“多元”关联模式的时空数据挖掘

来源期刊:中南大学学报(自然科学版)2011年第1期

论文作者:陈新保 LI Song-nian 朱建军 陈建群

文章页码:106 - 114

关键词:“多元”关联模式;要素关联规则;等价类

Key words:multivariate association patterns; feature association rules; equivalence classes

摘    要:为了从大量的时空数据集中挖掘类似于“星型”和“序列型”的“多元”关联规则模式,首先,针对要素同类和关系同质,提出“多元”关联模式的概念,即“多类别”和“多要素”下的“多规则”的关联组合;其次,用“图论”的方法构建常见的“星型”和“序列型”等“多元”关联模式;再次,提出“多元”关联模式的挖掘算法,引入“等价类”,搭建“多元”关联模式。合成实例(城市规划)说明“多元”关联模式的时空数据挖掘模式及其挖掘算法具有可用性。

Abstract: To mine multivariate association patterns (MVAP), such as “star-like” and “sequence” multivariate association patterns, from large spatiotemporal datasets, a combination of multi-class-features (MCF) and multi-association-rules (MAR) was proposed according to entity types and relationships. The MVAP was then established based on the methods of graph theory. A new MVAP algorithm was presented by introducing “Equivalence Classes” to quickly identify MVAP. By use of an example in urban planning used to explain the MVAP process for spatiotemporal data mining, the results show that the MVAP and their algorithm have applicability.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号