lr_eval.m

来自「FISMAT accommodates different arithmetic」· M 代码 · 共 30 行

function mu_M = LR_eval(L,R,M,i)

% mu_M = LR_eval(L,R,M,i)
%
% Evaluation of the membership degree mu_M(x=i) for a given fuzzy number in LR-representation.
% M = [Xmin Xmax m n alpha beta] 
% LR-fuzzy-set: the functions F=L and F=R are a reference function iff
% F(0)=1, F(x)=F(-x), F(x) is nonincreasing on [0,+inf), F(x) = 1 for x \in [-1,+1] and 0
% outside; F(x)=max(0,1-abs(x)^p), p>=0; F(x)=e^-abs(x)^p, p>=0; F(x)=1/(1+abs(x)^p), p>=0.
% A fuzzy number M is said to be an L-R type flat fuzzy number iff
%          L((m-x)/alpha) for x<=m
% mu_A(x)= 1              for m<x<n
%          R((x-n)/beta)  for x>=n
% For m=n M is a L-R type fuzzy number. L is for left and R for right reference. For m=n, m is
% the mean value of M, alpha and beta are called left and right spreads, respectively. A fuzzy
% number is denoted as: M=(m,n,alpha,beta)_LR .
 
% FSTB - Fuzzy Systems Toolbox for MATLAB
% Copyright (c) 1993-1996 by Olaf Wolkenhauer
% Control Systems Centre at UMIST
% Manchester M60 1QD, UK

%       28-Apr-1995

%if (i <= M(3)), x= (M(3)-i)/M(5); mu_M=eval(L); end;
if (i <= M(3)), x= (M(3)-i)/M(5); mu_M=max(0,1-x); end;
if (i > M(3)) & (i < M(4)), mu_M=1; end;            % the flat part.
%if (i >= M(4)), x= (i-M(4))/M(6); mu_M=eval(R); end;
if (i >= M(4)), x= (i-M(4))/M(6); mu_M=max(0,1-x); end;