基于相关系数的隐私保护关联规则挖掘  

Privacy Preserving Association Rule Mining Based on Correlation Coefficient

作　　者：戴智丽[1] 李霞[1] 吕庆春[1] 

机构地区：[1]燕山大学信息科学与工程学院,秦皇岛066004

出　　处：《计算机工程》2010年第5期84-85,共2页Computer Engineering

摘　　要：传统的隐私保护关联规则挖掘算法由于没有考虑规则左右件相关系数的影响,对非敏感规则的支持度影响很大。为了减小这种影响,提出通过调整规则左右件相关系数隐藏敏感规则的算法。该算法通过调整相关系数,使敏感规则的价值无法被发现,从而达到隐藏敏感规则的目的。实验结果表明,该算法的规则丢失率和相异度均有所下降。Traditional privacy preserving association rule mining algorithms do not consider the correlation of the left hand side and the right hand side, which affect non-restrictive rule support negatively. In order to solve the problem, this paper presents an algorithm which adjusts the correlation coefficient to hide restrictive rules because the value of this rule can not be found. Experimental results show that the algorithm has lower miss rate and dissimilarity.

关 键 词：关联规则 隐私保护 数据挖掘 相关系数 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]