Knowledge Representation in KDD Based on Linguistic Atoms

An important issue in Knowledge Discovery in Databases is to allow the discovered knowledge to be as close as possible to natural languages to satisfy user needs with tractability on one hand, and to offer KDD systems robustness on the other hand. At this junction, this paper describes a new concept of linguistic atoms with three digital characteristics: expected value Ex, entropy En, and deviation D. The mathematical description has effectively illtegrated the fuzziness and randomness of linguistic terms in a unified way Based on this model a method of knowledge representation in KDD is developed which bridges the gap between quantitative knowledge and qualitative knowledge. Mapping between quantitatives and qualitatives becomes much easier and interchangeab1e. In order to discover genera1ized knowledge from a database, one may use virtual linguistic terms and cloud transforms for the auto-generation of concept hierarchies to attributes. Predictive data mining with the cloud model is given for implementation. This further illustrates the advantages of this linguistic model in KDD.