genetic
Class Genetic

java.lang.Object
  |
  +--genetic.Genetic

public class Genetic

extends java.lang.Object

Genetic Algorithm adapted by Murat Yildizoglu ([email protected]).
This algorithm is used by the class GenFirm developped by
Murat Yildizoglu. It is adapted from the SGA class developped by Stephen J. Hartley
(SGA is Available by anonymous ftp from ftp.aic.nrl.navy.mil in directory
/pub/galist/src/ga. )
The main difference with SGA are the organization as a package and the elimination
of Application part of the code in order to let GenFirm drive the algorithm.

(C) Murat Yildizoglu, 2000-2001 Universite Bordeaux IV University Montesquieu. Bordeaux France.

Permission to use, copy, modify, and distribute this
software and its documentation for NON-COMMERCIAL purposes
and without fee is hereby granted provided that this
copyright notice appears in all copies.
Last change: MY 17 Dec 98

Version:

1.0 17 Dec 1998

Author:

Murat Yildizoglu (mailto:[email protected])
* *************** Class: Genetic ************************
Contains the Genetic Algorithm use by GenFirm
Implements the methods for selection, crossover and mutation.
Randomly initialises the population.
Initialisation :
Genetic(Number_of_Chromosomes, Chromosome_Length, Crossover_type, Elitism, Crossover_Rate, Mutation_Rate);
************************************************************

Constructor Summary

Genetic(int pop0, int g0, int xover0, boolean elit0, double xoverrate0, double mutatrate0)

Method Summary

void	apply_elitism() Uses elitism or not conditioned by the do_elitism option chosen in the algorithm (cf. the constructor Genetic).
void	crossover()
int	Decode(int chr)
double	getFitness(int chr)
void	mutate()
void	newGeneration() newGeneration(): Generates new generation through selection, crossover and mutation.
void	selection() Selection: Creates new population through selection and tries to correct eventual degenerate Fitness point
void	SetFitness(int chr, double reward)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

Genetic

public Genetic(int pop0,
               int g0,
               int xover0,
               boolean elit0,
               double xoverrate0,
               double mutatrate0)

Method Detail

newGeneration

public void newGeneration()

newGeneration(): Generates new generation through selection, crossover and mutation. Allows external application to generate new generations on demand

Decode

public int Decode(int chr)

getFitness

public double getFitness(int chr)

SetFitness

public void SetFitness(int chr,
                       double reward)

selection

public void selection()

Selection: Creates new population through selection and tries to correct eventual degenerate Fitness point

crossover

public void crossover()

mutate

public void mutate()

apply_elitism

public void apply_elitism()

Uses elitism or not conditioned by the do_elitism option chosen in the algorithm (cf. the constructor Genetic).