Aspects of approximate reasoning applied to unsupervised databasemining

摘要

A computational approach is shown for unsupervised, reactive,database mining. This approach is dependent on soft computingtechniques. Database mining seeks to discover noteworthy, unrecognizedassociations between data items in a database. Both crisp and non-crispdata are subject to discovery. Another aspect of uncertainty is themetric that controls discovery. Research issues involve: coherencemeasures, granularization, user intelligible results, unsupervisedrecognition of interesting results, and concept formation