Implementing adaptive vectorial centroid in Bayesian logistic regression for interval type-2 fuzzy sets

Abstract

A prior distributions in standard Bayesian knowledge are assumed to be classical probability distribution. It is required to representable those probabilities of fuzzy events based on Bayesian knowledge. Propelled by such real applications, in this research study, the theoretical foundations of Vectorial Centroid of interval type-2 fuzzy set with Bayesian logistic regression is introduced. As opposed of utilising type-1 fuzzy set, type-2 fuzzy set is recommended based on the involvement of uncertainty quantity. It additionally highlights the association of fuzzy sets with Bayesian logistic regression permits the use of fuzzy attributes by considering the need of human intuition in data analysis. It may be worth including here that this proposed methodology then applied for BUPA liver-disorder dataset and validated theoretically and empirically.