Interpretability, Interpolation and Rule Weights in Linguistic Fuzzy Modeling

Linguistic fuzzy modeling that is usually implemented using Mamdani type of fuzzy systems suffers from the lack of accuracy and high computational costs. The paper shows that product-sum inference is an immediate remedy to both problems and that in this case it is sufficient to consider symmetrical output membership functions. For the identification of the latter, a numerically efficient method is suggested and arising interpretational aspects are discussed. Additionally, it is shown that various rule weighting schemes brought into the game to improve accuracy in linguistic modeling only increase computational overhead and can be reduced to the proposed model configuration with no loss of information.