runiformmutation.sci

基于SCILAB的The Genetic Algorithm Toolbox for SCILAB (GATS)工具箱

function [p] = RUniformMutation(parent,bounds,Ops)
// Non uniform mutation changes one of the parameters of the parent
// based on a non-uniform probability distribution.  This Gaussian
// distribution starts wide, and narrows to a point distribution as the
// current generation approaches the maximum generation.
//
// function [newSol] = multiNonUnifMutate(parent,bounds,Ops)
// parent  - the first parent ( [solution string function value] )
// bounds  - the bounds matrix for the solution space
// Ops     - Options for nonUnifMutate[gen #NonUnifMutations maxGen b]

cg=Ops(1); 				// Current Generation
mg=Ops(3);                              // Maximum Number of Generations
b=Ops(4);                               // Shape parameter
df = bounds(:,2) - bounds(:,1); 	// Range of the variables
numVar = size(parent,2)-1; 		// Get the number of variables
// Pick a variable to mutate randomly from 1 to number of vars
mPoint = round(rand * (numVar-1)) + 1;
md = round(rand); 			// Choose a direction of mutation
if md 					// Mutate towards upper bound
  newValue=parent(mPoint)+delta(cg,mg,bounds(mPoint,2)-parent(mPoint),b);
else 					// Mutate towards lower bound
  newValue=parent(mPoint)-delta(cg,mg,parent(mPoint)-bounds(mPoint,1),b);
end
parent(mPoint) = newValue; 		// Make the child