Menu
▾
▴
[Octave-cvsupdate] SF.net SVN: octave:[9082] trunk/octave-forge/main/fuzzy-logic-toolkit/inst
|
From: <lm...@us...> - 2011-11-13 18:37:14
|
Revision: 9082
http://octave.svn.sourceforge.net/octave/?rev=9082&view=rev
Author: lmarkov
Date: 2011-11-13 18:37:05 +0000 (Sun, 13 Nov 2011)
Log Message:
-----------
A inst/heart_disease_demo_1.m
M inst/smf.m
A inst/heart_disease_demo_2.m
M inst/mamdani_tip_demo.m
M inst/gauss2mf.m
M inst/writefis.m
M inst/zmf.m
M inst/addvar.m
M inst/showrule.m
M inst/gbellmf.m
A inst/hamacher_product.m
A inst/algebraic_product.m
M inst/dsigmf.m
M inst/gensurf.m
A inst/einstein_product.m
M inst/sugeno_tip_demo.m
M inst/getfis.m
M inst/trimf.m
M inst/showfis.m
M inst/cubic_approx_demo.m
M inst/psigmf.m
D inst/heart_demo_1.m
D inst/heart_demo_2.m
A inst/drastic_product.m
M inst/evalfis.m
M inst/trapmf.m
A inst/bounded_difference.m
M inst/linear_tip_demo.m
M inst/newfis.m
M inst/pimf.m
A inst/hamacher_sum.m
A inst/algebraic_sum.m
A inst/investment_portfolio_demo.m
M inst/plotmf.m
A inst/einstein_sum.m
A inst/bounded_sum.m
M inst/sigmf.m
M inst/gaussmf.m
M inst/evalmf.m
M inst/sugeno_tip_calculator.fis
M inst/addmf.m
M inst/readfis.m
A inst/drastic_sum.m
A inst/investment_portfolio.fis
M inst/cubic_approximator.fis
M inst/addrule.m
Modified Paths:
--------------
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addmf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addrule.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addvar.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/cubic_approx_demo.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/cubic_approximator.fis
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/dsigmf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/evalfis.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/evalmf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gauss2mf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gaussmf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gbellmf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gensurf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/getfis.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/linear_tip_demo.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/mamdani_tip_demo.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/newfis.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/pimf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/plotmf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/psigmf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/readfis.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/showfis.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/showrule.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/sigmf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/smf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/sugeno_tip_calculator.fis
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/sugeno_tip_demo.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/trapmf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/trimf.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/writefis.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/zmf.m
Added Paths:
-----------
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/algebraic_product.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/algebraic_sum.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/bounded_difference.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/bounded_sum.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/drastic_product.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/drastic_sum.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/einstein_product.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/einstein_sum.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/hamacher_product.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/hamacher_sum.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/heart_disease_demo_1.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/heart_disease_demo_2.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/investment_portfolio.fis
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/investment_portfolio_demo.m
Removed Paths:
-------------
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/heart_demo_1.m
trunk/octave-forge/main/fuzzy-logic-toolkit/inst/heart_demo_2.m
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addmf.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addmf.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addmf.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -51,10 +51,9 @@
## them for FIS inputs or Mamdani-type FIS outputs has not yet been tested.
##
## @noindent
-## To run the demonstration code below, type @t{demo('addmf')} at the
-## Octave prompt. This demo creates two FIS input variables and associated
-## membership functions and then produces two figures showing the term
-## sets for the two FIS inputs.
+## To run the demonstration code, type @t{demo('addmf')} at the Octave prompt.
+## This demo creates two FIS input variables and associated membership functions
+## and then produces two figures showing the term sets for the two FIS inputs.
##
## @seealso{rmmf, setfis}
## @end deftypefn
@@ -65,7 +64,7 @@
## Filename: addmf.m
## Note: The demo code is based on an assignment written by
## Dr. Bruce Segee (University of Maine Dept. of ECE).
-## Last-Modified: 30 Aug 2011
+## Last-Modified: 28 Oct 2011
function fis = addmf (fis, in_or_out, var_index, mf_name, mf_type, mf_params)
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addrule.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addrule.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addrule.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -41,35 +41,50 @@
## connect == antecedent connective (1 == and; 2 == or)
## @end itemize
##
-## To express the hedge "not", prepend a minus sign to the membership function
-## index. ("Not" is the only hedge supported.) To omit an input or output, use
-## 0 for the membership function index. The consequent connective is always
-## "and".
+## To express:
+## @itemize @w
+## @item
+## "not" -- prepend a minus sign to the membership function index
+## @item
+## "somewhat" -- append ".05" to the membership function index
+## @item
+## "very" -- append ".20" to the membership function index
+## @item
+## "extremely" -- append ".30" to the membership function index
+## @item
+## "very very" -- append ".40" to the membership function index
+## @item
+## custom hedge -- append .xy, where x.y is the degree to which the membership
+## value should be raised, to the membership function index
+## @end itemize
##
+## To omit an input or output, use 0 for the membership function index.
+## The consequent connective is always "and".
+##
## @noindent
## For example, to express:
## @example
-## "If input_1 is mf_2 or input_3 is not mf_1,
-## then output_2 is mf_1."
+## "If (input_1 is mf_2) or (input_3 is not mf_1) or (input_4 is very mf_1),
+## then (output_1 is mf_2) and (output_2 is mf_1^0.3)."
## @end example
##
## @noindent
## with weight 1, the corresponding row of @var{rule_matrix} would be:
## @example
-## [2 0 -1 0 1 1 2]
+## [2 0 -1 4.2 2 1.03 1 2]
## @end example
##
## @noindent
-## For a complete example that uses addrule, see heart_demo_1.m.
+## For a complete example that uses addrule, see heart_disease_demo_1.m.
##
-## @seealso{heart_demo_1, showrule}
+## @seealso{heart_disease_demo_1, showrule}
## @end deftypefn
## Author: L. Markowsky
## Keywords: fuzzy-logic-toolkit fuzzy rule
## Directory: fuzzy-logic-toolkit/inst/
## Filename: addrule.m
-## Last-Modified: 16 Jul 2011
+## Last-Modified: 11 Nov 2011
function fis = addrule (fis, rule_matrix)
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addvar.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addvar.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/addvar.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -38,8 +38,7 @@
## specify the lower and upper bounds of the variable's domain.
##
## @noindent
-## To run the demonstration code below, type @t{demo('addvar')} at the
-## Octave prompt.
+## To run the demonstration code, type @t{demo('addvar')} at the Octave prompt.
##
## @end deftypefn
@@ -47,7 +46,7 @@
## Keywords: fuzzy-logic-toolkit fuzzy variable
## Directory: fuzzy-logic-toolkit/inst/
## Filename: addvar.m
-## Last-Modified: 30 Aug 2011
+## Last-Modified: 28 Oct 2011
function fis = addvar (fis, in_or_out, var_name, var_range)
Added: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/algebraic_product.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/algebraic_product.m (rev 0)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/algebraic_product.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -0,0 +1,56 @@
+## Copyright (C) 2011 L. Markowsky <lm...@us...>
+##
+## This file is part of the fuzzy-logic-toolkit.
+##
+## The fuzzy-logic-toolkit is free software; you can redistribute it
+## and/or modify it under the terms of the GNU General Public License
+## as published by the Free Software Foundation; either version 3 of
+## the License, or (at your option) any later version.
+##
+## The fuzzy-logic-toolkit is distributed in the hope that it will be
+## useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+## of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+## General Public License for more details.
+##
+## You should have received a copy of the GNU General Public License
+## along with the fuzzy-logic-toolkit; see the file COPYING. If not,
+## see <http://www.gnu.org/licenses/>.
+
+## -*- texinfo -*-
+## @deftypefn {Function File} {@var{retval} =} algebraic_product (@var{x})
+## @deftypefnx {Function File} {@var{retval} =} algebraic_product (@var{x}, @var{y})
+##
+## Return the algebraic product of the input.
+## The algebraic product of two real scalars x and y is: x * y
+##
+## For one vector argument, apply the algebraic product to all of elements of
+## the vector. (The algebraic product is associative.) For one two-dimensional
+## matrix argument, return a vector of the algebraic product of each column.
+##
+## For two vectors or matrices of identical dimensions, or for one scalar and
+## one vector or matrix argument, return the pair-wise product.
+##
+## @seealso{algebraic_sum, bounded_difference, bounded_sum, drastic_product, drastic_sum, einstein_product, einstein_sum, hamacher_product, hamacher_sum}
+## @end deftypefn
+
+## Author: L. Markowsky
+## Keywords: fuzzy-logic-toolkit fuzzy algebraic_product
+## Directory: fuzzy-logic-toolkit/inst/
+## Filename: algebraic_product.m
+## Last-Modified: 12 Nov 2011
+
+function retval = algebraic_product (x, y = 0)
+ if (!(isreal (x) && isreal (y)))
+ puts ("Type 'help algebraic_product' for more information.\n");
+ error ("algebraic_product requires real scalar or matrix arguments\n");
+ elseif (nargin == 2 && ...
+ (isscalar (x) || isscalar (y) || isequal (size (x), size (y))))
+ retval = x .* y;
+ elseif (nargin == 1 && ndims (x) <= 2)
+ retval = prod (x);
+ else
+ puts ("Type 'help algebraic_product' for more information.\n");
+ error ("invalid arguments to function algebraic_product\n");
+ endif
+endfunction
+
Added: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/algebraic_sum.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/algebraic_sum.m (rev 0)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/algebraic_sum.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -0,0 +1,71 @@
+## Copyright (C) 2011 L. Markowsky <lm...@us...>
+##
+## This file is part of the fuzzy-logic-toolkit.
+##
+## The fuzzy-logic-toolkit is free software; you can redistribute it
+## and/or modify it under the terms of the GNU General Public License
+## as published by the Free Software Foundation; either version 3 of
+## the License, or (at your option) any later version.
+##
+## The fuzzy-logic-toolkit is distributed in the hope that it will be
+## useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+## of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+## General Public License for more details.
+##
+## You should have received a copy of the GNU General Public License
+## along with the fuzzy-logic-toolkit; see the file COPYING. If not,
+## see <http://www.gnu.org/licenses/>.
+
+## -*- texinfo -*-
+## @deftypefn {Function File} {@var{retval} =} algebraic_sum (@var{x, y})
+## @deftypefnx {Function File} {@var{retval} =} algebraic_sum (@var{x, y})
+##
+## Return the algebraic sum of the input.
+## The algebraic sum of two real scalars x and y is: x + y - x * y
+##
+## For one vector argument, apply the algebraic sum to all of elements of
+## the vector. (The algebraic sum is associative.) For one two-dimensional
+## matrix argument, return a vector of the algebraic sum of each column.
+##
+## For two vectors or matrices of identical dimensions, or for one scalar and
+## one vector or matrix argument, return the pair-wise algebraic sum.
+##
+## @seealso{algebraic_product, bounded_difference, bounded_sum, drastic_product, drastic_sum, einstein_product, einstein_sum, hamacher_product, hamacher_sum}
+## @end deftypefn
+
+## Author: L. Markowsky
+## Keywords: fuzzy-logic-toolkit fuzzy algebraic_sum
+## Directory: fuzzy-logic-toolkit/inst/
+## Filename: algebraic_sum.m
+## Last-Modified: 12 Nov 2011
+
+function retval = algebraic_sum (x, y = 0)
+ if (!(isreal (x) && isreal (y)))
+ puts ("Type 'help algebraic_sum' for more information.\n");
+ error ("algebraic_sum requires real scalar or matrix arguments\n");
+ elseif (nargin == 2 && ...
+ (isscalar (x) || isscalar (y) || isequal (size (x), size (y))))
+ retval = x .+ y .- x .* y;
+ elseif (nargin == 1 && isvector (x))
+ retval = algebraic_sum_of_vector (x);
+ elseif (nargin == 1 && ndims (x) == 2)
+ num_cols = columns (x);
+ retval = zeros (1, num_cols);
+ for i = 1 : num_cols
+ retval(i) = algebraic_sum_of_vector (x(:, i));
+ endfor
+ else
+ puts ("Type 'help algebraic_sum' for more information.\n");
+ error ("invalid arguments to function algebraic_sum\n");
+ endif
+endfunction
+
+function retval = algebraic_sum_of_vector (real_vector)
+ x = 0;
+ for i = 1 : length (real_vector)
+ y = real_vector(i);
+ x = x + y - x * y;
+ endfor
+ retval = x;
+endfunction
+
Added: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/bounded_difference.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/bounded_difference.m (rev 0)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/bounded_difference.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -0,0 +1,72 @@
+## Copyright (C) 2011 L. Markowsky <lm...@us...>
+##
+## This file is part of the fuzzy-logic-toolkit.
+##
+## The fuzzy-logic-toolkit is free software; you can redistribute it
+## and/or modify it under the terms of the GNU General Public License
+## as published by the Free Software Foundation; either version 3 of
+## the License, or (at your option) any later version.
+##
+## The fuzzy-logic-toolkit is distributed in the hope that it will be
+## useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+## of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+## General Public License for more details.
+##
+## You should have received a copy of the GNU General Public License
+## along with the fuzzy-logic-toolkit; see the file COPYING. If not,
+## see <http://www.gnu.org/licenses/>.
+
+## -*- texinfo -*-
+## @deftypefn {Function File} {@var{retval} =} bounded_difference (@var{x})
+## @deftypefnx {Function File} {@var{retval} =} bounded_difference (@var{x}, @var{y})
+##
+## Return the bounded difference of the input.
+## The bounded difference of two real scalars x and y is: max (0, x + y - 1)
+##
+## For one vector argument, apply the bounded difference to all of the elements
+## of the vector. (The bounded difference is associative.) For one
+## two-dimensional matrix argument, return a vector of the bounded difference
+## of each column.
+##
+## For two vectors or matrices of identical dimensions, or for one scalar and
+## one vector or matrix argument, return the pair-wise bounded difference.
+##
+## @seealso{algebraic_product, algebraic_sum, bounded_sum, drastic_product, drastic_sum, einstein_product, einstein_sum, hamacher_product, hamacher_sum}
+## @end deftypefn
+
+## Author: L. Markowsky
+## Keywords: fuzzy-logic-toolkit fuzzy bounded_difference
+## Directory: fuzzy-logic-toolkit/inst/
+## Filename: bounded_difference.m
+## Last-Modified: 12 Nov 2011
+
+function retval = bounded_difference (x, y = 0)
+ if (!(isreal (x) && isreal (y)))
+ puts ("Type 'help bounded_difference' for more information.\n");
+ error ("bounded_difference requires real scalar or matrix arguments\n");
+ elseif (nargin == 2 && ...
+ (isscalar (x) || isscalar (y) || isequal (size (x), size (y))))
+ retval = max (0, (x .+ y - 1));
+ elseif (nargin == 1 && isvector (x))
+ retval = bounded_difference_of_vector (x);
+ elseif (nargin == 1 && ndims (x) == 2)
+ num_cols = columns (x);
+ retval = zeros (1, num_cols);
+ for i = 1 : num_cols
+ retval(i) = bounded_difference_of_vector (x(:, i));
+ endfor
+ else
+ puts ("Type 'help bounded_difference' for more information.\n");
+ error ("invalid arguments to function bounded_difference\n");
+ endif
+endfunction
+
+function retval = bounded_difference_of_vector (real_vector)
+ x = 1;
+ for i = 1 : length (real_vector)
+ y = real_vector(i);
+ x = max (0, (x + y - 1));
+ endfor
+ retval = x;
+endfunction
+
Added: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/bounded_sum.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/bounded_sum.m (rev 0)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/bounded_sum.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -0,0 +1,71 @@
+## Copyright (C) 2011 L. Markowsky <lm...@us...>
+##
+## This file is part of the fuzzy-logic-toolkit.
+##
+## The fuzzy-logic-toolkit is free software; you can redistribute it
+## and/or modify it under the terms of the GNU General Public License
+## as published by the Free Software Foundation; either version 3 of
+## the License, or (at your option) any later version.
+##
+## The fuzzy-logic-toolkit is distributed in the hope that it will be
+## useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+## of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+## General Public License for more details.
+##
+## You should have received a copy of the GNU General Public License
+## along with the fuzzy-logic-toolkit; see the file COPYING. If not,
+## see <http://www.gnu.org/licenses/>.
+
+## -*- texinfo -*-
+## @deftypefn {Function File} {@var{retval} =} bounded_sum (@var{x})
+## @deftypefnx {Function File} {@var{retval} =} bounded_sum (@var{x}, @var{y})
+##
+## Return the bounded sum of the input.
+## The bounded sum of two real scalars x and y is: min (1, x + y)
+##
+## For one vector argument, apply the bounded sum to all of elements of
+## the vector. (The bounded sum is associative.) For one two-dimensional
+## matrix argument, return a vector of the bounded sum of each column.
+##
+## For two vectors or matrices of identical dimensions, or for one scalar and
+## one vector or matrix argument, return the pair-wise bounded sum.
+##
+## @seealso{algebraic_product, algebraic_sum, bounded_difference, drastic_product, drastic_sum, einstein_product, einstein_sum, hamacher_product, hamacher_sum}
+## @end deftypefn
+
+## Author: L. Markowsky
+## Keywords: fuzzy-logic-toolkit fuzzy bounded_sum
+## Directory: fuzzy-logic-toolkit/inst/
+## Filename: bounded_sum.m
+## Last-Modified: 12 Nov 2011
+
+function retval = bounded_sum (x, y = 0)
+ if (!(isreal (x) && isreal (y)))
+ puts ("Type 'help bounded_sum' for more information.\n");
+ error ("bounded_sum requires real scalar or matrix arguments\n");
+ elseif (nargin == 2 && ...
+ (isscalar (x) || isscalar (y) || isequal (size (x), size (y))))
+ retval = min (1, (x .+ y));
+ elseif (nargin == 1 && isvector (x))
+ retval = bounded_sum_of_vector (x);
+ elseif (nargin == 1 && ndims (x) == 2)
+ num_cols = columns (x);
+ retval = zeros (1, num_cols);
+ for i = 1 : num_cols
+ retval(i) = bounded_sum_of_vector (x(:, i));
+ endfor
+ else
+ puts ("Type 'help bounded_sum' for more information.\n");
+ error ("invalid arguments to function bounded_sum\n");
+ endif
+endfunction
+
+function retval = bounded_sum_of_vector (real_vector)
+ x = 0;
+ for i = 1 : length (real_vector)
+ y = real_vector(i);
+ x = min (1, (x + y));
+ endfor
+ retval = x;
+endfunction
+
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/cubic_approx_demo.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/cubic_approx_demo.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/cubic_approx_demo.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -20,8 +20,7 @@
## @deftypefn {Script File} {} cubic_approx_demo
##
## Demonstrate the use of the Octave Fuzzy Logic Toolkit to approximate a
-## non-linear function using a Sugeno-type FIS with linear output membership
-## functions.
+## non-linear function using a Sugeno-type FIS with linear output functions.
##
## The demo:
## @itemize @minus
@@ -30,23 +29,26 @@
## @item
## plots the input membership functions
## @item
-## plots the output as a function of the input
+## plots the (linear) output functions
+## @item
+## plots the FIS output as a function of the input
## @end itemize
##
-## @seealso{heart_demo_1, heart_demo_2, linear_tip_demo, mamdani_tip_demo, sugeno_tip_demo}
+## @seealso{heart_disease_demo_1, heart_disease_demo_2, investment_portfolio_demo, linear_tip_demo, mamdani_tip_demo, sugeno_tip_demo}
## @end deftypefn
## Author: L. Markowsky
## Keywords: fuzzy-logic-toolkit fuzzy tests demos
## Directory: fuzzy-logic-toolkit/inst
## Filename: cubic_approx_demo.m
-## Last-Modified: 27 Aug 2011
+## Last-Modified: 12 Nov 2011
## Read the FIS structure from a file.
fis = readfis ('cubic_approximator.fis');
-## Plot the input membership functions.
+## Plot the input membership functions and linear output functions.
plotmf (fis, 'input', 1);
+plotmf (fis, 'output', 1, -150, 150);
-## Plot the output y as a function of the input x.
+## Plot the FIS output y as a function of the input x.
gensurf (fis);
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/cubic_approximator.fis
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/cubic_approximator.fis 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/cubic_approximator.fis 2011-11-13 18:37:05 UTC (rev 9082)
@@ -29,7 +29,7 @@
[Output1]
Name='Approx-X-Cubed'
-Range=[-130 130]
+Range=[-5 5]
NumMFs=11
MF1 = 'Tangent-at-Neg-Five':'linear', [75 250]
MF2 = 'Tangent-at-Neg-Four':'linear', [48 128]
Added: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/drastic_product.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/drastic_product.m (rev 0)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/drastic_product.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -0,0 +1,107 @@
+## Copyright (C) 2011 L. Markowsky <lm...@us...>
+##
+## This file is part of the fuzzy-logic-toolkit.
+##
+## The fuzzy-logic-toolkit is free software; you can redistribute it
+## and/or modify it under the terms of the GNU General Public License
+## as published by the Free Software Foundation; either version 3 of
+## the License, or (at your option) any later version.
+##
+## The fuzzy-logic-toolkit is distributed in the hope that it will be
+## useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+## of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+## General Public License for more details.
+##
+## You should have received a copy of the GNU General Public License
+## along with the fuzzy-logic-toolkit; see the file COPYING. If not,
+## see <http://www.gnu.org/licenses/>.
+
+## -*- texinfo -*-
+## @deftypefn {Function File} {@var{retval} =} drastic_product (@var{x})
+## @deftypefnx {Function File} {@var{retval} =} drastic_product (@var{x}, @var{y})
+##
+## Return the drastic product of the input.
+## The drastic product of two real scalars x and y is:
+## @example
+## @group
+## min (x, y) if max (x, y) == 1
+## 0 otherwise
+## @end group
+## @end example
+##
+## For one vector argument, apply the drastic product to all of the elements
+## of the vector. (The drastic product is associative.) For one
+## two-dimensional matrix argument, return a vector of the drastic product
+## of each column.
+##
+## For two vectors or matrices of identical dimensions, or for one scalar and
+## one vector or matrix argument, return the pair-wise drastic product.
+##
+## @seealso{algebraic_product, algebraic_sum, bounded_difference, bounded_sum, drastic_sum, einstein_product, einstein_sum, hamacher_product, hamacher_sum}
+## @end deftypefn
+
+## Author: L. Markowsky
+## Keywords: fuzzy-logic-toolkit fuzzy drastic_product
+## Directory: fuzzy-logic-toolkit/inst/
+## Filename: drastic_product.m
+## Last-Modified: 12 Nov 2011
+
+function retval = drastic_product (x, y = 0)
+ if (nargin == 0 || nargin > 2 ||
+ !is_real_matrix (x) || !is_real_matrix (y))
+ argument_error
+
+ elseif (nargin == 1)
+ if (isvector (x))
+ retval = vector_arg (x);
+ elseif (ndims (x) == 2)
+ retval = matrix_arg (x);
+ else
+ argument_error;
+ endif
+
+ elseif (nargin == 2)
+ if (isequal (size (x), size (y)))
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (isscalar (x) && ismatrix (y))
+ x = x * ones (size (y));
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (ismatrix (x) && isscalar (y))
+ y = y * ones (size (x));
+ retval = arrayfun (@scalar_args, x, y);
+ else
+ argument_error;
+ endif
+ endif
+endfunction
+
+function retval = scalar_args (x, y)
+ if (max (x, y) == 1)
+ retval = min (x, y);
+ else
+ retval = 0;
+ endif
+endfunction
+
+function retval = vector_arg (x)
+ if (isempty (x))
+ retval = 1;
+ elseif (max (x) == 1)
+ retval = min (x);
+ else
+ retval = 0;
+ endif
+endfunction
+
+function retval = matrix_arg (x)
+ num_cols = columns (x);
+ retval = zeros (1, num_cols);
+ for i = 1 : num_cols
+ retval(i) = vector_arg (x(:, i));
+ endfor
+endfunction
+
+function argument_error
+ puts ("Type 'help drastic_product' for more information.\n");
+ error ("invalid arguments to function drastic_product\n");
+endfunction
Added: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/drastic_sum.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/drastic_sum.m (rev 0)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/drastic_sum.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -0,0 +1,107 @@
+## Copyright (C) 2011 L. Markowsky <lm...@us...>
+##
+## This file is part of the fuzzy-logic-toolkit.
+##
+## The fuzzy-logic-toolkit is free software; you can redistribute it
+## and/or modify it under the terms of the GNU General Public License
+## as published by the Free Software Foundation; either version 3 of
+## the License, or (at your option) any later version.
+##
+## The fuzzy-logic-toolkit is distributed in the hope that it will be
+## useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+## of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+## General Public License for more details.
+##
+## You should have received a copy of the GNU General Public License
+## along with the fuzzy-logic-toolkit; see the file COPYING. If not,
+## see <http://www.gnu.org/licenses/>.
+
+## -*- texinfo -*-
+## @deftypefn {Function File} {@var{retval} =} drastic_sum (@var{x})
+## @deftypefnx {Function File} {@var{retval} =} drastic_sum (@var{x}, @var{y})
+##
+## Return the drastic sum of the input.
+## The drastic sum of two real scalars x and y is:
+## @example
+## @group
+## max (x, y) if min (x, y) == 0
+## 1 otherwise
+## @end group
+## @end example
+##
+## For one vector argument, apply the drastic sum to all of the elements
+## of the vector. (The drastic sum is associative.) For one
+## two-dimensional matrix argument, return a vector of the drastic sum
+## of each column.
+##
+## For two vectors or matrices of identical dimensions, or for one scalar and
+## one vector or matrix argument, return the pair-wise drastic sum.
+##
+## @seealso{algebraic_product, algebraic_sum, bounded_difference, bounded_sum, drastic_product, einstein_product, einstein_sum, hamacher_product, hamacher_sum}
+## @end deftypefn
+
+## Author: L. Markowsky
+## Keywords: fuzzy-logic-toolkit fuzzy drastic_sum
+## Directory: fuzzy-logic-toolkit/inst/
+## Filename: drastic_sum.m
+## Last-Modified: 12 Nov 2011
+
+function retval = drastic_sum (x, y = 0)
+ if (nargin == 0 || nargin > 2 ||
+ !is_real_matrix (x) || !is_real_matrix (y))
+ argument_error
+
+ elseif (nargin == 1)
+ if (isvector (x))
+ retval = vector_arg (x);
+ elseif (ndims (x) == 2)
+ retval = matrix_arg (x);
+ else
+ argument_error;
+ endif
+
+ elseif (nargin == 2)
+ if (isequal (size (x), size (y)))
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (isscalar (x) && ismatrix (y))
+ x = x * ones (size (y));
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (ismatrix (x) && isscalar (y))
+ y = y * ones (size (x));
+ retval = arrayfun (@scalar_args, x, y);
+ else
+ argument_error;
+ endif
+ endif
+endfunction
+
+function retval = scalar_args (x, y)
+ if (min (x, y) == 0)
+ retval = max (x, y);
+ else
+ retval = 1;
+ endif
+endfunction
+
+function retval = vector_arg (x)
+ if (isempty (x))
+ retval = 0;
+ elseif (min (x) == 0)
+ retval = max (x);
+ else
+ retval = 1;
+ endif
+endfunction
+
+function retval = matrix_arg (x)
+ num_cols = columns (x);
+ retval = zeros (1, num_cols);
+ for i = 1 : num_cols
+ retval(i) = vector_arg (x(:, i));
+ endfor
+endfunction
+
+function argument_error
+ puts ("Type 'help drastic_sum' for more information.\n");
+ error ("invalid arguments to function drastic_sum\n");
+endfunction
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/dsigmf.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/dsigmf.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/dsigmf.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -59,8 +59,7 @@
## Here, the symbol ~ means "approximately equal".
##
## @noindent
-## To run the demonstration code below, type @t{demo('dsigmf')} at the
-## Octave prompt.
+## To run the demonstration code, type @t{demo('dsigmf')} at the Octave prompt.
##
## @seealso{gauss2mf, gaussmf, gbellmf, pimf, psigmf, sigmf, smf, trapmf, trimf, zmf}
## @end deftypefn
@@ -69,7 +68,7 @@
## Keywords: fuzzy-logic-toolkit fuzzy membership-function sigmoidal
## Directory: fuzzy-logic-toolkit/inst/
## Filename: dsigmf.m
-## Last-Modified: 7 Jun 2011
+## Last-Modified: 28 Oct 2011
function y = dsigmf (x, params)
Added: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/einstein_product.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/einstein_product.m (rev 0)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/einstein_product.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -0,0 +1,97 @@
+## Copyright (C) 2011 L. Markowsky <lm...@us...>
+##
+## This file is part of the fuzzy-logic-toolkit.
+##
+## The fuzzy-logic-toolkit is free software; you can redistribute it
+## and/or modify it under the terms of the GNU General Public License
+## as published by the Free Software Foundation; either version 3 of
+## the License, or (at your option) any later version.
+##
+## The fuzzy-logic-toolkit is distributed in the hope that it will be
+## useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+## of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+## General Public License for more details.
+##
+## You should have received a copy of the GNU General Public License
+## along with the fuzzy-logic-toolkit; see the file COPYING. If not,
+## see <http://www.gnu.org/licenses/>.
+
+## -*- texinfo -*-
+## @deftypefn {Function File} {@var{retval} =} einstein_product (@var{x})
+## @deftypefnx {Function File} {@var{retval} =} einstein_product (@var{x}, @var{y})
+##
+## Return the Einstein product of the input.
+## The Einstein product of two real scalars x and y is:
+## (x * y) / (2 - (x + y - x * y))
+##
+## For one vector argument, apply the Einstein product to all of the elements
+## of the vector. (The Einstein product is associative.) For one
+## two-dimensional matrix argument, return a vector of the Einstein product
+## of each column.
+##
+## For two vectors or matrices of identical dimensions, or for one scalar and
+## one vector or matrix argument, return the pair-wise Einstein product.
+##
+## @seealso{algebraic_product, algebraic_sum, bounded_difference, bounded_sum, drastic_product, drastic_sum, einstein_sum, hamacher_product, hamacher_sum}
+## @end deftypefn
+
+## Author: L. Markowsky
+## Keywords: fuzzy-logic-toolkit fuzzy einstein_product
+## Directory: fuzzy-logic-toolkit/inst/
+## Filename: einstein_product.m
+## Last-Modified: 12 Nov 2011
+
+function retval = einstein_product (x, y = 0)
+ if (nargin == 0 || nargin > 2 ||
+ !is_real_matrix (x) || !is_real_matrix (y))
+ argument_error
+
+ elseif (nargin == 1)
+ if (isvector (x))
+ retval = vector_arg (x);
+ elseif (ndims (x) == 2)
+ retval = matrix_arg (x);
+ else
+ argument_error;
+ endif
+
+ elseif (nargin == 2)
+ if (isequal (size (x), size (y)))
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (isscalar (x) && ismatrix (y))
+ x = x * ones (size (y));
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (ismatrix (x) && isscalar (y))
+ y = y * ones (size (x));
+ retval = arrayfun (@scalar_args, x, y);
+ else
+ argument_error;
+ endif
+ endif
+endfunction
+
+function retval = scalar_args (x, y)
+ retval = (x * y) / (2 - (x + y - x * y));
+endfunction
+
+function retval = vector_arg (real_vector)
+ x = 1;
+ for i = 1 : length (real_vector)
+ y = real_vector(i);
+ x = (x * y) / (2 - (x + y - x * y));
+ endfor
+ retval = x;
+endfunction
+
+function retval = matrix_arg (x)
+ num_cols = columns (x);
+ retval = zeros (1, num_cols);
+ for i = 1 : num_cols
+ retval(i) = vector_arg (x(:, i));
+ endfor
+endfunction
+
+function argument_error
+ puts ("Type 'help einstein_product' for more information.\n");
+ error ("invalid arguments to function einstein_product\n");
+endfunction
Added: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/einstein_sum.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/einstein_sum.m (rev 0)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/einstein_sum.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -0,0 +1,96 @@
+## Copyright (C) 2011 L. Markowsky <lm...@us...>
+##
+## This file is part of the fuzzy-logic-toolkit.
+##
+## The fuzzy-logic-toolkit is free software; you can redistribute it
+## and/or modify it under the terms of the GNU General Public License
+## as published by the Free Software Foundation; either version 3 of
+## the License, or (at your option) any later version.
+##
+## The fuzzy-logic-toolkit is distributed in the hope that it will be
+## useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+## of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+## General Public License for more details.
+##
+## You should have received a copy of the GNU General Public License
+## along with the fuzzy-logic-toolkit; see the file COPYING. If not,
+## see <http://www.gnu.org/licenses/>.
+
+## -*- texinfo -*-
+## @deftypefn {Function File} {@var{retval} =} einstein_sum (@var{x})
+## @deftypefnx {Function File} {@var{retval} =} einstein_sum (@var{x}, @var{y})
+##
+## Return the Einstein sum of the input.
+## The Einstein sum of two real scalars x and y is: (x + y) / (1 + x * y)
+##
+## For one vector argument, apply the Einstein sum to all of the elements
+## of the vector. (The Einstein sum is associative.) For one
+## two-dimensional matrix argument, return a vector of the Einstein sum
+## of each column.
+##
+## For two vectors or matrices of identical dimensions, or for one scalar and
+## one vector or matrix argument, return the pair-wise Einstein sum.
+##
+## @seealso{algebraic_product, algebraic_sum, bounded_difference, bounded_sum, drastic_product, drastic_sum, einstein_product, hamacher_product, hamacher_sum}
+## @end deftypefn
+
+## Author: L. Markowsky
+## Keywords: fuzzy-logic-toolkit fuzzy einstein_sum
+## Directory: fuzzy-logic-toolkit/inst/
+## Filename: einstein_sum.m
+## Last-Modified: 12 Nov 2011
+
+function retval = einstein_sum (x, y = 0)
+ if (nargin == 0 || nargin > 2 ||
+ !is_real_matrix (x) || !is_real_matrix (y))
+ argument_error
+
+ elseif (nargin == 1)
+ if (isvector (x))
+ retval = vector_arg (x);
+ elseif (ndims (x) == 2)
+ retval = matrix_arg (x);
+ else
+ argument_error;
+ endif
+
+ elseif (nargin == 2)
+ if (isequal (size (x), size (y)))
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (isscalar (x) && ismatrix (y))
+ x = x * ones (size (y));
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (ismatrix (x) && isscalar (y))
+ y = y * ones (size (x));
+ retval = arrayfun (@scalar_args, x, y);
+ else
+ argument_error;
+ endif
+ endif
+endfunction
+
+function retval = scalar_args (x, y)
+ retval = (x + y) / (1 + x * y);
+endfunction
+
+function retval = vector_arg (real_vector)
+ x = 0;
+ for i = 1 : length (real_vector)
+ y = real_vector(i);
+ x = (x + y) / (1 + x * y);
+ endfor
+ retval = x;
+endfunction
+
+function retval = matrix_arg (x)
+ num_cols = columns (x);
+ retval = zeros (1, num_cols);
+ for i = 1 : num_cols
+ retval(i) = vector_arg (x(:, i));
+ endfor
+endfunction
+
+function argument_error
+ puts ("Type 'help einstein_sum' for more information.\n");
+ error ("invalid arguments to function einstein_sum\n");
+endfunction
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/evalfis.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/evalfis.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/evalfis.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -90,7 +90,45 @@
## @end example
##
## @noindent
+## Evaluation of hedges and "not":
##
+## Each element of each FIS rule antecedent and consequent indicates the
+## corresponding membership function, hedge, and whether or not "not" should
+## be applied to the result. The index of the membership function to be used is
+## given by the positive whole number portion of the antecedent/consequent
+## vector entry, the hedge is given by the fractional portion (if any), and
+## "not" is indicated by a minus sign. A "0" as the integer portion in any
+## position in the rule indicates that the corresponding FIS input or output
+## variable is omitted from the rule.
+##
+## For custom hedges and the four built-in hedges "somewhat," "very,"
+## "extremely," and "very very," the membership function value (without the
+## hedge or "not") is raised to the power corresponding to the hedge. All
+## hedges are rounded to 2 digits.
+##
+## For example, if "mu(x)" denotes the matching degree of the input to the
+## corresponding membership function without a hedge or "not," then the final
+## matching degree recorded in @var{rule_input} will be computed by applying
+## the hedge and "not" in two steps. First, the hedge is applied:
+##
+## @example
+## @group
+## (fraction == .05) <=> somewhat x <=> mu(x)^0.5 <=> sqrt(mu(x))
+## (fraction == .20) <=> very x <=> mu(x)^2 <=> sqr(mu(x))
+## (fraction == .30) <=> extremely x <=> mu(x)^3 <=> cube(mu(x))
+## (fraction == .40) <=> very very x <=> mu(x)^4
+## (fraction == .dd) <=> <custom hedge> x <=> mu(x)^(dd/10)
+## @end group
+## @end example
+##
+## After applying the appropriate hedge, "not" is calculated by:
+## @example
+## minus sign present <=> not x <=> 1 - mu(x)
+## minus sign and hedge present <=> not <hedge> x <=> 1 - mu(x)^(dd/10)
+## @end example
+##
+## Hedges and "not" in the consequent are handled similarly.
+##
## @noindent
## The intermediate result @var{rule_output}:
##
@@ -172,15 +210,17 @@
## @noindent
## Examples:
##
-## Six examples of using evalfis are shown in:
+## Seven examples of using evalfis are shown in:
## @itemize @bullet
## @item
## cubic_approx_demo.m
## @item
-## heart_demo_1.m
+## heart_disease_demo_1.m
## @item
-## heart_demo_2.m
+## heart_disease_demo_2.m
## @item
+## investment_portfolio_demo.m
+## @item
## linear_tip_demo.m
## @item
## mamdani_tip_demo.m
@@ -188,17 +228,17 @@
## sugeno_tip_demo.m
## @end itemize
##
-## @seealso{cubic_approx_demo, heart_demo_1, heart_demo_2, linear_tip_demo, mamdani_tip_demo, sugeno_tip_demo}
+## @seealso{cubic_approx_demo, heart_disease_demo_1, heart_disease_demo_2, investment_portfolio_demo, linear_tip_demo, mamdani_tip_demo, sugeno_tip_demo}
## @end deftypefn
## Author: L. Markowsky
## Keywords: fuzzy-logic-toolkit fuzzy fuzzy-inference-system fis
## Directory: fuzzy-logic-toolkit/inst/
## Filename: evalfis.m
-## Last-Modified: 16 Jul 2011
+## Last-Modified: 12 Nov 2011
function [output, rule_input, rule_output, fuzzy_output] = ...
- evalfis (user_input, fis, num_points=101)
+ evalfis (user_input, fis, num_points = 101)
## If evalfis was called with an incorrect number of arguments, or the
## arguments do not have the correct type, print an error message and halt.
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/evalmf.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/evalmf.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/evalmf.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -18,10 +18,15 @@
## -*- texinfo -*-
## @deftypefn {Function File} {@var{y} =} evalmf (@var{x}, @var{param}, @var{mf_type})
+## @deftypefnx {Function File} {@var{y} =} evalmf (@var{x}, @var{param}, @var{mf_type}, @var{hedge})
+## @deftypefnx {Function File} {@var{y} =} evalmf (@var{x}, @var{param}, @var{mf_type}, @var{hedge}, @var{not_flag})
## @deftypefnx {Function File} {@var{y} =} evalmf (@var{[x1 x2 ... xn]}, @var{[param1 ... ]}, @var{mf_type})
+## @deftypefnx {Function File} {@var{y} =} evalmf (@var{[x1 x2 ... xn]}, @var{[param1 ... ]}, @var{mf_type}, @var{hedge})
+## @deftypefnx {Function File} {@var{y} =} evalmf (@var{[x1 x2 ... xn]}, @var{[param1 ... ]}, @var{mf_type}, @var{hedge}, @var{not_flag})
##
-## For a given domain, set of parameters, and membership function type,
-## return the corresponding y-values for the membership function.
+## For a given domain, set of parameters, membership function type, and
+## optional hedge and not_flag, return the corresponding y-values for the
+## membership function.
##
## The argument @var{x} must be a real number or a non-empty list of strictly
## increasing real numbers, @var{param} must be a valid parameter or a vector
@@ -29,38 +34,61 @@
## corresponding to a membership function type. Evalmf handles both built-in and
## custom membership functions.
##
+## For custom hedges and the four built-in hedges "somewhat", "very",
+## "extremely", and "very very", raise the membership function values to
+## the power corresponding to the hedge.
+##
+## @example
+## @group
+## (fraction == .05) <=> somewhat x <=> mu(x)^0.5 <=> sqrt(mu(x))
+## (fraction == .20) <=> very x <=> mu(x)^2 <=> sqr(mu(x))
+## (fraction == .30) <=> extremely x <=> mu(x)^3 <=> cube(mu(x))
+## (fraction == .40) <=> very very x <=> mu(x)^4
+## (fraction == .dd) <=> <custom hedge> x <=> mu(x)^(dd/10)
+## @end group
+## @end example
+##
+## The @var{not_flag} negates the membership function using:
+## @example
+## mu(not(x)) = 1 - mu(x)
+## @end example
+##
## @noindent
-## To run the demonstration below, type @t{demo('evalmf')} at the Octave
-## prompt.
-##
+## To run the demonstration code, type @t{demo('evalmf')} at the Octave prompt.
## @end deftypefn
## Author: L. Markowsky
## Keywords: fuzzy-logic-toolkit fuzzy membership-function evaluate
## Directory: fuzzy-logic-toolkit/inst/
## Filename: evalmf.m
-## Last-Modified: 16 Jul 2011
+## Last-Modified: 13 Nov 2011
-function y = evalmf (x, params, mf_type)
+function y = evalmf (x, params, mf_type, hedge = 0, not_flag = false)
- ## If the caller did not supply 3 argument values with the correct types,
+ ## If the caller did not supply 3 - 5 argument values with the correct types,
## print an error message and halt.
- if (nargin != 3)
+ if ((nargin < 3) || (nargin > 5))
puts ("Type 'help evalmf' for more information.\n");
- error ("evalmf requires 3 arguments\n");
+ error ("evalmf requires between 3 and 5 arguments\n");
elseif (!is_domain (x))
puts ("Type 'help evalmf' for more information.\n");
error ("evalmf's first argument must be a valid domain\n");
elseif (!is_string (mf_type))
puts ("Type 'help evalmf' for more information.\n");
- error ("evalmf's third argument to evalmf must be a string\n");
+ error ("evalmf's third argument must be a string\n");
+ elseif (!is_real (hedge))
+ puts ("Type 'help evalmf' for more information.\n");
+ error ("evalmf's fourth argument must be a real number\n");
+ elseif (!isbool (not_flag))
+ puts ("Type 'help evalmf' for more information.\n");
+ error ("evalmf's fifth argument must be a Boolean\n");
endif
## Calculate and return the y values of the membership function on the
## domain x.
- y = evalmf_private (x, params, mf_type);
+ y = evalmf_private (x, params, mf_type, hedge, not_flag);
endfunction
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gauss2mf.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gauss2mf.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gauss2mf.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -58,8 +58,7 @@
## than 1).
##
## @noindent
-## To run the demonstration code below, type @t{demo('gauss2mf')} at the
-## Octave prompt.
+## To run the demonstration code, type @t{demo('gauss2mf')} at the Octave prompt.
##
## @seealso{dsigmf, gaussmf, gbellmf, pimf, psigmf, sigmf, smf, trapmf, trimf, zmf}
## @end deftypefn
@@ -68,7 +67,7 @@
## Keywords: fuzzy-logic-toolkit fuzzy membership-function gaussian
## Directory: fuzzy-logic-toolkit/inst/
## Filename: gauss2mf.m
-## Last-Modified: 7 Jun 2011
+## Last-Modified: 28 Oct 2011
function y = gauss2mf (x, params)
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gaussmf.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gaussmf.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gaussmf.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -54,8 +54,7 @@
## @end itemize
##
## @noindent
-## To run the demonstration code below, type @t{demo('gaussmf')} at the
-## Octave prompt.
+## To run the demonstration code, type @t{demo('gaussmf')} at the Octave prompt.
##
## @seealso{dsigmf, gauss2mf, gbellmf, pimf, psigmf, sigmf, smf, trapmf, trimf, zmf}
## @end deftypefn
@@ -64,7 +63,7 @@
## Keywords: fuzzy-logic-toolkit fuzzy membership-function gaussian
## Directory: fuzzy-logic-toolkit/inst/
## Filename: gaussmf.m
-## Last-Modified: 20 Jun 2011
+## Last-Modified: 28 Oct 2011
function y = gaussmf (x, params)
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gbellmf.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gbellmf.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gbellmf.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -58,8 +58,7 @@
## differentiable and is symmetric about the line x = c.
##
## @noindent
-## To run the demonstration code below, type @t{demo('gbellmf')} at the
-## Octave prompt.
+## To run the demonstration code, type @t{demo('gbellmf')} at the Octave prompt.
##
## @seealso{dsigmf, gauss2mf, gaussmf, pimf, psigmf, sigmf, smf, trapmf, trimf, zmf}
## @end deftypefn
@@ -68,7 +67,7 @@
## Keywords: fuzzy-logic-toolkit fuzzy membership-function bell-shaped bell
## Directory: fuzzy-logic-toolkit/inst/
## Filename: gbellmf.m
-## Last-Modified: 7 Jun 2011
+## Last-Modified: 28 Oct 2011
function y = gbellmf (x, params)
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gensurf.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gensurf.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/gensurf.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -57,10 +57,12 @@
## @item
## cubic_approx_demo.m
## @item
-## heart_demo_1.m
+## heart_disease_demo_1.m
## @item
-## heart_demo_2.m
+## heart_disease_demo_2.m
## @item
+## investment_portfolio_demo.m
+## @item
## linear_tip_demo.m
## @item
## mamdani_tip_demo.m
@@ -72,17 +74,17 @@
## The form of gensurf that suppresses plotting (the final form above) is not yet
## implemented.
##
-## @seealso{cubic_approx_demo, heart_demo_1, heart_demo_2, linear_tip_demo, mamdani_tip_demo, sugeno_tip_demo, plotmf}
+## @seealso{cubic_approx_demo, heart_disease_demo_1, heart_disease_demo_2, investment_portfolio_demo, linear_tip_demo, mamdani_tip_demo, sugeno_tip_demo, plotmf}
## @end deftypefn
## Author: L. Markowsky
## Keywords: fuzzy-logic-toolkit fuzzy fuzzy-inference-system fis plot
## Directory: fuzzy-logic-toolkit/inst/
## Filename: gensurf.m
-## Last-Modified: 30 Aug 2011
+## Last-Modified: 11 Nov 2011
-function [x, y, z] = gensurf (fis, input_axes=[1 2], output_axis=1, ...
- grids=[15 15], ref_input=[], num_points=101)
+function [x, y, z] = gensurf (fis, input_axes = [1 2], output_axis = 1, ...
+ grids = [15 15], ref_input = [], num_points = 101)
## If gensurf was called with an incorrect number of arguments, or the
## arguments do not have the correct type, print an error message and halt.
Modified: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/getfis.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/getfis.m 2011-11-13 18:30:38 UTC (rev 9081)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/getfis.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -93,12 +93,12 @@
## Keywords: fuzzy-logic-toolkit fuzzy fuzzy-inference-system fis
## Directory: fuzzy-logic-toolkit/inst/
## Filename: getfis.m
-## Last-Modified: 31 Aug 2011
+## Last-Modified: 31 Oct 2011
##------------------------------------------------------------------------------
-function retval = getfis (fis, arg2='dummy', arg3='dummy', arg4='dummy', ...
- arg5='dummy', arg6='dummy')
+function retval = getfis (fis, arg2 = 'dummy', arg3 = 'dummy', ...
+ arg4 = 'dummy', arg5 = 'dummy', arg6 = 'dummy')
switch (nargin)
case 1 retval = getfis_one_arg (fis);
Added: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/hamacher_product.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/hamacher_product.m (rev 0)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/hamacher_product.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -0,0 +1,101 @@
+## Copyright (C) 2011 L. Markowsky <lm...@us...>
+##
+## This file is part of the fuzzy-logic-toolkit.
+##
+## The fuzzy-logic-toolkit is free software; you can redistribute it
+## and/or modify it under the terms of the GNU General Public License
+## as published by the Free Software Foundation; either version 3 of
+## the License, or (at your option) any later version.
+##
+## The fuzzy-logic-toolkit is distributed in the hope that it will be
+## useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+## of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+## General Public License for more details.
+##
+## You should have received a copy of the GNU General Public License
+## along with the fuzzy-logic-toolkit; see the file COPYING. If not,
+## see <http://www.gnu.org/licenses/>.
+
+## -*- texinfo -*-
+## @deftypefn {Function File} {@var{retval} =} hamacher_product (@var{x})
+## @deftypefnx {Function File} {@var{retval} =} hamacher_product (@var{x}, @var{y})
+##
+## Return the Hamacher product of the input.
+## The Hamacher product of two real scalars x and y is:
+## (x * y) / (x + y - x * y)
+##
+## For one vector argument, apply the Hamacher product to all of the elements
+## of the vector. (The Hamacher product is associative.) For one
+## two-dimensional matrix argument, return a vector of the Hamacher product
+## of each column.
+##
+## For two vectors or matrices of identical dimensions, or for one scalar and
+## one vector or matrix argument, return the pair-wise Hamacher product.
+##
+## @seealso{algebraic_product, algebraic_sum, bounded_difference, bounded_sum, drastic_product, drastic_sum, einstein_product, einstein_sum, hamacher_sum}
+## @end deftypefn
+
+## Author: L. Markowsky
+## Keywords: fuzzy-logic-toolkit fuzzy hamacher_product
+## Directory: fuzzy-logic-toolkit/inst/
+## Filename: hamacher_product.m
+## Last-Modified: 12 Nov 2011
+
+function retval = hamacher_product (x, y = 0)
+ if (nargin == 0 || nargin > 2 ||
+ !is_real_matrix (x) || !is_real_matrix (y))
+ argument_error
+
+ elseif (nargin == 1)
+ if (isvector (x))
+ retval = vector_arg (x);
+ elseif (ndims (x) == 2)
+ retval = matrix_arg (x);
+ else
+ argument_error;
+ endif
+
+ elseif (nargin == 2)
+ if (isequal (size (x), size (y)))
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (isscalar (x) && ismatrix (y))
+ x = x * ones (size (y));
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (ismatrix (x) && isscalar (y))
+ y = y * ones (size (x));
+ retval = arrayfun (@scalar_args, x, y);
+ else
+ argument_error;
+ endif
+ endif
+endfunction
+
+function retval = scalar_args (x, y)
+ retval = (x * y) / (x + y - x * y);
+endfunction
+
+function retval = vector_arg (real_vector)
+ x = 1;
+ for i = 1 : length (real_vector)
+ y = real_vector(i);
+ if (x == 0 && y == 0)
+ x = 0;
+ else
+ x = (x * y) / (x + y - x * y);
+ endif
+ endfor
+ retval = x;
+endfunction
+
+function retval = matrix_arg (x)
+ num_cols = columns (x);
+ retval = zeros (1, num_cols);
+ for i = 1 : num_cols
+ retval(i) = vector_arg (x(:, i));
+ endfor
+endfunction
+
+function argument_error
+ puts ("Type 'help hamacher_product' for more information.\n");
+ error ("invalid arguments to function hamacher_product\n");
+endfunction
Added: trunk/octave-forge/main/fuzzy-logic-toolkit/inst/hamacher_sum.m
===================================================================
--- trunk/octave-forge/main/fuzzy-logic-toolkit/inst/hamacher_sum.m (rev 0)
+++ trunk/octave-forge/main/fuzzy-logic-toolkit/inst/hamacher_sum.m 2011-11-13 18:37:05 UTC (rev 9082)
@@ -0,0 +1,101 @@
+## Copyright (C) 2011 L. Markowsky <lm...@us...>
+##
+## This file is part of the fuzzy-logic-toolkit.
+##
+## The fuzzy-logic-toolkit is free software; you can redistribute it
+## and/or modify it under the terms of the GNU General Public License
+## as published by the Free Software Foundation; either version 3 of
+## the License, or (at your option) any later version.
+##
+## The fuzzy-logic-toolkit is distributed in the hope that it will be
+## useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+## of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+## General Public License for more details.
+##
+## You should have received a copy of the GNU General Public License
+## along with the fuzzy-logic-toolkit; see the file COPYING. If not,
+## see <http://www.gnu.org/licenses/>.
+
+## -*- texinfo -*-
+## @deftypefn {Function File} {@var{retval} =} hamacher_sum (@var{x})
+## @deftypefnx {Function File} {@var{retval} =} hamacher_sum (@var{x}, @var{y})
+##
+## Return the Hamacher sum of the input.
+## The Hamacher sum of two real scalars x and y is:
+## (x + y - 2 * x * y) / (1 - x * y)
+##
+## For one vector argument, apply the Hamacher sum to all of the elements
+## of the vector. (The Hamacher sum is associative.) For one
+## two-dimensional matrix argument, return a vector of the Hamacher sum
+## of each column.
+##
+## For two vectors or matrices of identical dimensions, or for one scalar and
+## one vector or matrix argument, return the pair-wise Hamacher sum.
+##
+## @seealso{algebraic_product, algebraic_sum, bounded_difference, bounded_sum, drastic_product, drastic_sum, einstein_product, einstein_sum, hamacher_product}
+## @end deftypefn
+
+## Author: L. Markowsky
+## Keywords: fuzzy-logic-toolkit fuzzy hamacher_sum
+## Directory: fuzzy-logic-toolkit/inst/
+## Filename: hamacher_sum.m
+## Last-Modified: 12 Nov 2011
+
+function retval = hamacher_sum (x, y = 0)
+ if (nargin == 0 || nargin > 2 ||
+ !is_real_matrix (x) || !is_real_matrix (y))
+ argument_error
+
+ elseif (nargin == 1)
+ if (isvector (x))
+ retval = vector_arg (x);
+ elseif (ndims (x) == 2)
+ retval = matrix_arg (x);
+ else
+ argument_error;
+ endif
+
+ elseif (nargin == 2)
+ if (isequal (size (x), size (y)))
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (isscalar (x) && ismatrix (y))
+ x = x * ones (size (y));
+ retval = arrayfun (@scalar_args, x, y);
+ elseif (ismatrix (x) && isscalar (y))
+ y = y * ones (size (x));
+ retval = arrayfun (@scalar_args, x, y);
+ else
+ argument_error;
+ endif
+ endif
+endfunction
+
+function retval = scalar_args (x, y)
+ retval = (x + y - 2 * x * y) / (1 - x * y);
+endfunction
+
+function retval = vector_arg (real_vector)
+ x = 0;
+ fo...
[truncated message content] |
