Re: Genetic Algorithm

May wrote:
> I want to know how rank selection work in detail.
>
> And I have also read this linear function for rank selection.
>    
>      prob(rank) = q - (rank -1)^r
>
> where q = a user defined parameter ( q varies between 1/pop_size and
> 2/pop_size)
>
> This function returns the probability of an individual ranked in
> position rank
> (rank = 1 means the best individual, rank = pop_size the worst one) to
> be selected.
>
> e.g; pop_size=100 and q=0.015 then r=q/(pop_size-1) =0.00015151515
>
> and prob(1)=0.015
>     prob(2)=0.0148484848
>     :
>     prob(100)=0.00000000000000000051
>
>     I have got these probabilities and how can I use these
> probabilities to select chromosomes.
>     I also want to use this rank selection method in Evolutionary
> Planner/Navigator. Please suggest me.
>
> Thanks in advance.
>
> With Regards,
> May

I'v recently started to get into GA's. One of the selection methods I 
use is based on a probability density function which has form y=mx (i.e. 
straight line through origin).
Suppose the population is N, then the bottom left of the line will be at 
(0,0) and the top right will be at (N,x) where x is such that the area 
under the line (i.e. a triangle) is 1.
With a bit of maths and rearranging, I worked out that to choose a 
parent (p) based on the above scheme p=N*sqrt(rnd()) where rnd() is the 
usual uniform random number generator [0,1].
If you have things arranged so that individual 0 in your gene pool is 
the most fit, then simply do p=N*(1-sqrt(rnd()).
Hope that helps somehwat. Drawing the pdf on a piece of paper might help 
you to visualize things.
Cheers,
Emyr