A Genetic Algorithm Approach for Discovering Tuned Fuzzy Classification Rules with Intra- and Inter-Class Exceptions

Fuzzy rule-based systems (FRBSs) are proficient in dealing with cognitive uncertainties like vagueness and ambiguity imperative to real-world decision-making situations. Fuzzy classification rules (FCRs) based on fuzzy logic provide a framework for a flexible human-like reasoning involving linguistic variables. Appropriate membership functions (MFs) and suitable number of linguistic terms – according to actual distribution of data – are useful to strengthen the knowledge base (rule base [RB]+ data base [DB]) of FRBSs. An RB is expected to be accurate and interpretable, and a DB must contain appropriate fuzzy constructs (type of MFs, number of linguistic terms, and positioning of parameters of MFs) for the success of any FRBS. Moreover, it would be fascinating to know how a system behaves in some rare/exceptional circumstances and what action ought to be taken in situations where generalized rules cease to work. In this article, we propose a three-phased approach for discovery of FCRs augmented with intra- and inter-class exceptions. A pre-processing algorithm is suggested to tune DB in terms of the MFs and number of linguistic terms for each attribute of a data set in the first phase. The second phase discovers FCRs employing a genetic algorithm approach. Subsequently, intra- and inter-class exceptions are incorporated in the rules in the third phase. The proposed approach is illustrated on an example data set and further validated on six UCI machine learning repository data sets. The results show that the approach has been able to discover more accurate, interpretable, and interesting rules. The rules with intra-class exceptions tell us about the unique objects of a category, and rules with inter-class exceptions enable us to take a right decision in the exceptional circumstances.