A Novel Classification Scheme of Moving Targets at Sea Based on Ward's and K-means Clustering
A Novel Classification Scheme of Moving Targets at Sea Based on Ward's and K-means Clustering
复制标题
基于Ward和K-means聚类的海上运动目标分类新方案
DOI：
10.1145/3207677.3278058
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Pengcheng Zhou
中科院分区：
文献类型：
--
作者：
Yan Jiang;Bo Li;Hao Zhang;Q. Luo;Pengcheng Zhou
基于结构数据库技术、Ward’s聚类和K-means聚类，提出了一种针对海上运动目标监测数据的分类识别方案。首先，构建结构化数据库来存储监测数据。其次，通过分析船舶自动识别系统（AIS）导出的船舶运动规律，得到海上运动目标的识别特征，并从监测数据中提取其识别特征；然后，使用Ward聚类对特征数据进行分类。最后，利用k均值聚类方法对现有编队舰艇进行识别。仿真结果表明，该方法适用于海上运动目标的分类和识别。
Based1 on the structure database technology, Ward's and K-means clustering, a classification and identification scheme is proposed for the monitoring data of the moving targets at sea. First, a structural database is built to store the monitored data. Secondly, by analyzing the movement rules of ships which derived from the automatic identification system(AIS), the identification features of the moving targets at sea are obtained and extracted them from the monitored data. And then, the Ward's clustering is used to classify the feature data. Finally, the K-means clustering is used to identify the existing formation ships. The simulation results show that the proposed scheme is applicable to classify and identify the moving targets at sea.