隐私保护数据库中自适应重复数据删除仿真  

Adaptive Deduplication Simulation in Privacy Protection Database

作　　者：高继梅 GAO Ji-mei(College of Mechanical and Electronic Engineering,Huanghe Jiaotong University,Jiaozuo Henan 454950,China)

机构地区：[1]黄河交通学院机电工程学院,河南焦作454950

出　　处：《计算机仿真》2019年第1期239-242,共4页Computer Simulation

摘　　要：针对当前隐私保护数据库中自适应重复数据删除时,存在着重复数据删除时间过长,误删率较高、内存消耗过大等问题,提出基于分数阶变换累积量的重复数据删除方法。通过对隐私保护数据库中的重复数据进行分析,得到重复数据特征区间,对区间进行特征域平滑,计算出重复数据静态量化向量方差,以方差计算结果获取隐私保护数据库中存储节点子集随机概率,构建重复数据流信息模型,引用数据分数阶变换方法对模型中重复数据信息进行滤波处理,结合4阶累积量后置聚集进行重复数据删除。实验结果表明,所提方法重复数据删除时间较短、误删率较低、内存消耗较小。In this paper,a data deduplication method based on fractional transform cumulant was presented.Through the analysis of duplicated data in privacy protection database,the feature interval of duplicated data was obtained and the feature domain of interval was smoothed. Then,the variance of static quantization vector of duplicated data was calculated. According to calculation result of the variance,the random probability of subset of storage nodes in privacy protection database was obtained. Moreover,the duplicated data flow information model was built. Finally,the fractional transform method was used to filter the duplicated data information in model. Thus,the fourth-order cumulant post-aggregation was applied to the data deduplication. Simulation results show that the proposed method takes less time in data deduplication,which has lower error deletion rate and lower memory consumption.

关 键 词：隐私保护 重复数据删除 分数阶 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]