| 基于最大频繁项目序列集挖掘DMFIA算法的改进 |
| |
| 引用本文： | 宋卫林,徐惠民. 基于最大频繁项目序列集挖掘DMFIA算法的改进[J]. 计算机工程与设计, 2007, 28(7): 1493-1496,1500 |
| |
| 作者姓名： | 宋卫林 徐惠民 |
| |
| 作者单位： | 北京邮电大学,电信工程学院,北京,100876;北京邮电大学,电信工程学院,北京,100876 |
| |
| 摘 要： | 为了有效地解决客户序列视图数据库的数据挖掘问题,借鉴了关联规则挖掘最大频繁项目集DMFIA算法的相关思想.详细阐述了该算法,针对原算法不能有效地解决客户序列视图数据库的数据挖掘这一问题,在原算法的基础上结合序列模式提出了改进的DMFIA算法,并在原算法的基础上有了较大的改进.为了验证算法的正确性,运用Ora-cle9i数据库的PL/SQL进行了相应的验证.实验结果证实了改进算法的有效性和实用性,并具有较好的创新性和理论价值.
|
| 关 键 词： | 数据挖掘 关联规则 序列模式 DMFIA算法 最大频繁项目集 最大频繁项目序列集 |
| 文章编号： | 1000-7024（2007）07-1493-04 |
| 修稿时间： | 2006-03-05 |
Improvement of DMFIA algorithm based on mining of maximal frequent item sequence sets |
| |
| SONG Wei-lin,XU Hui-min. Improvement of DMFIA algorithm based on mining of maximal frequent item sequence sets[J]. Computer Engineering and Design, 2007, 28(7): 1493-1496,1500 |
| |
| Authors: | SONG Wei-lin XU Hui-min |
| |
| Affiliation: | School ofTelecommunicationEngineering, Beijing University ofPosts and Telecommunications, Beijing 100876, China |
| |
| Abstract: | In order to solve the problem of data mining about customer sequence view database validly, the correlative idea ofthe DMFIA algorithm for mining of maximal frequent item sets is refered. The DMFIA algorithm is expounded particularly. Because the algorithm can not solve the problem of data mining about customer sequence view database validly, the improved algorithm combining with sequential patterns is put forword. Based on the DMFIA algorithm, the larger improvement is achieved in the improved algorithm. In order to validate the correctness of the improved algorithm, the algorithms are tested through PL/SQL language of oracle9i database accordingly. The experimental result validates the validity and practicability of the improved algorithm. It shows the better creativity and value of theory of the improved algorithm. |
| |
| Keywords: | data mining association rule sequence pattern DMFIA algorithm maximum frequent item sets maximum frequent item sequence sets |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
