
Accession Number : ADA185148
Title : Multidimensional Least Squares Fitting of Fuzzy Models.
Descriptive Note : Technical rept. Jun 85Jun 86,
Corporate Author : ARMY BALLISTIC RESEARCH LAB ABERDEEN PROVING GROUND MD
Personal Author(s) : Celmins, Aivars K R
PDF Url : ADA185148
Report Date : 10 Apr 1987
Pagination or Media Count : 54
Abstract : We describe a new method for the fitting of differentiable fuzzy model functions to crisp data. The model functions can be either scalar or multidimensional and need not be linear. The data are ncomponent vectors. An efficient algorithm is achieved by restricting the fuzzy model functions to sets which depend on fuzzy parameter vector and assuming that the vector has a conical membership function. A fuzzy model function, equated to zero, defines in the nspace a fuzzy hypersurface. Simple properties of such surfaces are established and a structure in the space of fuzzy manifolds is introduced by defining a discord and collocation between any two fuzzy manifolds. Using these concepts and the restriction to conical membership functions, we derive a simple spread propagation formula for arbitrary functions of fuzzy variables. The model fitting is done in a least squares sense by minimizing the squares of the deviations from one of the membership values of the fitted hypersurface at the observations. Under the outlined restriction, the problem can be reduced to an ordinary least squares formulation for which software is available.
Descriptors : *LEAST SQUARES METHOD, *MATHEMATICAL MODELS, *FITTING FUNCTIONS(MATHEMATICS), VARIABLES, ALGORITHMS, EFFICIENCY, PARAMETERS, CHARTS, CRATERS, SIZES(DIMENSIONS)
Subject Categories : Numerical Mathematics
Distribution Statement : APPROVED FOR PUBLIC RELEASE