显露模式(Emerging Patterns)的有效挖掘

Efficient mining of emerging patterns

EPs可以用来在数据库中进行知识发现 ,也可以捕获时标数据库中的显露趋势或数据类之间的有用对比 .由于Apriori属性对EPs不再适用 ,而且多维数据集或小支持度阈值 (如 0 5 % )有太多的侯选项集 .对此Naive算法代价太大 ,这使得EPs的有效挖掘成为一个挑战性问题 .为解决这些问题 ,本文介绍使用精确的边界描述大型项集集合 ,设计只操作边界集的EPs挖掘算法 ,并且使用边界表示已发现的EPs .

EPs can be used for knowledge discovery and for capturing emerging trends in timestamped databases,or making useful contrast between data classes.Since the Apriori property no longer holds for EPs,and there are ustally too many candidates for high dimensional databases or for small support thresholds such as 0.5%.Nave algorithms cost too much.All these make the effective mining of EPs a challenge.To solve these problems,we introduce EPs mining algorithms which manipulate only borders of collections ,and which represent discovered EPs using borders.All EPs satisfying a constraint can be efficiently discovered by our border-based algorithms.