隐私保护数据挖掘算法MASK的优化

针对MASK算法在重构原数据支持度的指数级复杂度的缺陷,提出了一种基于集合的优化策略,得到一种新的隐私保护挖掘算法.根据集合原理,利用已知数据项推出未知数据项数目,简化了计算各数据项数目的过程,减少了重构原数据支持度过程中扫描数据库的次数,消除了算法的指数级复杂度.实验结果表明,该优化方法比原算法有更好的性能.

Optimization for MASK algorithm in privacy preserving data mining

Aiming at the disadvantage of exponential complexity of reconstructing the original support of a set for MASK, a strategy based on aggregate is presented. A new algorithm of data mining is presented. According to aggregate, the number of unknown data item can be obtained from the known data item and the process of calculating the number of the data becomes easy. The algorithm could reduce the number of scanning the database in the course of reconstructing the original support of a set, and break the exponential com-plexity. The experiment indicates that this method has a better performance than the MASK.