一种基于CLIQUE聚类的全球地震目录分析方法  

Research on Global Earthquake Catalogue Based on CLIQUE Algorithm

作　　者：杨振凯 江南[1] 杨飞[1] YANG Zhenkai;JIANG Nan;YANG Fei(Information Engineering University, Zhengzhou 450001, Chin)

机构地区：[1]信息工程大学,河南郑州450001

出　　处：《测绘科学技术学报》2018年第1期105-110,共6页Journal of Geomatics Science and Technology

基　　金：国家重点研发计划项目(2016YFB0502300)

摘　　要：CLIQUE是一种重要的数据挖掘算法,广泛应用于大型数据库中的高维数据聚类。分析了CLIQUE算法的主要思想以及聚类算法在地震目录分析中的研究现状,提出了利用CLIQUE算法对全球地震目录进行聚类处理的流程。根据时空数据的多维特征,首先划分子空间计算密集单元,再将其连接聚簇并投影至各个维度进行可视分析。以近40 a(1977-2016年)的全球地震目录为数据源进行CLIQUE聚类实验,结果表明CLIQUE能有效发现地震现象在不同维度下呈现的聚集模式,且相对于其他聚类算法具有较高的效率。本文方法具有一定的可靠性与实用性,能够为地震事件的评估和防范提供决策依据。CLIQUE is an important clustering method in data mining,and it is widely used in high-dimensional data clustering of the large database.In this paper,main idea of CLIQUE algorithm and current research of clustering application in earthquake catalogue were analyzed.A processing method of global earthquake catalogue with CLIQUE algorithm was put forward.Based on the multi-dimensional aspects of spatio-temporal data,the subspace was divided to compute dense units.Then the clusters formed by dense units were presented in lower dimensions for visualization and analysis.The experiment was conducted on the global earthquake catalogue for 40 years from1977 to 2016.Result indicates that CLIQUE can discover apparent aggregation patterns of earthquake in different dimensions and it is more efficient in contrast to other clustering methods.The clustering method proposed in this paper has the advantage of high reliability and availability,and it can also provide a basis for decision-making for the evaluation and precaution of seismic events.

关 键 词：CLIQUE算法 地震目录 时空数据 聚类 密集单元 

分 类 号：P208[天文地球—地图制图学与地理信息工程]