计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (31): 148-151.DOI: 10.3778/j.issn.1002-8331.2010.31.041

• 数据库、信号与信息处理 • 上一篇    下一篇

面向用户的空间拓扑关联规则挖掘

方 刚,熊 江,应 宏,涂承胜   

  1. 重庆三峡学院 数学与计算机科学学院,重庆 万州 404000
  • 收稿日期:2010-07-15 修回日期:2010-09-06 出版日期:2010-11-01 发布日期:2010-11-01
  • 通讯作者: 方 刚

User oriented spatial topology association rules mining

FANG Gang,XIONG Jiang,YING Hong,TU Cheng-sheng   

  1. College of Mathematics and Computer Science,Chongqing Three Gorges University,Wanzhou,Chongqing 404000,China
  • Received:2010-07-15 Revised:2010-09-06 Online:2010-11-01 Published:2010-11-01
  • Contact: FANG Gang

摘要: 在挖掘空间拓扑关联规则时,由于现有挖掘算法不能够提取满足用户特定需求的空间拓扑关联规则,若使用传统约束性关联规则挖掘算法,则存在大量的重复计算和冗余候选项;提出一种面向用户的空间拓扑关联规则挖掘算法,其适合在多空间关系模式下,挖掘满足用户特定需求的拓扑关联。该算法通过拓扑关系编码法将空间关系事务转换成整数,用非目标自由空间对象类的集合序列数值递增的方法,索引构建候选频繁项,并用布尔运算计算支持数。在挖掘满足用户特定需求的空间拓扑关联规则时,该算法是快速而有效的。

关键词: 拓扑关联, 索引候选项, 集合序列数, 面向用户, 空间关联规则

Abstract: As present these mining algorithms can not extract spatial topology association for demand given by user,and if traditional constrain association rules mining algorithms are used to mining these spatial topology association rules,they will have repeated computing and superfluous candidate.Hence,an algorithm of user oriented spatial topology association mining is proposed,which is suitable for mining topology association for demand given by user in multi-spatial relation pattern.The algorithm uses the coding method of topology relation to transform spatial relation transaction into integer,and uses set sequence value ascending of non-target free spatial object class to index create candidate frequent itemsets,and uses Boolean operation to compute support.The algorithm uses these methods to efficiently improve mining efficiency.The algorithm is used to mine spatial topology association rules for demand given by user,and this experiment indicates that the efficiency is fast and efficient.

Key words: topology association, indexical candidate, set sequence, user oriented, spatial association rules

中图分类号: