期刊论文

Incremental Top-k high utility pattern mining algorithm in dynamic database

中文

计算机应用研究

1001-3695

2017

34

5

1401-1405

10.3969/j.issn.1001-3695.2017.05.028

国家自然科学基金资助项目

本校为第一机构

高效用模式的挖掘需要设定一个合适的阈值,而阈值设定对用户来说并非易事,阈值过小导致产生大量低效用模式,阈值过大可能导致无高效用模式生成。因而Top-k高效用模式挖掘方法被提出,k指效用值前k大的模式。并且大量的高效用挖掘研究仅针对静态数据库,但在实际应用中常常会遇到新事务的加入的情况。针对以上问题,提出了增量的Top-k高效用挖掘算法TOPK-HUP-INS。算法通过四个有效的策略,在增量数据的情况下,有效地挖掘用户所需数量的高效用模式。通过在不同数据集上的对比实验表明TOPK-HUP-INS算法在时空性能上表现优异。

Setting an appropriate threshold was essential to high utility pattern mining, however it was a difficult task for users. If the threshold was too low, a large number of low utility patterns were generated; if the threshold was too high, no high utility patterns might be generated. According, Top-k high utility pattern mining was proposed, in which k was the number of highest utility patterns. Most studies on high utility mining were only designed for static database, yet in real-world applications some new transactions inserted in original database. To address the above issues, this paper pro...