基于核属性的知识获取算法

Knowledge Acquisition Algorithm Based on Attribute Core

Rough集理论是近年来发展起来的一种有效地处理不精确、不确定、含糊信息的数学理论方法,在机器学习、数据挖掘、智能数据分析、控制算法获取等领域取得了很大的成功。决策表是Rough Set理论的处理对象,用Rough Set对决策表进行规则提取通常有代数观和信息观两种主要理论和方法,使用哪一种方法提取的规则集更好是很多研究者的目标。本文针对Rough Set理论的核心内容之一的知识获取进行了研究,提出了一种基于属性重要性排序的知识获取算法,并且证明了在不相容系统中使用信息观方法比使用代数观的方法更好,能够提取更合理的规则集。

Rough set is a valid mathematical theory developed in recent years,which has the ability to deal with imprecise, uncertain, and vague information. It has been applied in such fields as machine learning, data mining, intelligent data analyzing and control algorithm acquiring successfully. The attribute core of a decision table is often the start point and key of many decision information system reduction procedures based on rough set theory. The algebra view and informa- tion view are two main views and of rough set theory in knowledge acquisition. Many scholars are finding the best methods which can get better rules using algebra view or information view. In this paper, based on the problem of rules acquisition of a decision table, we develop a knowledge acquisition algorithm based on attribute sorting according to importance of attribute, and prove that we can get better rules using information view in incompatible system.