以图频繁集为基础的核心节点发现  

Core Nodes Detection Based on Frequent Itemsets of Graph

作　　者：宋文军[1,2] 刘红星[1,2] 王崇骏[1,2] 谢俊元[1,2] 

机构地区：[1]南京大学计算机软件新技术国家重点实验室,南京210093 [2]南京大学计算机科学与技术系,南京210093

出　　处：《计算机科学与探索》2010年第1期82-88,共7页Journal of Frontiers of Computer Science and Technology

基　　金：国家自然科学基金No.60721002;60875038;60503021;国家教育部重点项目No.108151;江苏省高新技术计划No.BG2007038~~

摘　　要：结合基于图的关联规则挖掘和双向搜索的策略,产生最大频繁项集,从而提出基于图的最大频繁项集(graph based maximum frequen tset,GBMFS)生成算法。运用此算法,结合社会网络的动态特征,发现社会网络中所存在的团伙的核心成员。最后,在实际系统中对相关的算法进行了验证。This paper concentrates on the detection of core nodes in the crime network,but as a basis,it models the network as a graph and presents the algorithm of GBMFS（graph based maximum frequent set）,which combines the mining of association rules with bidirectional search strategy and can be used to discover the most frequent itemsets in a graph.After getting several snaps of social network in different time and integrating the discovery of quasi-clique with GBMFS,the algorithm of discovering core nodes in these snaps is achieved.At last the algorithm is applied in a real system.

关 键 词：最大频繁项集 图 核心节点 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]