A Hybrid Classification Method for Database Contents Analysis

The hybridisation of different classification and mining techniques coming from different areas such as the numeric and the symbolic worlds can produce a significant enhancement of the overall classification and retrieval performance in a Data Mining or Information Retrieval context. This paper introduces an experimental methodology to match an explicative structure issued from a symbolic classification to a numerical classification. The classification models used in the experiment are a boolean lattice on the symbolic side and a Kohonen Self Organising Map model (SOM) on the numerical side.