org.opt4j.optimizer.ea

Class Nsga2

java.lang.Object

org.opt4j.optimizer.ea.Nsga2

All Implemented Interfaces:

Selector

Direct Known Subclasses:

SelectorDefault

public class Nsga2
extends Object
implements Selector

The Nsga2 Selector.

Author:

lukasiewycz, noorshams

See Also:

Nsga2Module, "A Fast Elitist Non-Dominated Sorting Genetic Algorithm for Multi-Objective Optimization: NSGA-II, K. Deb, Samir Agrawal, Amrit Pratap, and T. Meyarivan, Parallel MockProblem Solving from Nature, 2000"

Constructor Summary

Constructors

Constructor and Description
Nsga2(Rand random, int tournament, FrontDensityIndicator indicator) Constructs a Nsga2 Selector.

Method Summary

Modifier and Type	Method and Description
List<List<Individual>>	fronts(Collection<Individual> individuals) Evaluate the fronts and set the correspondent rank values.
Collection<Individual>	getLames(int n, Collection<Individual> population) Selects a subset of lambda Individuals and returns it as a new Collection.
Collection<Individual>	getParents(int mu, Collection<Individual> population) Selects a subset of Individuals and returns it as a new Collection.
void	init(int maxsize) Sets the maximal number of Individuals.

Methods inherited from class java.lang.Object

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

Constructor Detail

Nsga2

@Inject
public Nsga2(Rand random,
                     int tournament,
                     FrontDensityIndicator indicator)

Constructs a Nsga2 Selector.

Parameters:

random - the random number generator

tournament - the tournament value

Method Detail

init

public void init(int maxsize)

Description copied from interface: Selector

Sets the maximal number of Individuals.

Specified by:

init in interface Selector

Parameters:

maxsize - the number of individuals

getParents

public Collection<Individual> getParents(int mu,
                                         Collection<Individual> population)

Description copied from interface: Selector

Selects a subset of Individuals and returns it as a new Collection. These so called parents can be used to form the next generation.

Specified by:

getParents in interface Selector

Parameters:

mu - the number of parents to select

population - the list of individuals

Returns:

the parents

getLames

public Collection<Individual> getLames(int n,
                                       Collection<Individual> population)

Description copied from interface: Selector

Selects a subset of lambda Individuals and returns it as a new Collection. These individuals can be erased in the next generation.

Specified by:

getLames in interface Selector

Parameters:

n - the number of lames to select

population - the list of individuals

Returns:

the worst lambda individuals

fronts

public List<List<Individual>> fronts(Collection<Individual> individuals)

Evaluate the fronts and set the correspondent rank values.

Parameters:

individuals - the individuals

Returns:

the fronts