概率数据中的频繁项挖掘

Mining Frequent Items in Probabilistic Data

概率数据是从很多隐含模糊数据或不确定的数据的数据资源中生存的数据,而在概率数据上计算统计信息也已经引起了广泛的关注。频繁项挖掘是概率数据上的一个重要的统计查询内容,它也是很多研究工作的基础。使用项的期望频繁度来判断频繁项会丢失概率数据内部结构的重要信息,本文介绍一种被许多概率数据中查询管理采用的定义来发现所有的频繁项。

Computing statistical information on probabilistic data has attracted a lot of attention, as the data generated from a wide range of data sources are inherently fuzzy of uncertain. Finding the frequent items is an important statistical query on probabilistic data. And it is the basic work of many researches. However, deciding whether an item is a fre- quent item by expected frequency of an item misses important information about the internal structure of the probabilistic data. In this paper, we study a definition that has been widely adopted for many query management on probabilistie da- ta, trying to find all the frequent items.