org.moeaframework.algorithm
Class SPEA2.StrengthFitnessEvaluator

java.lang.Object
  org.moeaframework.algorithm.SPEA2.StrengthFitnessEvaluator

All Implemented Interfaces:

FitnessEvaluator

Enclosing class:

SPEA2

public class SPEA2.StrengthFitnessEvaluator
extends Object
implements FitnessEvaluator

Fitness evaluator for the strength measure with crowding-based niching.

Field Summary

Fields inherited from interface org.moeaframework.core.FitnessEvaluator

FITNESS_ATTRIBUTE

Constructor Summary

SPEA2.StrengthFitnessEvaluator(int k)
Constructs a new fitness evaluator for computing the strength measure with crowding-based niching.

Method Summary

boolean	areLargerValuesPreferred() Returns true if larger fitness values are preferred; otherwise smaller fitness values are preferred.
void	evaluate(Population population) Evaluates the solutions in the specified population assigning the FITNESS_ATTRIBUTE attribute.

Methods inherited from class java.lang.Object

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

Constructor Detail

SPEA2.StrengthFitnessEvaluator

public SPEA2.StrengthFitnessEvaluator(int k)

Constructs a new fitness evaluator for computing the strength measure with crowding-based niching.

Parameters:

k - crowding is based on the distance to the k-th nearest neighbor

Method Detail

evaluate

public void evaluate(Population population)

Description copied from interface: FitnessEvaluator

Evaluates the solutions in the specified population assigning the FITNESS_ATTRIBUTE attribute.

Specified by:

evaluate in interface FitnessEvaluator

Parameters:

population - the population to be evaluated

areLargerValuesPreferred

public boolean areLargerValuesPreferred()

Description copied from interface: FitnessEvaluator

Returns true if larger fitness values are preferred; otherwise smaller fitness values are preferred.

Specified by:

areLargerValuesPreferred in interface FitnessEvaluator

Returns:

true if larger fitness values are preferred; otherwise smaller fitness values are preferred