垂直划分多决策表下基于条件信息熵的隐私保护属性约简

J4 ›› 2010, Vol. 45 ›› Issue (9): 14-19.

• 第十届中国Rough集与软计算学术会议专栏 • 上一篇下一篇

垂直划分多决策表下基于条件信息熵的隐私保护属性约简

叶明全^1,2, 胡学钢¹,伍长荣³

1.合肥工业大学计算机与信息学院, 安徽合肥 2300091;
2.皖南医学院计算机教研室, 安徽芜湖 241002;
3.安徽师范大学数学计算机学院, 安徽芜湖 241002

收稿日期:2010-06-13 出版日期:2010-09-16 发布日期:2010-10-12
作者简介:叶明全(1973-),男,副教授,博士研究生,研究方向为粗糙集、数据挖掘与隐私保护. Email:ymq@wnmc.edu.cn
基金资助:
国家自然科学基金资助项目(60975034);安徽省高校省级自然科学研究资助项目(KJ2010B241)

Privacy preserving attribute reduction based on conditional information entropy over vertically partitioned multi-decision tables

YE Ming-quan^1,2, HU Xue-gang¹, WU Chang-rong³

1. Institute of Computer and Information, Hefei University of Technology, Hefei 230009, Anhui, China;
2. Computer Staff Room, Wannan Medical College, WuHu 241002, Anhui, China;
3. Institute of Mathematics and Computer, Anhui Normal University, WuHu 241002, Anhui, China

Received:2010-06-13 Online:2010-09-16 Published:2010-10-12

摘要/Abstract

摘要：

针对垂直划分多决策表，利用半可信第三方和交换加密体制,设计了一个安全多方计算交集基数协议。利用该协议设计了安全多方计算信息熵和安全多方计算条件信息熵的解决方案,提出了一种基于条件信息熵的隐私保护属性约简算法。该算法基于粗糙集信息观的约简理论实现了分布式环境下全局属性约简的求解,使各参与方在不共享其隐私信息的前提下达到集中式属性约简的效果,分析结果表明该算法是有效可行的。

关键词: 属性约简;隐私保护;安全多方计算;粗糙集;条件信息熵

Abstract:

A privacy-preserving set intersection cardinality computation protocol based on semi-trusted third party and commutative encryption is developed, which can be used to slove the privacy-preserving computational problems, such as information entropy computation and conditional information entropy computation. A privacy-preserving attribute reduction algorithm based on conditional information entropy for the vertically partitioned multi-decision tables is proposed.The algorithm can compute globally valid attribute reduction using the attribute reduction idea based on information viewpoint of Rough set theory, which can get accurate attribute reduction effect in the premise of no sharing of private information among participators. Analysis results show the proposed algorithm is efficient.

Key words: attribute reduction; privacy preserving; secure multi-party computation; Rough set; conditional information entropy

叶明全1,2, 胡学钢1,伍长荣3. 垂直划分多决策表下基于条件信息熵的隐私保护属性约简[J]. J4, 2010, 45(9): 14-19.

YE Ming-quan1,2, HU Xue-gang1, WU Chang-rong3. Privacy preserving attribute reduction based on conditional information entropy over vertically partitioned multi-decision tables[J]. J4, 2010, 45(9): 14-19.

参考文献

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

垂直划分多决策表下基于条件信息熵的隐私保护属性约简

Privacy preserving attribute reduction based on conditional information entropy over vertically partitioned multi-decision tables

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

多维度评价

本文评价

推荐阅读 0