| 模糊关联规则的并行挖掘算法 |
| |
| 引用本文： | 陆建江,徐宝文,邹晓峰,康达周.模糊关联规则的并行挖掘算法[J].东南大学学报(自然科学版),2005,35(2):165-170. |
| |
| 作者姓名： | 陆建江 徐宝文 邹晓峰 康达周 |
| |
| 作者单位： | 东南大学计算机科学与工程系,南京,210096;江苏省软件质量研究所,南京,210096;解放军理工大学通信工程学院,南京,210007;东南大学计算机科学与工程系,南京,210096 |
| |
| 基金项目： | 国家自然科学基金，国家重点基础研究发展计划(973计划)，高等学校博士学科点专项科研项目 |
| |
| 摘 要： | 介绍了模糊关联规则挖掘算法的基本思想及实现步骤,提出了模糊关联规则的并行挖掘算法.并行挖掘算法采用并行的模糊c-均值算法将数量型属性划分成若干个模糊集,并借助模糊集软化属性的划分边界.用改进布尔型关联规则的并行挖掘算法来发现频繁模糊属性集.最后由多个处理器并行地产生满足最小模糊信任度的模糊关联规则.在分布式互连的PC/工作站环境下进行性能分析,结果表明并行的挖掘算法具有好的可扩展性、规模增长性和加速比性能.
|
| 关 键 词： | 数据挖掘 数量型属性 模糊聚类 关联规则 并行 |
| 文章编号： | 1001-0505(2005)02-0165-06 |
Parallel mining algorithm for fuzzy association rules |
| |
| Lu Jianjiang,Xu Baowen,Zou Xiaofeng,Kang Dazhou.Parallel mining algorithm for fuzzy association rules[J].Journal of Southeast University(Natural Science Edition),2005,35(2):165-170. |
| |
| Authors: | Lu Jianjiang Xu Baowen Zou Xiaofeng Kang Dazhou |
| |
| Abstract: | A parallel algorithm for mining fuzzy association rules is presented and its principle and steps are discussed. In this algorithm, the quantitative attributes are partitioned into several fuzzy sets by parallel fuzzy c-means algorithm. By means of fuzzy sets the partition boundary of the attributes is softened. Then, the parallel algorithm for mining Boolean association rules is improved to discover frequent fuzzy attributes. Finally, the fuzzy association rules with least fuzzy confidence are generated by all processors. This algorithm has been implemented at distributively linked PC/workstation. The experiment results show that the parallel mining algorithm has fine scaleup, sizeup and speedup. |
| |
| Keywords: | data mining quantitative attribute fuzzy cluster association rules parallel |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
