View article

Frequent pattern mining has been a focused theme in data mining research and an important first step in the analysis of data arising in a broad range of applications. The traditional exact model for frequent pattern requires that every item occurs in each supporting transaction. However, real application data is usually subject to random noise or measurement error, which poses new challenges for the efficient discovery of frequent pattern from the noisy data. Mining approximate frequent pattern in the presence of noise involves two key issues: the definition of a noise-tolerant mining model and the design of an efficient mining algorithm. In this paper, we will give an overview of the approximate itemset and sequential pattern mining.