FuAGGE: A Novel System to Automatically Generate Fuzzy Rule Based Learners

Abstract

Data in real world applications are in most cases linguistic information that are ambiguous and uncertain. Hence, such data should be handled by fuzzy set representation schemes to increase expressiveness and comprehensiveness. Moreover, mining these data requires ways to generate automatically useful information/knowledge through a set of fuzzy rules. This paper proposes a novel system called FuAGGE that stands for Fuzzy Automatic Generator Genetic Expression. The FuAGGE approach uses a grammar based   evolutionary technique. The grammar is expressed in the Backus Naur Form (BNF) and represents a fuzzy set covering method. The grammar is mapped into programs that are themselves implementations of fuzzy rule-based learners. Binary strings are used as inputs to the mapper along with the BNF grammar. These binary strings represent possible potential solutions resulting from the initializer component and the building blocks from Weka, a workbench that contains a collection of visualization tools and algorithms for data analysis and predictive modeling. This operation facilitates the induction process and makes induced programs shorter. FuAGGE has been tested on a benchmark of well-known datasets and experimental results prove the efficiency of the proposed method. It is shown through comparison that our method outperforms most recent and similar, manual techniques. The system is able to generate rule-based learners specialized to specific domains, for example medical or biological data. The generated learners will be able to produces efficient rule models. The produced rule models will achieves more accurate classification for the specific used domain.