摘要
随着大数据时代的来临,数据挖掘过程中的隐私泄露给数据挖掘工作者带来了很多问题和挑战.在数据挖掘过程中,如何在保护敏感信息的同时,高效地挖掘出符合精确度的结果,是隐私保护数据挖掘领域的热点问题.文中首先介绍了AOPAM隐私保护关联规则挖掘算法,通过分析该算法的缺陷和不足,引入了递推和分治策略,提出了一种新的改进算法.通过利用已知项求解未知项的思维,简化了高阶矩阵的求逆运算,有效减少了数据库的扫描次数,降低了AOPAM算法在计算重构项集支持度时的时间复杂度.实验表明,以同类型数据测试,与原算法相比,改进后算法在运行时间效率上得到了有效提高.
In the era of big data, privacy disclosure has brought various problems and challenges to data mining researchers. Then how to keep sensitive data safe while excavating data effectively is studied. Firstly, a privacy preserving association rule mining algorithm called AOPAM is analyzed. Since the algorithm is not effective in execution time, a modified method based on recursion and divide-and-conquer strategy is proposed to handle the problems of AOPAM. Based on KuU, the proposed method simplifies the inversion of high-order matrix, cuts down the scan times on database, which results in lower time complexity of refactoring support of items in AOPAM. Experiment results show that, compared with the original algorithm, the proposed method has higher runtime efficiency with the same test dataset.
作者
殷英
王逊
黄树成
YIN Ying;WANG Xun;HUANG Shucheng(School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China)
出处
《江苏科技大学学报（自然科学版）》
CAS
2019年第2期69-73,95,共6页
Journal of Jiangsu University of Science and Technology:Natural Science Edition
基金
国家自然科学基金资助项目(61772244
61572498)
关键词
数据挖掘
隐私保护
关联规则
data mining
privacy preserving
association rule
