| 基于约简数据集的关联规则挖掘策略 |
| |
| 引用本文： | 彭云,聂承启,余松森.基于约简数据集的关联规则挖掘策略[J].计算机工程与应用,2006,42(11):169-172. |
| |
| 作者姓名： | 彭云 聂承启 余松森 |
| |
| 作者单位： | 江西师范大学计算机信息工程学院,南昌,330027;广东工业大学自动化学院,广州,510075 |
| |
| 基金项目： | 江西省自然科学基金;广东省广州市科技攻关项目 |
| |
| 摘 要： | 原始数据集中含有大量噪声数据,且数据的规模很大,直接进行关联规则挖掘会影响准确度和效率。文章提出了一种对原始数据先进行聚类,再提取关联规则的挖掘策略,可以在一定程度内减少噪声数据的干扰,消除数据对象中的冗余属性,提高规则挖掘的有效性。
|
| 关 键 词： | 关联规则 数据挖掘 聚类分析 属性约简 |
| 文章编号： | 1002-8331-（2006）11-0169-04 |
| 收稿时间： | 2005-09-01 |
| 修稿时间： | 2005-09-01 |
Association Rules Mining Strategy Based on Reduced Data Set |
| |
| Peng Yun,Nie Chengqi,Yu Songsen.Association Rules Mining Strategy Based on Reduced Data Set[J].Computer Engineering and Applications,2006,42(11):169-172. |
| |
| Authors: | Peng Yun Nie Chengqi Yu Songsen |
| |
| Affiliation: | College of Computer Information Engineering, Jiangxi Normal University, Nanchang 330027;College of Automation,Guangdong University of Technology,Guangzhou 510075 |
| |
| Abstract: | There are a lot of noise data in initial data set,and the scale of data is very large,so directly mining association rules from initial data set will diminish the accuracy and efficiency.A novel association rules mining strategy based on reduced data set is presented in the paper,and the clustering analysis is the first step,so the noise data can be eliminated to a certain extent,which can improve the correctness of result-rules.The second step is rules-mining, owing to the attributes reductlon,the redundant attributes can be omitted,and the association rules can be educed in the key attributes set. |
| |
| Keywords: | association rules data mining clustering analysis attributes reduction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
