MATLAB: How can i use the ‘feval’ function in Binary Genetic Algorithm for evaluating a fitness function

Question

Respected Scholars,

I have used "cost=feval(fitnessfunction,argument)", where fitnessfunction is a function call and argument is a flexible Matrix. But,Optimizer GA have shown errors saying that "Argument must be a string or a function handle" and "Index exceeds matrix dimensions"

Code:

ff=@funcname; %ff is the function handle (handles the function 'funcname')
npar=1; %no.of optimization variables
maxit=100; %Maximum No.of Iterations
mincost=-9999999; %Minimum Cost
%GA Parameters
selection=0.5; %Fraction of Population Kept
popsize=input('enter pop size depending on the no.of possible 'a' values='); %Set Population Size
mutrate=0.15;
nbits=6;
Nt=nbits*npar;
keep=floor(selection*popsize); %Population Members that Survive
iga=0; %Generation Counter Initialized
pop=round(rand(popsize,Nt)); %Random population of 1s and 0s
par=gadecode(pop,0,10,nbits); %convert binary to continuous values (par handles the function 'gadecode')
cost=feval(ff,par); %Calculates population cost using ff

Example fitness function:

function f=funcname(a)
for a=1:10
f=(a*a)+a;
disp(f);
end
end

Thank You… In Advance

Answer 1

Your line

popsize=input('enter pop size depending on the no.of possible 'a' values='); %Set Population Size

needs to be

popsize = input('enter pop size depending on the no.of possible ''a'' values='); %Set Population Size