Towards a Discovering Knowledge Comprehensible and Exploitable by the End-User

Abstract

The main goal to extract knowledge in database is to help the user to give semantics of data and to optimize the information research. Unfortunately, this fundamental constraint is not taken into account by almost all the approaches for knowledge discovery. Indeed, these approaches generate a big number of rules that are not easily assimilated by the human brain. In this paper, we propose a new approach for Knowledge Discovery in Databases through the fusion of conceptual clustering, fuzzy logic, and formal concept analysis. While basing on the hierarchical structure offered by the lattices, we proceed to discover the Knowledge in a hierarchical way. Thus, according to the degree of detail required by the user, this approach proposes a level of knowledge and different views of this knowledge, so the user can easily exploit all knowledge generated. Moreover, this solution is extensible, the user is able to choose the fuzzy method of classification according to the domain of his data and his needs.