基于AIS数据的敏感水域船舶异常行为检测

Abnormal Behavior Detection of Ships in Sensitive Water Area Based on AIS Data

为了检测敏感水域中船舶的异常行为,提出了基于船舶自动识别系统(AIS)数据的敏感水域船舶异常行为检测框架。首先,选定3个敏感水域,将进出次数、停留时间和速度比值3个指标作为异常因子并建立检测框架;然后,采用专家调查法构造判断矩阵,进而确定异常因子权重;接着,基于AIS数据确定异常因子值及其评分,综合异常因子权重并利用层次加权计算得到船舶异常得分;最后,利用南海、东京湾和琉球3个敏感水域近2年的AIS数据进行了试验分析。试验结果表明,该框架可有效检测出敏感水域中行为异常的船舶,具有可行性。

In order to detect the abnormal behavior of ships in sensitive water area,an abnormal behavior detection framework of ships in sensitive water area based on automatic identification system(AIS)data is proposed.Firstly,three sensitive water areas are selected,three indexes of entry and exit times,residence time and velocity ratio are used as abnormal factors,and the detection framework is established.Secondly,the expert investigation method is used to construct the judgment matrix,and then the weights of abnormal factors are determined.Then,the abnormal factor values and scores are determined based on AIS data,and the abnormal factor weights are synthesized and the ship abnormal scores are obtained through hierarchical weighting calculation.Finally,the AIS data from three sensitive water areas of the South China Sea,Tokyo Bay and Ryukyu in the past two years are used for experimental analysis.The experimental results show that the framework can effectively detect ships with abnormal behavior in sensitive water area,and it is feasible.