基于灰色方法与结构距离的飓风轨迹聚类算法  

The clustering algorithm of cyclone track based on grey theory and structure distance

作　　者：江艺羡 张岐山[1] JIANG Yixian ZHANG Qishan(School of Economics and Management, Puzhou University, Fuzhou 350108, China Public Health School, Fujian Medical University, Fuzhou 350108, China)

机构地区：[1]福州大学经济与管理学院,福州350108 [2]福建医科大学公共卫生学院,福州350108

出　　处：《系统工程理论与实践》2017年第4期1046-1055,共10页Systems Engineering-Theory & Practice

基　　金：国家自然科学基金青年项目(61300104);福建省自然科学基金(2013J01230)~~

摘　　要：飓风轨迹的聚类分析以轨迹间的相似性为基础.但是目前轨迹相似距离研究主要仅针对一个或两个轨迹属性,使得得到的聚类结果无法充分体现轨迹的运动特征.为充分利用轨迹的属性特征,结合灰色相关理论,提出将位置、方向、速度三个属性融合为结构相似距离,并以此作为轨迹间相似距离度量函数进行聚类分析,以达到更全面了解轨迹运动特点的目的.实例分析表明该算法能充分体现轨迹运动特征,聚类结果更具有实际意义.The clustering analysis of cyclone track is built on the similarity between them. Current studies on trajectory similarity distance were for one or two attributes only. So in the case, the results were unable to fully reflect the motion characteristics of trajectory. In order to make full use of the trajectory attributes, based on the grey theory, this paper proposed that the three attributes （position, direction and velocity） should be fused as structure distance for clustering analysis, helping to achieve a more comprehensive understanding of the purpose of trajectory motion. Example analysis shows that the algorithm can fully reflect the trajectory characteristics, and the results have more practical significance.

关 键 词：聚类 轨迹 灰色GM(1 1)模型 结构距离 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]