adana (version 1.1.0)

selwscale: Window Scaling

Description

Window Scaling is a method based on subtracting the worst fitness value from the other fitness values. In this case, since the scaled values of the worst fit individuals will be 0, these individuals will not be given a chance to be selected.

Usage

selwscale(fitvals, ns, fmin, ...)

Arguments

fitvals

Vector of fitness values belonging to individuals

ns

Number of individuals to be selected

fmin

The number to subtract from all fitness values.

…

Further arguments passed to or from other methods.

Value

The indices of randomly selected individuals are returned.

See Also

select, selrand, selrswrp, selrws, selrws2, selsus, seldet, selrss, selsscale, selsscale2, sellscale, selrscale, selrscale2, selpscale, selescale, seltour, seltour2

Examples

# NOT RUN {
fitvals = c(6.1, 3.5, 6.2, 4.4, 5.2)
fmin = min(fitvals)
cnames = paste0("C",1:length(fitvals))
matpool = selwscale(fitvals, fmin=fmin)
cat(cnames[matpool],"\n")
fitvals = fitvals[matpool]
fitvals
matpool = selwscale(fitvals, fmin=fmin)
cat(cnames[matpool],"\n")
fitvals = fitvals[matpool]
fitvals
fmin = min(fitvals)
matpool = selwscale(fitvals, fmin=fmin)
cat(cnames[matpool],"\n")
# }