基于粗糙集理论的数据挖掘研究初探  

Brief Research on Rough Set Theory Based on Data Mining

作　　者：王书青[1] 刘旭东[1] 

机构地区：[1]石家庄铁路职业技术学院,河北石家庄050041

出　　处：《石家庄铁路职业技术学院学报》2005年第2期88-91,共4页Journal of Shijiazhuang Institute of Railway Technology

摘　　要：数据挖掘是应用一系列技术从大型数据库或数据仓库的数据中提取人们感兴趣的信息或知识,这些知识或信息是隐含的事先未知而潜在有用的。粗糙集理论是一种处理不确定和模糊问题的数学工具,它的一系列优点使其特别适合于数据挖掘研究。介绍了数据挖掘的概念、特点、任务、分类、要求及研究意义,分析了粗糙集理论的特点、所处理的问题、在数据挖掘中的简单应用,以及粗糙集在数据挖掘中的应用展望等。Data Mining is a kind of technique which can extract knowledge or information that people require from vast Database or Data Warehouse and the knowledge or information is latently useful and connotative and unknown in advance. Rough set theory is a tool designed for dealing with uncertainty and vague knowledge. It is quite suitable for the research of Data-Mining. This paper introduces the concept, characteristics, tasks, classification and demand of Data-Mining and its purpose. It analyzes the characteristics of Rough Set theory, the problems processed by the theory, its simple application and the prospect in Data Mining.

关 键 词：粗糙集 数据挖掘 分类 人工智能 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]