The invention discloses an RF (Radio Frequency) and LSTM (Long Short Term Memory) combined ship trajectory prediction model, which comprises the following steps of: firstly, selecting and processing historical AIS (Automatic Identification System) data, removing speed abnormal points and trajectory abnormal points, and filling missing values in a speed decomposition and linear interpolation mode to obtain a relatively complete trajectory; clustering analysis is carried out on multiple sections of tracks of each ship to obtain common track sections of each ship, and abnormal track sections are deleted as analysis of ship behaviors. On the basis, an RF and LSTM combined trajectory prediction model is constructed by the common trajectory segments of the ship, and the model can realize medium and long term ship trajectory prediction, provide technical support for marine law enforcement and traffic safety, and provide reference for ship trajectory prediction.

    本发明公开了一种RF和LSTM组合的船舶轨迹预测模型,首先通过选择并处理历史AIS数据,去除速度异常点、轨迹异常点,并通过速度分解和线性插值的方式填补缺失值,得到比较完整的轨迹。通过对每一条船舶的多段轨迹进行聚类分析,得到每条船舶常用的轨迹段,删除异常的轨迹段,作为对船舶行为的解析。在此基础上,以船舶的常用轨迹段构建了RF和LSTM相结合的轨迹预测模型,该模型能够实现中长期的船舶轨迹预测,为海上执法和交通安全提供技术支撑,为船舶轨迹预测提供参考。


    Access

    Download


    Export, share and cite



    Title :

    RF and LSTM combined ship trajectory prediction model


    Additional title:

    一种RF和LSTM组合的船舶轨迹预测模型


    Contributors:
    ZHANG CONG (author) / ZHU JISHUAI (author) / DENG MEIHUAN (author) / CHEN MUSEN (author) / WANG YINGBO (author) / WU ZUYONG (author)

    Publication date :

    2024-03-22


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Ship Trajectory Prediction with Social History LSTM

    Zhao, Wenfeng / Zhang, Xudong | IEEE | 2023


    A Bi-directional LSTM Ship Trajectory Prediction Method based on Attention Mechanism

    Zhang, Sheng / Wang, Long / Zhu, Mingdong et al. | IEEE | 2021


    CNN, improved LSTM and attention mechanism-based ship trajectory prediction method and system

    LI XIULAI / LIU BOYI / CHEN MINGRUI et al. | European Patent Office | 2024

    Free access

    UB-LSTM: A Trajectory Prediction Method Combined with Vehicle Behavior Recognition

    Haipeng Xiao / Chaoqun Wang / Zhixiong Li et al. | DOAJ | 2020

    Free access

    Multidimensional Non-linear Ship Trajectory Prediction Based on LSTM Network Corrected by GA-BP

    Wang, Xinyu / Zhao, Wenyu / Wang, Shuangxin et al. | Springer Verlag | 2023