SciLib.Neuro
Class Population

java.lang.Object
  SciLib.Neuro.Population

public class Population
extends java.lang.Object

This class defines a Population class that contains a genetic algorithm.

Field Summary

(package private) FunctionmD

f

Constructor Summary

Population()
default constructor

Method Summary

double	averageFitness() Compute the average fitness
void	computeTheBest() Generate theBestGen for all variables
void	crossover() Crossover selection: selects two parents that take part in the crossover.
void	elitist() Elitist function: If the best member of the current generation is worse then the best member of the previous generation, the latter one would replace the worst member of the current population
void	evaluate() evaluate the fitness
void	Evolution() Evolution process
void	genFunction(FunctionmD func) generate Problem Function
vector	getBestGen() get the best generation vector
matrix	getChromosome() get the chromosome matrix
vector	getFitness() get the fitness vector
double	getNumGen() get tne maximum number of generations
int	getNumVar() get tne number of variables
double	getpMutation() get the probability of mutation
int	getpopSize() get tne population size
double	getpxOver() get the probability of crossover
double	getTheBest() get theBest value
void	initialize() Initialize the population
void	mutate() Mutation: Random uniform mutation.
void	nextGeneration() generate next generation
void	read(java.lang.String fileName) Read a data file that contains information about a problem File format Number of variables : nVar Number of populations : nPop Maximum generations : maxGen probability of crossover : pxOver probability of mutation : pMutation Upper Limit : upper[i] Lower Limit : lower[i]
double	stddveFitness() Compute the standard deviation fitness

Methods inherited from class java.lang.Object

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

Field Detail

f

FunctionmD f

Constructor Detail

Population

public Population()

default constructor

Method Detail

getTheBest

public double getTheBest()

get theBest value

Returns:

A double value

getNumVar

public int getNumVar()

get tne number of variables

Returns:

An integer value

getpopSize

public int getpopSize()

get tne population size

Returns:

An integer value

getNumGen

public double getNumGen()

get tne maximum number of generations

Returns:

A double value

getpxOver

public double getpxOver()

get the probability of crossover

Returns:

A double value

getpMutation

public double getpMutation()

get the probability of mutation

Returns:

A double value

getChromosome

public matrix getChromosome()

get the chromosome matrix

Returns:

A matrix

getFitness

public vector getFitness()

get the fitness vector

Returns:

A vector

getBestGen

public vector getBestGen()

get the best generation vector

Returns:

A vector

genFunction

public void genFunction(FunctionmD func)

generate Problem Function

read

public void read(java.lang.String fileName)

Read a data file that contains information about a problem File format Number of variables : nVar Number of populations : nPop Maximum generations : maxGen probability of crossover : pxOver probability of mutation : pMutation Upper Limit : upper[i] Lower Limit : lower[i]

initialize

public void initialize()

Initialize the population

computeTheBest

public void computeTheBest()

Generate theBestGen for all variables

elitist

public void elitist()

Elitist function: If the best member of the current generation is worse then the best member of the previous generation, the latter one would replace the worst member of the current population

evaluate

public void evaluate()

evaluate the fitness

nextGeneration

public void nextGeneration()

generate next generation

crossover

public void crossover()

Crossover selection: selects two parents that take part in the crossover. Implements a single point crossover

mutate

public void mutate()

Mutation: Random uniform mutation. A variable selected for mutation is replaced by a random value between lower and upper bounds of this variable

Evolution

public void Evolution()

Evolution process

averageFitness

public double averageFitness()

Compute the average fitness

Returns:

a double value

stddveFitness

public double stddveFitness()

Compute the standard deviation fitness

Returns:

a double value