点击次数：

论文类型：期刊论文

发表时间：2012-11-01

发表刊物：International Journal of Advancements in Computing Technology

收录刊物：EI、Scopus

卷号：4

期号：20

页面范围：625-632

ISSN号：20058039

摘要：Frequent pattern mining on uncertain dataset takes into consideration of item's existing probability, but does discriminate items by their different importance. To address this issue, we propose a new mining model called High Expected Weight Itemsets Mining (or weighted frequent pattern mining) on uncertain dataset based on the concept of expected weight. We also propose a corresponding algorithm called HEWI-Mine to mine high expected weight itemsets from uncertain dataset using a pattern- growth approach. We perform some testing mining on multiple datasets, and observe different mining results produced. Because items in real-world transaction database do contain different weight properties, such as price or profit, this model may contribute to more precise analysis on business applications involving frequent pattern mining.