首页 | 本学科首页   官方微博 | 高级检索  
     

FSP:一种基于图论的频繁结构模式挖掘算法
引用本文:沙金,纪宁,陈立松. FSP:一种基于图论的频繁结构模式挖掘算法[J]. 微电子学与计算机, 2007, 24(2): 93-95,98
作者姓名:沙金  纪宁  陈立松
作者单位:1. 石家庄铁道学院,计算机系,河北,石家庄,050043
2. 华北电力大学,电气工程学院,河北,保定,071003
摘    要:研究在图集中挖掘频繁结构模式的方法,并提出了一种发现频繁结构的新算法FSP(Frequent Structure Pattem Mining),通过在图中建立了一种新的字典顺序,并把每个图映射成唯一的最小DFS编码作为图的规范形式,从而把图转换成一个序列。基于这种字典顺序,FSP算法不需要生成候选,采用深度优先搜索策略挖掘频繁连通子图。试验结果显示,FSP算法在性能上优于以前的算法。

关 键 词:数据挖掘  频繁结构模式  DFS编码  深度优先搜索
文章编号:1000-7180(2007)02-0093-03
修稿时间:2005-12-26

FSP: A Graph-based Frequent Structure Pattern Mining Algorithm
SHA Jin,JI Ning,CHEN Li-song. FSP: A Graph-based Frequent Structure Pattern Mining Algorithm[J]. Microelectronics & Computer, 2007, 24(2): 93-95,98
Authors:SHA Jin  JI Ning  CHEN Li-song
Affiliation:1 .Department of Computer Science and Technology, Shijiazhuang Railway Institute, Shijiazhuang 050043, China;2 .College of Electrical Engineering, North China Electric Power University, Baoding 071003, China
Abstract:Investigate new approaches for frequent graph-based pattern mining in graph datasets and propose a novel algorithm called FSP(frequent structure pattern mining).FSP builds a new lexicographic order among graphs,and maps each graph to a unique minimum DFS code as its canonical label.Based on this lexicographic order.FSP adopts the depth-first search strategy to mine frequent connected subgraphs efficiently,without candidate generation.Our performance study shows that FSP substantially outperforms previous algorithms.
Keywords:Data mining   Frequent structure pattern   DFS code   Depth-first search
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号