Support vector machine (SVM) models have good performance in predicting daily traffic volume at toll stations, however, they cannot accurately predict holiday traffic volume. Therefore, an improved SVM model is proposed in this paper. The paper takes a toll station in Heilongjiang, China as an example, and uses the daily traffic volume as the learning set. The current day traffic volume is used as the dependent variable and the previous 7-day traffic volume is used as the independent variable for model learning. This paper found that the basic SVM model is not accurate enough to forecast the traffic volume during holidays. To improve the model accuracy, this paper first used the SVM model to forecast non-holiday traffic volumes, and proposed a prediction method using quarterly conversion coefficients combined with the SVM model to construct an improved SVM model. The result of the prediction showed that the improved SVM model in this paper was able to effectively improve accuracy, making it better than in the basic SVM and GBDT model, thus proving the feasibility of the improved SVM model.


    Access

    Download


    Export, share and cite



    Title :

    Traffic Volume Forecasting Model of Freeway Toll Stations During Holidays – An SVM Model


    Contributors:
    Xiaowei HU (author) / Yongzhi XIAO (author) / Tianlin WANG (author) / Lu YANG (author) / Pengcheng TANG (author)


    Publication date :

    2022




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown






    Understanding Intercity Freeway Traffic Variability at Holidays Using Anonymous Cell Phone Data

    Liu, Gang / Wang, Chenhao / Qiu, Tony Z. | Springer Verlag | 2016


    Developing Microscopic Integrated Freeway-Toll Plaza Model

    Al-Deek, Haitham M. / Nezamuddin | ASCE | 2006


    Developing Microscopic Integrated Freeway-Toll Plaza Model

    Al-Deek, H. M. / Nezamuddin / American Society of Civil Engineers | British Library Conference Proceedings | 2005