Global Index (all files) (short | long) | Local contents | Local Index (files in subdir) (short | long)
[NumSubPop, NumIndSubPop, NumIndPop] = geanumind(NumVar, Difficulty)
Calculate number of subpopulations and individuals for GEATbx
This function takes the problem size (using number of variables)
and calculates the number of subpopulations and individuals
per subpopulation.
These numbers constitute a robust starting value.
The equations are suited for real-valued representations and
problems of low difficulty. Problems with many irregular local
minima and/or correlations between variables may need a larger
number of individuals.
Syntax: [NumSubPop, NumIndSubPop, NumIndPop] = geanumind(NumVar, Difficulty)
Input parameter:
NumVar - Scalar defining the number of variables of a
problem (used for size of problem)
Difficulty- (optional) Scalar defining the difficulty of the
problem (not used at the moment, but will be useful)
Output parameter:
NumSubPop - Scalar containing the number of subpopulations
NumIndSubPop - Scalar containing the number of individuals
per subpopulation
NumIndPop - Scalar containing the number of individuals in all
subpopulations (is NumSubPop x NumIndSubPop)
Examples:
% Calculate number of subpopulations and individuals for a problem with 12 variables
>> NumVar = [12]
>> [NumSubPop, NumIndSubPop, NumIndPop] = geanumind(NumVar)
NumSubPop = 3
NumIndSubPop = 20
NumIndPop = 60
% Calculate number of subpopulations and individuals for common problem sizes
>> NumVar = [5,10:10:200]
>> [NumSubPop, NumIndSubPop, NumIndPop] = geanumind(NumVar)
NumVar =
5 10 20 30 40 50 60 70 80 90 100 110 120 130 140 150 160 170 180 190 200
NumSubPop =
2 3 4 5 6 7 7 8 8 9 10 10 10 11 11 12 12 13 13 13 14
NumIndSubPop =
20 20 20 20 20 25 25 25 25 25 30 30 30 30 30 35 35 35 35 35 40
NumIndPop =
40 60 80 100 120 175 175 200 200 225 300 300 300 330 330 420 420 455 455 455 560
See also: geamain2
| GEATbx: | Main page Tutorial Algorithms M-functions Parameter/Options Example functions www.geatbx.com |