应用聚类分析方法串并案件的距离计算问题研究  

Distance Computing by Cluster Analysis for Joint Investigation

作　　者：唐宇 TANG Yu(Hongyuan County Public Security Bureau,Hongyuan 624400,Sichuan,China)

机构地区：[1]红原县公安局,四川红原624400

出　　处：《刑事技术》2018年第2期123-129,共7页Forensic Science and Technology

摘　　要：聚类分析方法应用到串并案件中,采用何种距离计算形式是需要解决的基本问题。通过理论分析选择Jaccard系数和余弦相似度两种距离计算形式,使用参考模型与聚类结果比较的性能度量方法,对两种距离计算形式进行对比研究,发现基于该两种距离计算形式的聚类结果与参考模型一致,得出应用聚类分析方法串并案件可以使用Jaccard系数和余弦相似度两种距离计算形式的结论。Distance computing is a basic problem when cluster analysis has been applied into joint investigation.Usually,Jaccard coefficient and cosine similarity are the two ways for distance computing.In this paper,the reference model was compared with the result of cluster analysis based on the handling of Jaccard coefficient and/or cosine similarity,showing that the result of cluster analysis is the same as that of reference model.Therefore,both Jaccard coefficient and cosine similarity can be used into cluster analysis for joint investigation.

关 键 词：串并案 聚类分析 距离计算 Jaccard系数 余弦相似度 

分 类 号：DF793.5[政治法律—诉讼法学]