Research of discovery feature sub-space model (DFSSM) based on complex type data

Abstract

Discusses the macroscopic and some other important problems in the field of KDD. First, it is very difficult to describe the complex type data by a general knowledge representation method. So we use the pattern which is defined as the vector in Hilbert space to represent the characteristic of complex type data. It also can be used to describe the rule of knowledge discovery. Secondly, we construct the general structure model based on complex type data-DFSSM (discovery feature sub-space model) followed by research on the inner mechanism of a knowledge discovery system. Finally, we prove the practicability and validity of this general structure model i.e. DFSSM, which can guide the knowledge discovery of textual data and image data (meteorologic nephogram data).