期刊文献+

基于支持度与置信度阈值优化技术的关联分类算法 被引量:9

Associative classification algorithm based on support and confident thresholds tuning technique
下载PDF
导出
摘要 基于关联规则的分类算法中,支持度和置信度阈值的设置会影响分类器的准确率。以往的关联分类算法都根据经验人为地设置支持度和置信度的阈值,很难保证分类器总能达到较好的分类效果。为了解决该问题,可以将优化求解策略引入到关联分类过程中。通过利用爬山法搜索技术来获得使分类准确率最高的支持度与置信度阈值,对Apriori_TFP_CMAR关联分类算法进行改进,避免了阈值设置不合理影响最终分类效果的问题,提高了关联分类算法的分类准确率。 The set of the support and confident thresholds usually affects the accuracy of classification based on association rules. As for the previous associative classification algorithms, the two thresholds are always set by experiences, so it is difficult to ensure that the classifier can always get the best accuracy. In order to solve this problem, the optimization strategies can be introduced to associative classification algorithm. The hill climbing search method was used to improve the Apriori_TFP_CMAR algorithm to get the highest classification accuracy of the set of support and confidence thresholds. This strategy can avoid the unreasonable set of threshold, and enhance the classification accuracy.
作者 张健 王蔚
出处 《计算机应用》 CSCD 北大核心 2007年第12期3032-3034,3038,共4页 journal of Computer Applications
基金 全国教育科学"十五"规划重点课题资助项目(DCA050056) 江苏省教育科学"十一五"规划2006年度课题资助项目(D/2006/01/096)
关键词 关联分类 支持度阈值 置信度阈值 Apriori_TFP 爬山法 associative classification support threshold confident threshold Apriori_TFP hill climbing
  • 引文网络
  • 相关文献

参考文献10

  • 1LIU B, HSU W, MAY. Integrating classification and association rule mining [C]// Proceedings of the 4th International Conference on Knowledge Discovery and Data Mining ( KDD-98). New York: AAAI, 1998: 80 - 86.
  • 2LI W M, HAN J W, PEI J. CMAR: accurate and efficient classification based on multiple class-association rules [C]//Proceedings of the 1st IEEE International Conference on Data Mining (ICDM 2001 ). Washington: IEEE Computer Society, 2001: 369- 376.
  • 3YIN X X, HAN J W. CPAR: classification based on predictive association rules [C]// Proceedings of the 2003 SIAM International Conference on Data Mining (SDM'03). San Francisco: [ s. n.], 2003:34 - 42.
  • 4COENEN F, LENG P. Data structures for association rule mining: t-trees and p-trees [J]. IEEE Transaction in KnowIedge and Data Engineering, 2004, 16(6) : 774 -778.
  • 5COENEN F. LUCS-KDD DN Software (Version 2) [ EB/OL]. [2007 -04 -02]. http://www. csc. liv. ac. uk/- frans/KDD/Software/ LUCS_KDD_DN/.
  • 6王晓峰,王天然.相关测度与增量式支持度和信任度的计算[J].软件学报,2002,13(11):2208-2214. 被引量:8
  • 7汪西原,汪西莉.启发式搜索策略(爬山法)的改进与实现[J].陕西师大学报(自然科学版),1999,27(1):58-58. 被引量:7
  • 8楼晓鸿,丁宝康.一种多支持度的关联规则采集算法[J].计算机工程,2001,27(6):102-103. 被引量:7
  • 9AGRAWAL R, SRIKANT R. Fast algorithms for mining association rules [C]// Proceeding of the 1994 International Conference on Vary Large Data Bases. Santiago: Morgan Kaufmann, 1994:487 -499.
  • 10BLAKE C L, MERZ C J. UCI Repository of machine learning databases [EB/OL]. [2007 -04 - 15]. http://www.ics. uci. edu/- mlearn/MLRepository, html.

二级参考文献9

共引文献19

同被引文献56

引证文献9

二级引证文献25

;
使用帮助 返回顶部