Un metodo dinamico per l'analisi dell'omogeneità non lineare

Abstract

Aim of this paper is to propose a new method for Adaptive Fuzzy Homogeneity Analysis. Van Rijckevorsel et al. (1987) define Fuzzy Homogeneity Analysis (FHA) as the Homogeneity analysis of non linear transformed data, where the transformation is performed using B-splines. The originality of the method consists of the inclusion of the knot location among the parameters to be defined and for the adaptivity of the process of optimization of the loss function. An algorithm to perform the proposed method is described. A comparison with the results of an exhaustive algorithm is reported to illustrate the performance of the proposed adaptive algorithm.