基于Bayes统计推断的粗糙集数据挖掘方法  

The Method of Rough Set Data Mining Based on Naive Bayes

作　　者：李丽红[1] 李超[1] 

机构地区：[1]河北理工大学理学院,河北唐山063009

出　　处：《河北理工大学学报（自然科学版）》2008年第2期75-77,共3页Journal of Hebei Polytechnic University:Social Science Edition

基　　金：国家自然科学基金(70271048);河北省自然科学基金(E2006000377)

摘　　要：分类发现是数据挖掘的一个重要任务,Bayes统计推断是数据挖掘中数据分类的主要方法也是其基础之一。建立在粗糙集基础上。利用概率工具以及Expectation-Maximization思想(RUBIN算法)和Bayes统计推断规则的结合提出了分类的方法和步骤,并给出实例分析,重点是RUBIN算法和Bayes统计推断规则相结合在粗糙集上建立的决策方法。Classification is an important mission of Data Mining. Naive Bayes is the main method for DMC and one of its foundations. This text, based on Routh Set, made use of all the statistical tool and the Expectation-Maximization method RUBIN method combination with the Naive Bayes to expound the method and step of the classification, as well as gave an example. The point of text is the combination of the RUBIN method and the Native Bayes to build up of RS decision method.

关 键 词：数据挖掘 粗糙集 RUBIN算法 Bayes统计推断规则 

分 类 号：O212.8[理学—概率论与数理统计]