selDomNumberPlusHV: Modified dominated Hypervolume selector.

In jakobbossek/ecr2: Evolutionary Computation in R

Modified dominated Hypervolume selector.

Description

Alternative SMS-EMOA survival selection as proposed in Algorithm 3 of [1]. Performs non-dominated sorting first. If the number of non-domination levels is at least two the algorithm drops the individual with the highest number of dominating points (ties are broken at random) from the last layer. If there is just one non-domination layer, i.e., all points are non-domianted the method drops the individual with minimal hypervolume contribution. This selector is the basis of the S-Metric Selection Evolutionary Multi-Objective Algorithm, termed SMS-EMOA (see smsemoa).

Usage

selDomNumberPlusHV(fitness, n.select, ref.point)

Arguments

fitness	[matrix] Matrix of fitness values (each column contains the fitness value(s) of one individual).
n.select	[integer(1)] Number of elements to select.
ref.point	[numeric] Reference point for hypervolume computation.

Value

[integer] Vector of survivor indizes.

Note

Note that the current implementation expects n.select = ncol(fitness) - 1 and the selection process quits with an error message if n.select is greater than 1.

References

[1] Beume, Nicola, Boris Naujoks and M. Emmerich. SMS-EMOA: Multiobjective selection based on dominated hypervolume.” European Journal of Operational Research. 181 (2007): 1653-1669.

See Also

Other selectors: selDomHV(), selGreedy(), selNondom(), selRanking(), selRoulette(), selSimple(), selTournament()

jakobbossek/ecr2 documentation built on Sept. 23, 2023, 12:33 p.m.