基于时空密度的船载AIS数据聚类分析方法研究

Clustering Analysis Method of Shipborne AIS Data Based on Spatio-Temporal Density

船载AIS数据包含位置、时间和其他属性,属于典型的时空数据,对其开展时空聚类分析有助于挖掘海上交通特征。结合AIS数据的具体特征,提出时间切片化方法,有效约简AIS数据并处理报告间隔不等的问题。在DBSCAN算法基础上综合考虑时间和空间要素,提出船载AIS数据时空聚类算法,并对实际数据开展分析。该方法能更好顾及船舶交通流的时空耦合特征,识别隐含的时空模式,为主管机关开展船舶交通管理、优化通航秩序、保障航行安全等提供一种新途径。

Shipborne AIS data contains location,time and other attributes,which belongs to typical spatio-temporal data.And the spatio-temporal clustering analysis on shipborne AIS data contributes to the data mining of maritime traffic characteristics.Considering the specific characteristics of AIS data,a time slicing method was proposed to effectively simplify the AIS data and deal with the problem of different report intervals.Based on DBSCAN algorithm,combining time and space attributes,a spatio-temporal clustering algorithm of shipborne AIS data was put forward,and the actual AIS data was taken for a case study.The proposed method can better take account of the spatial-temporal coupling characteristics of ship traffic flow and identify the hidden spatio-temporal pattern,which provides a new way for the competent authorities to carry out ship traffic management,optimize navigation order and ensure navigation safety.