moeoFrontByFrontCrowdingDistanceDiversityAssignment< MOEOT > Class Template Reference

Diversity assignment sheme based on crowding distance proposed in: K. More...

#include <moeoFrontByFrontCrowdingDistanceDiversityAssignment.h>

Inheritance diagram for moeoFrontByFrontCrowdingDistanceDiversityAssignment< MOEOT >:

moeoCrowdingDistanceDiversityAssignment< MOEOT > moeoDiversityAssignment< MOEOT > eoUF< eoPop< MOEOT > &, void > eoFunctorBase List of all members.

Public Types

typedef MOEOT::ObjectiveVector ObjectiveVector
 the objective vector type of the solutions

Public Member Functions

void updateByDeleting (eoPop< MOEOT > &_pop, ObjectiveVector &_objVec)

Private Member Functions

void setDistances (eoPop< MOEOT > &_pop)
 Sets the distance values.
unsigned int lastIndex (eoPop< MOEOT > &_pop, unsigned int _start)
 Returns the index of the last individual having the same fitness value than _pop[_start].

Detailed Description

template<class MOEOT>
class moeoFrontByFrontCrowdingDistanceDiversityAssignment< MOEOT >

Diversity assignment sheme based on crowding distance proposed in: K.

Deb, A. Pratap, S. Agarwal, T. Meyarivan, "A Fast and Elitist Multi-Objective Genetic Algorithm: NSGA-II", IEEE Transactions on Evolutionary Computation, vol. 6, no. 2 (2002). Tis strategy assigns diversity values FRONT BY FRONT. It is, for instance, used in NSGA-II.

Definition at line 25 of file moeoFrontByFrontCrowdingDistanceDiversityAssignment.h.


Member Function Documentation

template<class MOEOT>
void moeoFrontByFrontCrowdingDistanceDiversityAssignment< MOEOT >::updateByDeleting ( eoPop< MOEOT > &  _pop,
ObjectiveVector _objVec 
) [inline, virtual]

Warning:
NOT IMPLEMENTED, DO NOTHING ! Updates the diversity values of the whole population _pop by taking the deletion of the objective vector _objVec into account.
Parameters:
_pop the population
_objVec the objective vector
Warning:
NOT IMPLEMENTED, DO NOTHING !

Reimplemented from moeoCrowdingDistanceDiversityAssignment< MOEOT >.

Definition at line 40 of file moeoFrontByFrontCrowdingDistanceDiversityAssignment.h.

template<class MOEOT>
void moeoFrontByFrontCrowdingDistanceDiversityAssignment< MOEOT >::setDistances ( eoPop< MOEOT > &  _pop  )  [inline, private, virtual]

Sets the distance values.

Parameters:
_pop the population

Reimplemented from moeoCrowdingDistanceDiversityAssignment< MOEOT >.

Definition at line 55 of file moeoFrontByFrontCrowdingDistanceDiversityAssignment.h.

References moeoCrowdingDistanceDiversityAssignment< MOEOT >::inf(), moeoFrontByFrontCrowdingDistanceDiversityAssignment< MOEOT >::lastIndex(), and moeoCrowdingDistanceDiversityAssignment< MOEOT >::tiny().

template<class MOEOT>
unsigned int moeoFrontByFrontCrowdingDistanceDiversityAssignment< MOEOT >::lastIndex ( eoPop< MOEOT > &  _pop,
unsigned int  _start 
) [inline, private]

Returns the index of the last individual having the same fitness value than _pop[_start].

Parameters:
_pop the population
_start the index to start from

Definition at line 121 of file moeoFrontByFrontCrowdingDistanceDiversityAssignment.h.

Referenced by moeoFrontByFrontCrowdingDistanceDiversityAssignment< MOEOT >::setDistances().


The documentation for this class was generated from the following file:
Generated on Tue Jun 26 15:13:04 2007 for ParadisEO-MOEO by  doxygen 1.4.7