摘要
分类和关联规则发现是数据挖掘中的两个重要领域。使用关联规则算法挖掘分类规则被叫做分类关联规则算法,是一个有较好前景的方法。本文提出了一个最优分类关联规则算法——OCARA。该算法使用最优关联规则挖掘算法挖掘分类规则,并对最优规则集排序,从而获得一个分类精度较高的分类器。将OCARA与传统分类算法C4.5和一般分类关联规则算法CBA、RMR在8个UCI数据集上进行实验比较,结果显示OCARA具有更好的性能,证明OCARA是一个有效的分类关联规则挖掘算法。
Classification and association rule mining are two important fields in data mining. Using the association rule mining algorithm to discover classification rules is called the class association rule mining algorithm, which is a promising approach. This paper introduces an optimal class association rule mining algorithm named OCARA. Since OCARA uses the optimal association rule mining algorithm, and the rule set is sorted by the priority of rules, and thus it results in a more accurate classifier. This algorithm is compared with C4. 5, CBA, RMR on eight UCI data sets respectively. The experimental results show that it has better performance.
出处
《计算机工程与科学》
CSCD
北大核心
2009年第4期63-65,共3页
Computer Engineering & Science
基金
国家自然科学基金资助项目(60603053)
教育部重点支持项目(106158)
关键词
分类关联规则
关联规则
分类
数据挖
class association rule
association rule
classification
data mining
