jmetal.qualityIndicator
Class Hypervolume

java.lang.Object
  jmetal.qualityIndicator.Hypervolume

public class Hypervolume
extends java.lang.Object

This class implements the hypervolume indicator. The code is the a Java version of the original metric implementation by Eckart Zitzler. It can be used also as a command line program just by typing $java jmetal.qualityIndicator.Hypervolume Reference: E. Zitzler and L. Thiele Multiobjective Evolutionary Algorithms: A Comparative Case Study and the Strength Pareto Approach, IEEE Transactions on Evolutionary Computation, vol. 3, no. 4, pp. 257-271, 1999.

Field Summary

MetricsUtil

utils_

Constructor Summary

Hypervolume()
Constructor Creates a new instance of MultiDelta

Method Summary

double	calculateHypervolume(double[][] front, int noPoints, int noObjectives)
double	hypervolume(double[][] paretoFront, double[][] paretoTrueFront, int numberOfObjectives) Returns the hypevolume value of the paretoFront.
static void	main(java.lang.String[] args) This class can be invoqued from the command line.

Methods inherited from class java.lang.Object

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

Field Detail

utils_

public MetricsUtil utils_

Constructor Detail

Hypervolume

public Hypervolume()

Constructor Creates a new instance of MultiDelta

Method Detail

calculateHypervolume

public double calculateHypervolume(double[][] front,
                                   int noPoints,
                                   int noObjectives)

hypervolume

public double hypervolume(double[][] paretoFront,
                          double[][] paretoTrueFront,
                          int numberOfObjectives)

Returns the hypevolume value of the paretoFront. This method call to the calculate hipervolume one

Parameters:

paretoFront - The pareto front

paretoTrueFront - The true pareto front

numberOfObjectives - Number of objectives of the pareto front

main

public static void main(java.lang.String[] args)

This class can be invoqued from the command line. Three params are required: 1) the name of the file containing the front, 2) the name of the file containig the true Pareto front 3) the number of objectives