At present, the main problem of urban rail transit is the long-term smooth traffic forecast based on the operation process. Because there is no reasonable distinction and prediction of congestion, it is easy to form a surge of passenger flow in some periods, resulting in congestion. Through the scientific management of commuting time, platform facilities, and entrance and exit allocation, rail transit can be better planned and operating costs can be reduced. In view of the difficulty of urban rail transit prediction due to a large amount of real-time data and frequent emergencies, this paper applies the matrix of vector data structure to improve the accuracy of the shallow prediction model, and extracts the feature expression of kernel density function from the database to realize the accurate analysis of the urban rail transit. Based on the data of part of the passenger flow of Guangzhou Metro, a simulation experimental platform is built to verify the prediction of the regional rail transit passenger flow. The test results present that the accuracy of the algorithm in this paper is 99.6%, which is better than the traditional prediction method. It can analyze and predict the commuting situation of different rail transit modes, realize intelligent guidance management, and has guiding significance for urban rail intelligent traffic management.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Rail transit passenger volume forecasting method based on support vector machine


    Contributors:
    Wang, Hongzhi (editor) / Zhang, Shiling (editor) / Che, Shuang (author) / Chen, Yan (author)

    Conference:

    Third International Conference on Green Communication, Network, and Internet of Things (CNIoT 2023) ; 2023 ; Chongqing, China


    Published in:

    Proc. SPIE ; 12814


    Publication date :

    2023-10-20





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Urban Rail Transit Passenger Flow Forecasting—XGBoost

    Sun, Xiaoli / Zhu, Caihua / Ma, Chaoqun | ASCE | 2022


    Urban Rail Transit Passenger Flow Forecasting - XGBoost

    Sun, Xiaoli / Zhu, Caihua / Ma, Chaoqun | TIBKAT | 2022



    Urban rail transit passenger flow forecasting based on prophet-GRU combined model

    Lu, Yongjiu / Ye, Mao / Zhang, Renjie et al. | SPIE | 2023