| 关联规则挖掘的一个高效预处理算法 |
| |
| 引用本文： | 娄兰芳,潘庆先.关联规则挖掘的一个高效预处理算法[J].烟台大学学报(自然科学与工程版),2007,20(1):44-47. |
| |
| 作者姓名： | 娄兰芳 潘庆先 |
| |
| 作者单位： | 烟台大学,计算机学院,山东,烟台,264000 |
| |
| 摘 要： | 利用视图机制对原始数据进行预处理,把符合条件的数据和有用的属性放入视图中.根据一维(L1)和二维(L2)中的频繁数据项集对数据库中的属性进行过滤,以达到减少数据属性的目的,从而压缩数据库中的数据,为提高关联规则挖掘算法的性能打下基础.
|
| 关 键 词： | 关联规则 频繁项目集 过滤 视图 |
| 文章编号： | 1004-8820（2007）01-0044-04 |
| 收稿时间： | 2006-03-23 |
| 修稿时间： | 2006-03-23 |
An Efficient Preprocessing Algorithm for Mining Association Rules |
| |
| LOU Lan-fang,PAN Qing-xian.An Efficient Preprocessing Algorithm for Mining Association Rules[J].Journal of Yantai University(Natural Science and Engineering edirion),2007,20(1):44-47. |
| |
| Authors: | LOU Lan-fang PAN Qing-xian |
| |
| Institution: | School of Computer, Yantai University, Yantai 264005, China |
| |
| Abstract: | The data meeting some conditions and useful attributes are extracted into views using the mechanism of view to pretreated the primary data.Attributes in the database are filtrated according to the frequent data item sets of large one item sets(L_1) and large two item sets(L_2) in order to reduce the number of data attributes,at the same time,compress the data volume of the database. Thus should be made the infrastructure of the high performance data mining algorithm of association rules. |
| |
| Keywords: | association rules frequent data item sets filtrate view |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
