An Interpretability-Accuracy Tradeoff in Learning Parameters of Intuitionistic Fuzzy Rule-Based Systems

Abstract

Parameter learning of Intuitionistic Fuzzy Rule-Based Systems (IFRBSs) is discussed and applied to medical diagnosis with intent of establishing a sound tradeoff between interpretability and accuracy. This study aims to improve the accuracy of IFRBSs without sacrificing its interpretability. This paper proposes an Objective Programming Method with an Interpretability-Accuracy tradeoff (OPMIA) to learn the parameters of IFRBSs by tuning the types of membership and non-membership functions and by adjusting adaptive factors and rule weights. The proposed method has been validated in the context of a medical diagnosis problem and a well-known publicly available auto-mpg data set. Furthermore, the proposed method is compared to Objective Programming Method not considering the interpretability (OPMNI) and Objective Programming Method based on Similarity Measure (OPMSM). The OPMIA helps achieve a sound a tradeoff between accuracy and interpretability and demonstrates its advantages over the other two methods.