Discovering database summaries through refinements of fuzzy hypotheses

Abstract

Recently, many applications such as scientific databases and decision supporting systems that require comprehensive analysis of a very large amount of data, have been evolved. Summary discovery techniques, which extract compact representations grasping the meanings of large databases, can play a major role in those applications. We present an effective and robust method to discover simple linguistic summaries. We first propose a hypothesis refinement algorithm that is a key technique for our summary discovery method. Using the algorithm, a formal procedure for summary discovery is presented together with an illustrative example. Our discovery method can handle both rigid concepts and fuzzy concepts that occur frequently in practice. Discovered summaries can also be regarded as high-level interattribute dependencies.<>