|
|||||
|
|
| 一种改进的并行挖掘关联规则的算法 | |
| 引用本文： | 佘春东,孙世新,范植华,胡世祥,车著明. 一种改进的并行挖掘关联规则的算法[J]. 小型微型计算机系统, 2004, 25(12): 2139-2142 |
| 作者姓名： | 佘春东 孙世新 范植华 胡世祥 车著明 |
| 作者单位： | 1. 电子科技大学,计算机科学与工程学院,四川,成都,610054 2. 中国科学院,软件研究所,北京100080 3. 中国人民解放军,总装备部,北京100720 4. 西昌卫星发射中心,技术部,四川,西昌,615000 |
| 基金项目： | 中国科学院知识创新工程方向性研究项目基金 ( KGCX2 -JG-0 9)资助 |
| 摘 要： | 发现关联规则是数据挖掘的一个重要的任务．简要介绍了几种发现关联规则的串行算法和并行算法，并针对IDD和HD这两种效率和可扩展性较好的算法，引入在线LPT调度算法，有效地解决了IDD和HD算法中非常重要的候选项目集在各个处理器节点之间的划分问题，尽可能使得各个节点负载平衡，从而提高算法的效率． |
| 关 键 词： | 数据挖掘 并行处理 关联规则 负载平衡 可扩展性 近似算法 在线算法 离线算法 |
| 文章编号： | 1000-1220(2004)12-2139-04 |
Improved Algorithm for Parallel Mining Association Rules |
|
| SHE Chun-dong ,SUN Shi-xing ,FAN Zhi-hua ,HU Shi-xiang ,CHE Zhu-ming. Improved Algorithm for Parallel Mining Association Rules[J]. Mini-micro Systems, 2004, 25(12): 2139-2142 | |
| Authors: | SHE Chun-dong SUN Shi-xing FAN Zhi-hua HU Shi-xiang CHE Zhu-ming |
| Affiliation: | SHE Chun-dong 1,SUN Shi-xing 1,FAN Zhi-hua 2,HU Shi-xiang 3,CHE Zhu-ming 4 1 |
| Abstract: | Discovery of association rules is an important task of data mining. Several parallel and sequential algorithms have been proposed in this paper to solve the problem. IDD and HDD algorithms are efficient and scalable parallel methods applied in the discovery of association rules in the field of data mining. However, they become less effective due to the imbalance caused by distributing the candidates among the processors. Therefore, IDD and HDD are improved by means of introducing the on-line LPT scheduling algorithm to solve the problem of load balance effectively. |
| Keywords: | data mining parallel processing association rules load balance Scalability approximate algorithm online algorithm offline algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |