摘要
在传统的事务数据库中,频繁模式的挖掘是一个已经有很多较好解决办法的问题,但是在不确定数据集上,仅仅提出了几种频繁模式的挖掘技术,而这些新技术对于不确定数据集中的项的不确定性的处理效果不是很好.本文主要探讨在可能世界的概念下,用基于抽样的方法来处理不确定数据,并在此基础上,研究在保证较低的精度损失下优化频繁模式挖掘算法.
Mining frequent pattern from transactional datasets is a popular problem which has some good algorithmic solutions. In the case of uncertain datasets,however,several new techniques have been proposed. Unfortunately,these proposals often suffer when a lot of items occur with many different probabilities. In this paper,we focus on the method based on sampling by instantiating possible worlds of the uncertain data. Then we study the optimized frequent pattern mining algorithm which gains efficiency at a surprisingly low loss in accuracy.
出处
《商丘师范学院学报》
CAS
2015年第12期16-19,共4页
Journal of Shangqiu Normal University
