moeoNSGA< MOEOT > Class Template Reference

NSGA (Non-dominated Sorting Genetic Algorithm) as described in: N. More...

#include <moeoNSGA.h>

Inheritance diagram for moeoNSGA< MOEOT >:

moeoEA< MOEOT > moeoAlgo eoAlgo< MOEOT > eoUF< A1, R > eoFunctorBase List of all members.

Public Member Functions

 moeoNSGA (unsigned int _maxGen, eoEvalFunc< MOEOT > &_eval, eoGenOp< MOEOT > &_op, double _nicheSize=0.5)
 Simple ctor with a eoGenOp.
 moeoNSGA (unsigned int _maxGen, eoEvalFunc< MOEOT > &_eval, eoTransform< MOEOT > &_op, double _nicheSize=0.5)
 Simple ctor with a eoTransform.
 moeoNSGA (unsigned int _maxGen, eoEvalFunc< MOEOT > &_eval, eoQuadOp< MOEOT > &_crossover, double _pCross, eoMonOp< MOEOT > &_mutation, double _pMut, double _nicheSize=0.5)
 Ctor with a crossover, a mutation and their corresponding rates.
 moeoNSGA (eoContinue< MOEOT > &_continuator, eoEvalFunc< MOEOT > &_eval, eoGenOp< MOEOT > &_op, double _nicheSize=0.5)
 Ctor with a continuator (instead of _maxGen) and a eoGenOp.
 moeoNSGA (eoContinue< MOEOT > &_continuator, eoEvalFunc< MOEOT > &_eval, eoTransform< MOEOT > &_op, double _nicheSize=0.5)
 Ctor with a continuator (instead of _maxGen) and a eoTransform.
virtual void operator() (eoPop< MOEOT > &_pop)
 Apply a few generation of evolution to the population _pop until the stopping criteria is verified.

Protected Attributes

eoGenContinue< MOEOT > defaultGenContinuator
 a continuator based on the number of generations (used as default)
eoContinue< MOEOT > & continuator
 stopping criteria
eoPopLoopEval< MOEOT > popEval
 evaluation function used to evaluate the whole population
moeoDetTournamentSelect< MOEOT > select
 binary tournament selection
moeoFastNonDominatedSortingFitnessAssignment<
MOEOT > 
fitnessAssignment
 fitness assignment used in NSGA-II
moeoFrontByFrontSharingDiversityAssignment<
MOEOT > 
diversityAssignment
 diversity assignment used in NSGA-II
moeoElitistReplacement< MOEOT > replace
 elitist replacement
eoSGAGenOp< MOEOT > defaultSGAGenOp
 an object for genetic operators (used as default)
eoGeneralBreeder< MOEOT > genBreed
 general breeder
eoBreed< MOEOT > & breed
 breeder

Detailed Description

template<class MOEOT>
class moeoNSGA< MOEOT >

NSGA (Non-dominated Sorting Genetic Algorithm) as described in: N.

Srinivas, K. Deb, "Multiobjective Optimization Using Nondominated Sorting in Genetic Algorithms". Evolutionary Computation, Vol. 2(3), No 2, pp. 221-248 (1994). This class builds the NSGA algorithm only by using the fine-grained components of the ParadisEO-MOEO framework.

Definition at line 37 of file moeoNSGA.h.


Constructor & Destructor Documentation

template<class MOEOT>
moeoNSGA< MOEOT >::moeoNSGA ( unsigned int  _maxGen,
eoEvalFunc< MOEOT > &  _eval,
eoGenOp< MOEOT > &  _op,
double  _nicheSize = 0.5 
) [inline]

Simple ctor with a eoGenOp.

Parameters:
_maxGen number of generations before stopping
_eval evaluation function
_op variation operator
_nicheSize niche size

Definition at line 48 of file moeoNSGA.h.

template<class MOEOT>
moeoNSGA< MOEOT >::moeoNSGA ( unsigned int  _maxGen,
eoEvalFunc< MOEOT > &  _eval,
eoTransform< MOEOT > &  _op,
double  _nicheSize = 0.5 
) [inline]

Simple ctor with a eoTransform.

Parameters:
_maxGen number of generations before stopping
_eval evaluation function
_op variation operator
_nicheSize niche size

Definition at line 61 of file moeoNSGA.h.

template<class MOEOT>
moeoNSGA< MOEOT >::moeoNSGA ( unsigned int  _maxGen,
eoEvalFunc< MOEOT > &  _eval,
eoQuadOp< MOEOT > &  _crossover,
double  _pCross,
eoMonOp< MOEOT > &  _mutation,
double  _pMut,
double  _nicheSize = 0.5 
) [inline]

Ctor with a crossover, a mutation and their corresponding rates.

Parameters:
_maxGen number of generations before stopping
_eval evaluation function
_crossover crossover
_pCross crossover probability
_mutation mutation
_pMut mutation probability
_nicheSize niche size

Definition at line 77 of file moeoNSGA.h.

template<class MOEOT>
moeoNSGA< MOEOT >::moeoNSGA ( eoContinue< MOEOT > &  _continuator,
eoEvalFunc< MOEOT > &  _eval,
eoGenOp< MOEOT > &  _op,
double  _nicheSize = 0.5 
) [inline]

Ctor with a continuator (instead of _maxGen) and a eoGenOp.

Parameters:
_continuator stopping criteria
_eval evaluation function
_op variation operator
_nicheSize niche size

Definition at line 91 of file moeoNSGA.h.

template<class MOEOT>
moeoNSGA< MOEOT >::moeoNSGA ( eoContinue< MOEOT > &  _continuator,
eoEvalFunc< MOEOT > &  _eval,
eoTransform< MOEOT > &  _op,
double  _nicheSize = 0.5 
) [inline]

Ctor with a continuator (instead of _maxGen) and a eoTransform.

Parameters:
_continuator stopping criteria
_eval evaluation function
_op variation operator
_nicheSize niche size

Definition at line 104 of file moeoNSGA.h.


Member Function Documentation

template<class MOEOT>
virtual void moeoNSGA< MOEOT >::operator() ( eoPop< MOEOT > &  _pop  )  [inline, virtual]

Apply a few generation of evolution to the population _pop until the stopping criteria is verified.

Parameters:
_pop the population

Definition at line 114 of file moeoNSGA.h.

References moeoNSGA< MOEOT >::breed, moeoNSGA< MOEOT >::continuator, moeoNSGA< MOEOT >::diversityAssignment, moeoNSGA< MOEOT >::fitnessAssignment, moeoNSGA< MOEOT >::popEval, and moeoNSGA< MOEOT >::replace.


The documentation for this class was generated from the following file:
Generated on Fri Jul 6 09:41:04 2007 for ParadisEO-MOEO by  doxygen 1.4.7