ECJ-INTEREST-L Archives

October 2011

ECJ-INTEREST-L@LISTSERV.GMU.EDU

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Matthias Malovits <[log in to unmask]>
Reply To:
ECJ Evolutionary Computation Toolkit <[log in to unmask]>
Date:
Wed, 26 Oct 2011 01:58:44 +0200
Content-Type:
text/plain
Parts/Attachments:
text/plain (32 lines)
Hello everyone!

Within my Computational Biology studies at the University of applied
siences Hagenberg (Austria), I am currently working on my bachelor
thesis. The topic is "Comparison of frameworks for genetic
algorithms".

I want to implement a simple sequential GA for a traveling salesman
problem. Based on my researches on ECJ, I came to the conclusion that
I will have to implement/create following parts:

- special integervector-individual, which has to contain unique genes
from 1 to its genomes length
- an special "Initializer"
- a "Problem" containing the evaluate() method, in which i evaluate
the length of the individuals path
- my own MutationBreedingPipeline and CrossoverBreedingPipeline, so no
illegal individuals are produced
- the parameter file

My questions are:
- Where should I put the distance Matrix? Should it be integrated in
the Problem class?
- Will i need anything else in addition to the implementation-ideas
above? (I know it is a stupid question, but ECJ is that huge, so i
feel totally lost about what already exists and what does not)

Thx for your time!

Best regards,
Matthias

ATOM RSS1 RSS2