Accurate prediction of bus arrival time is crucial for constructing smart cities and intelligent transportation systems. Objectivity and clarity must be maintained throughout to ensure efficient operation. Therefore, it is essential to achieve precise bus arrival time prediction. A recurrent neural network prediction model employing a dual-stage attention mechanism is proposed. The model was constructed based on bidirectional long and short-term memory networks, and arrival time predictions incorporate both dynamic and static factors of bus travel. The model utilized an advanced seagull optimization algorithm to optimize the model parameters, enhanced model iteration and population richness by incorporating the sine-cosine operator and adaptive parameters, and ultimately validated model performance through simulation experiments. The experimental results showed that the prediction error of the benchmark model is 324s and that of the normal peak is 87s. Considering the dynamic and static factors, the prediction error of the model was 6s ~ 8s. The minimum values of mean absolute percentage error, root mean square error and mean absolute error of the model were 0.07, 11.28 and 9.22, respectively. The experimental results demonstrated that the minimum error of the model exhibits the highest prediction accuracy, substantiating the model’s potential for accurate prediction. Furthermore, the model’s performance is effectively safeguarded from the impact of peak time. In addition, the model is feasible in practical application.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    DA-RNN-Based Bus Arrival Time Prediction Model


    Additional title:

    Int. J. ITS Res.


    Contributors:
    Li, Zhixiao (author)


    Publication date :

    2024-12-01


    Size :

    15 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English





    ARRIVAL TIME PREDICTION DEVICE, ARRIVAL TIME PREDICTION SYSTEM, AND PROGRAM

    OKUDE MARIKO / NAGAI TOORU | European Patent Office | 2016

    Free access

    ARRIVAL TIME PREDICTION DEVICE AND ARRIVAL TIME PREDICTION DEVICE SYSTEM

    ARAKI KATSUNORI | European Patent Office | 2017

    Free access

    Historical Travel Time Based Bus-Arrival-Time Prediction Model

    Chen, Guojun / Yang, Xiaoguang / Zhang, Dong et al. | ASCE | 2011


    DA-RNN-Based Bus Arrival Time Prediction Model

    Li, Zhixiao | Springer Verlag | 2024