passenger flow data.

Downloads

Download data is not yet available.

References

[1] Fang H, et al. Metro Station functional clustering and dual-view recurrent graph convolutional network for metro passenger flow prediction. Expert Systems with Applications, 2024, 247: 122550. DOI: https://doi.org/10.1016/j.eswa.2023.122550

[2] Liu et al. Research on forecast of rail traffic flow based on ARIMA model. Journal of Physics: Conference Series, 2021, 1792(1): 12065. DOI: https://doi.org/10.1088/1742-6596/1792/1/012065

[3] Wu P, et al. A Time Series Decomposition and Reinforcement Learning Ensemble Method for Short-Term Passenger Flow Prediction in Urban Rail Transit. Urban Rail Transit, 2023, 9(4): 323-351. DOI: https://doi.org/10.1007/s40864-023-00205-1

[4] Li P, Wu W, Pei X. A separate modelling approach for short-term bus passenger flow prediction based on behavioural patterns: A hybrid decision tree method. Physica A: Statistical Mechanics and its Applications, 2023, 616: 128567. DOI: https://doi.org/10.1016/j.physa.2023.128567

[5] Che S, Chen Y. Rail transit passenger volume forecasting method based on support vector machine. Third International Conference on Green Communication, Network, and Internet of Things (CNIoT 2023). SPIE, 2023, 12814: 500-505. DOI: https://doi.org/10.1117/12.3010336

[6] Vinayakumar R, Soman K P, Poornachandran P. Applying deep learning approaches for network traffic prediction. 2017 International Conference on Advances in Computing, Communications, and Informatics (ICACCI). IEEE, 2017: 2353-2358. DOI: https://doi.org/10.1109/ICACCI.2017.8126198

[7] Yang Y, et al. Short-term passenger flow prediction for multi-traffic modes: A Transformer and residual network based multi-task learning method. Information Sciences, 2023, 642: 119144. DOI: https://doi.org/10.1016/j.ins.2023.119144

[8] Yong Liu. Short-Term Traffic Flow Prediction with Structure-Optimized Deep Belief Network. Sustainability in Environment, 2022. DOI: https://doi.org/10.22158/se.v7n2p16

[9] Qi Q, Cheng R, Ge H. Short-term inbound rail transit passenger flow prediction based on BILSTM model and influence factor analysis. Digital Transportation and Safety, 2023, 2(1): 12-22. DOI: https://doi.org/10.48130/DTS-2023-0002

[10] Zhu H, Yang X, Wang Y. Prediction of daily entrance and exit passenger flow of rail transit stations by deep learning method. Journal of Advanced Transportation, 2018, 1: 6142724. DOI: https://doi.org/10.1155/2018/6142724

Downloads

Published

23-11-2024

How to Cite

Huang, G., Mai, G., & Xiao, T. (2024). Bidirectional Long Short-Term Memory Model for Metro Passenger flow Prediction. Highlights in Science, Engineering and Technology, 118, 57-64. https://doi.org/10.54097/d7qdc362