增量式隐私保护数据挖掘研究

Research on incremental privacy preserving data mining

描述了隐私保护数据挖掘技术研究进展。针对隐私保护关联规则挖掘算法EMASK计算效率较低,同时不适用于动态变化数据库等的问题,提出基于粒度计算的增量式隐私保护数据挖掘算法BIEMASK。该算法用粒度计算的思想对EMASK算法进行改进,利用增量式更新算法FUP解决增量式事务数据库频繁项集计算问题。在实现隐私保护的同时,减少了I/O操作的次数,降低空间开销,由此提高计算效率。结果证明,无论是固定增量集数据库还是可变增量集数据库处理中,BIEMASK相对于EMASK而言,效率时间都有较大幅度的提高。

This paper described the research progress of privacy preserving data mining technology. Devoted to the question about privacy preserving association rule mining algorithm EMASK＇s lower computation efficiency and not applicable to dynamic database,it proposed incremental privacy preserving data mining algorithm based on granular computing BIEMASK. This algorithm proposed improvements with granular computing,solved the calculation problem of incremental business database frequent item sets by using the incremental updating algorithm FUP. While achieving privacy preserving,reduced the number of I/O operations and the space overhead,thus improved the efficiency. The experimental results show that,whether in fixed or variable incremental database processing,the time efficiency is improved greatly by BIEMASK compared with EMASK.