Despite the development of rail transit, urban transport capacity has increased substantially. It still faces severe jams during peaking operation periods. In this paper, inspired by artificial intelligence methods, we proposed a new data-driven method for the dynamic trajectory prediction of the train in front based on the long short-term memory(LSTM) network. we extracted train operation data from the ATO equipment of Chengdu Metro Line 8 and used three evaluation indicators for predicting the loss of the trajectory and the accuracy analysis. The experiments indicate that compared with the Kalman filter model, our method shows more robust stability and higher accuracy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Trajectory Prediction of Urban Rail Transit Based on Long Short-Term Memory Network


    Contributors:
    He, Yijuan (author) / Lv, Jidong (author) / Zhang, Daqian (author) / Chai, Ming (author) / Liu, Hongjie (author) / Dong, Haixia (author) / Tang, Tao (author)


    Publication date :

    2021-09-19


    Size :

    605704 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English