• Chinese Journal of Ship Research
  • Vol. 19, Issue 6, 303 (2024)
Jinyuan LI1, Faxin ZHU1, Xianbin TENG2, and Qilin BI2
Author Affiliations
  • 1School of Ship and Marine, Zhejiang Ocean University, Zhoushan 316022, China
  • 2College of Marine Engineering, Guangzhou Maritime College, Guangzhou 510725, China
  • show less
    DOI: 10.19693/j.issn.1673-3185.03755 Cite this Article
    Jinyuan LI, Faxin ZHU, Xianbin TENG, Qilin BI. Ship track prediction based on Bayesian optimization in temporal convolutional networks[J]. Chinese Journal of Ship Research, 2024, 19(6): 303 Copy Citation Text show less
    [in Chinese]
    Fig. 1. [in Chinese]
    [in Chinese]
    Fig. 2. [in Chinese]
    [in Chinese]
    Fig. 3. [in Chinese]
    [in Chinese]
    Fig. 4. [in Chinese]
    [in Chinese]
    Fig. 5. [in Chinese]
    [in Chinese]
    Fig. 6. [in Chinese]
    [in Chinese]
    Fig. 7. [in Chinese]
    [in Chinese]
    Fig. 8. [in Chinese]
    [in Chinese]
    Fig. 9. [in Chinese]
    [in Chinese]
    Fig. 10. [in Chinese]
    [in Chinese]
    Fig. 11. [in Chinese]
    [in Chinese]
    Fig. 12. [in Chinese]
    [in Chinese]
    Fig. 13. [in Chinese]
    航迹类型预处理前预处理后
    经度/(°)纬度/(°)经度/(°)纬度/(°)
    直线型航迹0.00120.00110.00080.0007
    S型航迹0.00580.00630.00510.0056
    M型航迹0.00660.00690.00570.0062
    Table 1. MAE evaluation indicators for pre-processed data
    算法参数TCNLSTM
    卷积核大小5
    卷积核数量64
    扩张因子8
    优化器AdamAdam
    隐藏层864
    学习率0.0010.001
    迭代次数1 0001 000
    批次大小6464
    Table 2. Parameters for experimental model
    算法模型${e_{\rm{RMSE}}}$${e_{\rm{MAE}}}$
    经度/(°)纬度/(°)经度/(°)纬度/(°)
    直线型航迹0.00080.00030.00020.0006
    S型航迹0.00240.00210.00230.0025
    M型航迹0.00240.00350.00180.0033
    Table 3. Results comparison of crossover experiments
    Jinyuan LI, Faxin ZHU, Xianbin TENG, Qilin BI. Ship track prediction based on Bayesian optimization in temporal convolutional networks[J]. Chinese Journal of Ship Research, 2024, 19(6): 303
    Download Citation