Nowadays, the phenomenon of congestion in rail transit is becoming more and more severe which need effective passenger inducement measures to alleviate this phenomenon. For solving the problem of precise estimation of passengers in crowded conditions, this article studies from the basis of theories and focuses on interval full load rate. First, a model was designed according to the interval full load rate and the number of passenger-controlled stations to calculate the rail traffic congestion degree. For getting the most accurate prediction results of the congestion degree, Autoregressive Integrated Moving Average model (ARIMA) and Prophet are compared to predict the interval full load rate. Then a simple model was designed to identify the Space-time range of congestion based on full load rate.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Passenger Flow State Prediction Based on Full Load Rate under Congestion


    Contributors:
    Zhao, Zeyu (author) / Liu, Jun (author) / Xu, Xinyue (author) / Yang, Zhiqiang (author)

    Conference:

    21st COTA International Conference of Transportation Professionals ; 2021 ; Xi’an, China


    Published in:

    CICTP 2021 ; 316-327


    Publication date :

    2021-12-14




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Passenger Flow State Prediction Based on Full Load Rate under Congestion

    Zhao, Zeyu / Liu, Jun / Xu, Xinyue et al. | TIBKAT | 2021



    PASSENGER FLOW PREDICTOR, PASSENGER FLOW PREDICTION METHOD, AND PASSENGER FLOW PREDICTION PROGRAM

    HIROTA ATSUSHI / HATAYAMA GORO / SAKURAGI SHINYA | European Patent Office | 2024

    Free access

    Passenger Congestion Mechanism Analysis in Comprehensive Passenger Transportation Terminal

    Wang, Hui Hui ;Ji, Chang Xu ;Shan, Dong Zhi | Trans Tech Publications | 2011


    Method for identifying scenic spot passenger flow congestion based on big data

    JI ZHENGXU / XIE CHUANJIA | European Patent Office | 2022

    Free access