edu.udo.cs.yale.tools.math.optimization.ec.pso
Class PSOOptimization

java.lang.Object
  edu.udo.cs.yale.tools.math.optimization.ec.pso.PSOOptimization

All Implemented Interfaces:

Optimization

Direct Known Subclasses:

PSOSVMOptimization, PSOWeighting.PSOWeightingOptimization

public abstract class PSOOptimization
extends java.lang.Object
implements Optimization

This class performs the optimization of a value vector with a particle swarm approach.

Version:

$Id: PSOOptimization.java,v 1.8 2006/08/03 14:39:37 ingomierswa Exp $

Author:

Ingo Mierswa

Field Summary

private double	globalWeight
private double	inertiaWeight
private double	inertiaWeightDelta
private double	localWeight
private int	maxGen
private double	maxValue
private int	maxWithoutImprovement
private double	minValue
private Population	population
private RandomGenerator	random

Constructor Summary

PSOOptimization(int popSize, int individualSize, int maxGen, int maxWithoutImprovement, double inertiaWeight, double localWeight, double globalWeight, double minValue, double maxValue, boolean dynamicInertiaWeight, RandomGenerator random)
Creates a new PSO optimization with the given parameters.

Method Summary

protected Population	createInitialPopulation(int popSize, int individualSize) Creates the initial population.
private void	evaluate(Population population) Calculates the fitness for all individuals and gives the fitness values to the population.
abstract PerformanceVector	evaluateIndividual(double[] individual) Subclasses must implement this method to calculate the fitness of the given individual.
double	getBestFitnessEver() Returns the best fitness ever.
double	getBestFitnessInGeneration() Returns the best fitness in the current generation.
PerformanceVector	getBestPerformanceEver() Returns the best performance vector ever.
double[]	getBestValuesEver() Returns the best values ever.
int	getGeneration() Returns the current generation.
void	nextIteration() This method is invoked after each evaluation.
void	optimize() Invoke this method for optimization.
void	setMaxValue(double maxValue)
void	setMinValue(double minValue)

Methods inherited from class java.lang.Object

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

Field Detail

maxGen

private int maxGen

maxWithoutImprovement

private int maxWithoutImprovement

inertiaWeight

private double inertiaWeight

localWeight

private double localWeight

globalWeight

private double globalWeight

minValue

private double minValue

maxValue

private double maxValue

inertiaWeightDelta

private double inertiaWeightDelta

random

private RandomGenerator random

population

private Population population

Constructor Detail

PSOOptimization

public PSOOptimization(int popSize,
                       int individualSize,
                       int maxGen,
                       int maxWithoutImprovement,
                       double inertiaWeight,
                       double localWeight,
                       double globalWeight,
                       double minValue,
                       double maxValue,
                       boolean dynamicInertiaWeight,
                       RandomGenerator random)

Creates a new PSO optimization with the given parameters.

Method Detail

evaluateIndividual

public abstract PerformanceVector evaluateIndividual(double[] individual)
                                              throws OperatorException

Subclasses must implement this method to calculate the fitness of the given individual. Please note that null might be returned for non-valid individuals.

Throws:

OperatorException

nextIteration

public void nextIteration()

This method is invoked after each evaluation. The default implementation does nothing but subclasses might implement this method to support online plotting or logging.

setMinValue

public void setMinValue(double minValue)

setMaxValue

public void setMaxValue(double maxValue)

createInitialPopulation

protected Population createInitialPopulation(int popSize,
                                             int individualSize)

Creates the initial population.

optimize

public void optimize()
              throws OperatorException

Invoke this method for optimization.

Specified by:

optimize in interface Optimization

Throws:

OperatorException

evaluate

private void evaluate(Population population)
               throws OperatorException

Calculates the fitness for all individuals and gives the fitness values to the population.

Throws:

OperatorException

getGeneration

public int getGeneration()

Returns the current generation.

Specified by:

getGeneration in interface Optimization

getBestFitnessInGeneration

public double getBestFitnessInGeneration()

Returns the best fitness in the current generation.

Specified by:

getBestFitnessInGeneration in interface Optimization

getBestFitnessEver

public double getBestFitnessEver()

Returns the best fitness ever.

Specified by:

getBestFitnessEver in interface Optimization

getBestPerformanceEver

public PerformanceVector getBestPerformanceEver()

Returns the best performance vector ever.

Specified by:

getBestPerformanceEver in interface Optimization

getBestValuesEver

public double[] getBestValuesEver()

Returns the best values ever. Use this method after optimization to get the best result.

Specified by:

getBestValuesEver in interface Optimization