nextgen {seao}R Documentation

Next generation

Description

Calculates a next generation, i.e. chooses and selects parents and performs crossover and mutation.

Usage

  nextgen(struc.ea,
          n.ind=NULL,
          gen.parent=NULL,
          selection=list(base="fit", rescale=0),
          corate=90,
          mutation=list(base="unif", spread=1, rate=15))

Arguments

struc.ea An evolutionary algorithm structure. It must contain at least $genes, which is a list describing the structure of the genome (parameter set).
n.ind The number of individuals one wants to generate. Default value is set to 25.
gen.parent A vector containing the numbers of the parent generations (batches). As default, the function includes all previous calculated generations (batches) for choosing the parents of the next generation (batch).
selection A list containing the base for selection, and possible selection. The base can be either "fit" (standard value) or "rank"; rescaling a number, standard value is 0, but 1.5 is a value which gives often nice results.
corate The parameter value recombination rate, i.e. the percentage individuals which should be recombined.
mutation Some evolutionary parameters to set. This contains whether a uniform ('unif') or normal ('norm') distribution should be used, whether the spread value (if this is set to 0, a value of 1 is used), and to set the paramater value randomization rate.

Value

The function returns an evolutionary algorithm object:

genes a list containing the genome (parameter set) stucture. This is the same as the genome (parameter set) structure of in the input (struc.ea$genes).
generations a list of structures with information of each generation (batch):
fit:
a vector containing the fitnesses of all individuals. These values are all set to NA, since the fitnesses of the new individuals are not known yet.
allele:
a matrix containing the allele-values of all individuals (experimental set-ups) of the new generation (batch)
parents:
a string vector with the numbers of the parent generations.
selection:
a list containing the selection base and rescaling.
crossover:
the crossover rate.
mutation:
a list containing the mutation parameters.

Note

As for all functions in this package, evolutionary terminology is used as described in seao.terminology..

Author(s)

Kurt Sys (kurt.sys@rug.ac.be)

References

See Also

genomestruc

Examples






[Package seao version 0.2-1 Index]