MultiObjective Genetic Algorithm

Joe Dumoulin joe at bresgal.com
Mon Feb 28 17:47:57 EST 2000


I'm not familiar with the paper you mention.  Does it require that you
have multiple objective functions or can you incorporate the mutiple
objectives into the representation.  If you can do the latter, you will
find it much less difficult to implement your ga.

If you must implement multiple objectives, if you can implement a
relationship between the two objectives, you could use the Deme classes to
implement your ga.  

Tell us more if you can..
Joe Dumoulin


-------------------------------------------------------------------------
A student asked the master: "Master, how may I find enlightenment?"  The
master replied with a question: "Have you finished your rice?"  The
student answered: "Yes, Master."  The master responded: "Then wash
your bowl!"

On Mon, 28 Feb 2000, Juan Andres Colmenares wrote:

> Hello.
> 
> I'm implementing the method described by Fonseca and Fleming in their
> paper:
> "Genetic Algorithm for Multiobjective Optimization: Formulation,
> Discussion and Generalization"
> 
> I think I have to make some changes to GAlib for handling Multiobjective
> Optimization Problems,
> but I think it is a lot of work. First fo all, I should add a virtual
> member function MOGAevaluates into the GAGenome class with its implicit
> changes. 
> 
> Do you have any suggestion? 
> Has it been done?
> 
> Thanks.
> 
> Juan Andres Colmenares
> University of Zulia
> Institute of Applied Calculus
> 





More information about the galib mailing list