基于朴素贝叶斯算法的船舶异常行为监测

随着海事事故与海上违法行为的不断增多,智能的监控方法成为降低海事事故,打击海上违法行为的有效手段.同时,船舶自动识别系统(Automatic Identification System,AIS)的普及及船舶交通管理系统(Vessel Traffic Service,VTS)的扩建,又为智能监控提供了数据支持.鉴于此,利用船舶自动识别系统提供的数据,分析通航水域船舶信息的分布情况,根据其概率分布采用朴素贝叶斯算法,从船舶航速、航向及距航道边界距离3个方面,构建船舶异常行为检测模型.最后,以成山角通航水域为例,检验模型的有效性.实验结果表明,构建的模型能够有效地完成异常行为监测,减少海事监管人员的工作强度,同时根据实验结果分析了成山角水域船舶航行的特点,并对成山角定线制提出合理化建议.

Ship Abnormal Behavior Detection Based on Naive Bayes

With maritime accidents and violating law increasing, intelligent surveillance as a kind of significant measure can be applied to decrease or avoid maritime accidents and violations. Meanwhile, Automatic Identification System (AIS) is widely used and Vessel Traffic Service (VTS) is being improved, which is beneficial to supply effective data for intelligent surveillance. On the bases of that, AIS data is used to analyze ship information on the sea area. According to probability distribution of ship information, Naive Bayes (NB) algorithm is applied to build abnormal detection model to monitor dynamic information such as speed, course and the distance between vessel position and limit of fairway. At last, data from Chengshan Jiao sea area is used to validate the validity of the algorithm. It is indicated from experimental results that the proposed method can effectively recognize ship abnormal behavior, which is conductive to decreasing workload. Moreover, the traffic characteristics in Chenshan Jiao sea area are analyzed and reasonable suggestions are proposed.