The security of water and martime transportation gained widespread attention in the background of continuous global economic growth. Vessel’s trajectory prediction enhances the security by exploiting Automatic Identification Systems (AIS) dataset which records the dynamic and static information of vessels. This paper introduced and compared three algorithms of trajectory prediction: extended Kalman filter (EKF), Least Squares support vector regression (LS-SVR) and improved LSSVR predictor. Firstly, we pre-processed the raw AIS dataset and then conducted the experiments to compared the algorithms mentioned. Finally, the cumulative distribution function of prediction root mean square error (RMSE) and their running time are showed. The results shows the EKF predictor has the best performance in accuracy and running time.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on Ship Trajectory Prediction Using Extended Kalman Filter and Least-Squares Support Vector Regression Based on AIS Data


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Zhang, Zhenyuan (editor) / Luo, Xinpeng (author) / Wang, Jie (author) / Li, Jiamin (author) / Lu, Hua (author) / Lai, Qiuyu (author) / Zhu, Xiangyu (author)

    Conference:

    International Conference on Intelligent Transportation Engineering ; 2021 ; Beijing, China October 29, 2021 - October 31, 2021



    Publication date :

    2022-06-01


    Size :

    9 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English