为提升船舶海上航行安全性，设计基于数据挖掘的船舶海上航行轨迹高精度跟踪方法。该方法利用数据处理模块对获取的船舶时空数据进行处理后，通过轨迹热点区域提取模块的改进密度峰值聚类算法，提取船舶航行轨迹热点区域；频繁轨迹挖掘模块在该区域内利用改进的序列模式挖掘算法，挖掘出具有时空属性的频繁航行轨迹，实现舰船海上航行轨迹跟踪。测试结果显示：该方法具有良好的聚类效果，能够可靠完成轨迹热点区域的聚类，DB指标的结果均在1.5以内；能够获取轨迹的热点区域，实现指定航线轨迹的高精度跟踪，在跟踪过程中没有发生明显的轨迹偏差情况。
In order to improve the safety of ship navigation at sea, a high-precision tracking method of ship navigation trajectory based on data mining is studied. This method uses the data processing module to process the acquired ship's spatio-temporal data, and then extracts the ship's navigation track hot spots through the improved density peak clustering algorithm of the track hot spots extraction module. The frequent trajectory mining module uses an improved sequential pattern mining algorithm to mine frequent navigation trajectories with spatio-temporal attributes in this region, so as to realize the tracking of ships' maritime navigation trajectories. The test results show that the method has a good clustering effect, and can reliably complete the clustering of track hot spots, and the results of DB indicators are within 1.5. The hot spot area of the track can be obtained to achieve high-precision tracking of the designated route track, and there is no obvious track deviation during the tracking process.
2023,45(1): 186-189 收稿日期：2022-08-14
DOI：10.3404/j.issn.1672-7649.2023.01.034
分类号：TP301
基金项目：江西省教育厅科学技术研究重点项目 (GJJ218702)
作者简介：夏容(1982-),女,硕士,副教授,研究方向为软件设计及数据库技术
