数据挖掘中基于Rough Set方法研究  

Research of Data Mining Based on Rough Set

作　　者：纪滨[1] 

机构地区：[1]安徽工业大学计算机学院,安徽马鞍山243002

出　　处：《计算机技术与发展》2008年第2期126-128,132,共4页Computer Technology and Development

基　　金：安徽省自然科学研究项目(2006KJ063B)

摘　　要：随着数据挖掘的兴起,有许多分类和预测的方法。数据挖掘研究的实施对象多为关系型数据库,这给粗糙集方法的应用带来了极大的方便。关系表可被看作为粗糙集理论中的决策表,而利用粗糙集理论来处理数据挖掘有着传统挖掘工具所不具有的优点。粗糙集理论是一种处理不确定和不精确问题的数学工具,文中通过实例介绍了粗糙集的基本理论,并通过实例详细介绍了在基于对决策表属性约简的基础上采用了可变精度粗糙模型实现规则的获取。该实例说明了对于不完备的信息系统,应用粗糙集理论进行数据挖掘是非常有效的。With the rise of data mining, there are many classification and prediction methods. What data mining researchs largely are relational databases. This has brought great convenience for rough set＇ s application. The relational table may regard as the decision table in rough set theory,and using the rough set to deal with data mining is more than the traditional mining tools.The rough set theory is a new mathematical approach to data analysis which are indiscernible with respect to some features. In this paper, basic theory of rough set is introducecl using an example, and the implementation of rule mining by variable precision rough set model based on reduction of decision form feature is illustrated using an example. It is effective for rule mining based on rough set by the example.

关 键 词：粗糙集 数据挖掘 信息系统 分类规则 数据归约 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] TP392[自动化与计算机技术—计算机科学与技术]