一种基于粒计算的知识隐藏方法  

A granular computing approach for knowledge hiding

作　　者：邱桃荣[1] 王璐[1] 熊树洁[1] 白小明[1] 

机构地区：[1]南昌大学计算机系,江西南昌330031

出　　处：《山东大学学报（理学版）》2010年第7期60-64,75,共6页Journal of Shandong University(Natural Science)

基　　金：江西省重点攻关项目(20061B01002);江西省教育厅科技资助项目([2007]28)

摘　　要：对数据中蕴涵的敏感知识的隐藏与保护是私有保护数据挖掘中重要一个研究课题。粒计算具有在不同的粒度层次上进行问题求解的能力。本文讨论了基于粗糙集粒计算模型的数据中知识隐藏与保护方法。首先,介绍了不完备信息系统下的相容关系、相容信息粒和信息粒度;其次,提出基于粒计算的知识隐藏与保护方法;最后,通过具体实例和在真实数据集上的测试表明了所提出方法的可行性。The protection of sensitive knowledge contained in the data is a key research issue in privacy preserving data mining.Granular computing has powerful ability in using different levels of granulations during problem solving.By using a granular computing model derived by rough set,a method for knowledge hiding in the data was discussed.First,some concepts such as tolerance relations,tolerance information granules and the size of granules were introduced.Second,an approach for knowledge hiding was proposed.Finally,the given example and testing in real datasets showed that the proposed method was effective.

关 键 词：知识隐藏 隐私保护 粒计算 相容信息粒 

分 类 号：TP39[自动化与计算机技术—计算机应用技术] TP181[自动化与计算机技术—计算机科学与技术]