概念格及其应用进展  

Advances in concept lattice and its application

作　　者：胡可云[1] 陆玉昌[1] 石纯一[1] 

机构地区：[1]清华大学计算机科学与技术系,北京100084

出　　处：《清华大学学报（自然科学版）》2000年第9期77-81,共5页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金项目! (79990 5 80 );国家"九七三"基础研究基金项目! (G19980 30 414) ;国家"九五"攀登预研基金项目

摘　　要：概念格是近年来获得飞速发展的数据分析的有力工具。从数据集中生成概念格的过程实质上是一种概念聚类过程。然而 ,概念格可以用于许多机器学习的任务 ,例如分类 ,关联规则的挖掘等。论文介绍了概念格的基本概念 ,讨论了现有的几种建格算法和在格上提取规则的方法及相关系统和应用。另外 ,还介绍了格的剪枝及概念格和另一个新型数据分析工具粗糙集之间的关系。Concept Lattice is a powerful tool for data analysis, which reveals the generalization/specification relationships between concepts in a vivid and concise way by a Hasse diagram. A concept lattice is built from data sets through the process of concept clustering. The concept lattice can be used in many other machine learning tasks, such as classification or association rule mining. This paper first introduced basic notions of concept lattice, then discussed several lattice construction methods and corresponding rule extraction algorithms and applications. Several concept lattice based systems were outlined briefly. This paper also describes topics such as lattice pruning and the relationship between concept lattice and rough sets.

关 键 词：概念格 规则提取 数据分析 概念聚类过程 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]