基于PL/SQL的粗糙集分类算法研究  

Rough set classification algorithm based on PL/SQL

作　　者：邢长征[1] 杨冬庆 李秀华[1] 

机构地区：[1]辽宁工程技术大学电子与信息工程系,辽宁阜新123000 [2]辽宁省阜新市自来水总公司,辽宁阜新123000

出　　处：《辽宁工程技术大学学报（自然科学版）》2006年第2期255-257,共3页Journal of Liaoning Technical University (Natural Science)

摘　　要：为改进数据分类的效果,基于粗糙集理论实现数据分类和规则推理的基本原理,利用粗糙集理论中核及决策类覆盖的思想,提出了一个在数据集中发现没有冗余属性的最小归纳依赖关系,简化带有不相容规则的决策系统的数据挖掘算法。通过PL/SQL演示了挖掘分类规则的过程,结果表明基于粗糙集分类算法的有效性。In order to improve the effect of mining classification rules in data, the paper introduces the basic principle for rule generation and mining classification rules in data sets. The paper also describes the concept of core and decision class covering in rough set theory. Then, by analyzing induction dependency relation among attributes, we give a new method of discovering minimum induction dependency relation in data sets. which is used to mine classification rules with non-consistent decision rules in a decision system. In the end, using PIdSQL code the process of mining classification rules is demonstrated. The result shows the validity of the algorithm based on rough set.

关 键 词：粗糙集 PL/SQL 分类规则 决策系统 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]