计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (27): 135-137.DOI: 10.3778/j.issn.1002-8331.2010.27.037

• 数据库、信号与信息处理 • 上一篇    下一篇

分布式数据库分类规则挖掘的聚集模型

王树锋   

  1. 常州工学院 计算机信息工程学院,常州市软件技术与应用重点实验室,江苏 常州 213002
  • 收稿日期:2009-02-25 修回日期:2009-04-23 出版日期:2010-09-21 发布日期:2010-09-21
  • 通讯作者: 王树锋

Aggregation model for distributed data classification rules mining

WANG Shu-feng   

  1. School of Computer Information & Engineering,Changzhou Institute of Technology,Changzhou Key Laboratory of Software Technology and Application,Changzhou,Jiangsu 213002,China
  • Received:2009-02-25 Revised:2009-04-23 Online:2010-09-21 Published:2010-09-21
  • Contact: WANG Shu-feng

摘要: 研究大规模分布式数据挖掘问题,提出了一个基于投票的挖掘分布式数据库的聚集模型。该模型计算产生于子数据库中每条规则的信任系数,通过投票得到一组划分的分类规则集。该模型表示出良好的预测能力和描述能力,而且概念上特别简单直观。

Abstract: In this paper the problem of mining large distributed databases is presented.An aggregation model is proposed,i.e.,sets of disjoint classification rules,which build over a subdatabase based on a majority vote.The aggregation model presents excellent predictive capability and descriptive capability and that is conceptually much simpler than the comparable techniques.

中图分类号: