mkm: Multi-objective Kriging model

In coldfir3/moko: Multi-Objective Kriging Optimization

Description

This function creates a multi-objective kriging model. It is based on the km function of the DiceKriging package and creates a structured list of km objects.

Usage

mkm(design, response, modelcontrol = NULL)

Arguments

design	Numeric data.frame of the designs (decision space)
response	Numeric data.frame of the observed responses (objectives and constraints) at each design point.
modelcontrol	An optional list of control parameters passed to the km function. One can control: objective (default: 1:ncol(response)) quiet (default: TRUE) formula (default: ~1) covtype (default: "matern5_2") nugget.estim (default: FALSE) estim.method (default: "MLE") optim.method (default: "BFGS") multistart (default: 1) gr (default: TRUE) iso (default: FALSE) scaling (default: FALSE) type (default: 'UK') se.compute (default: TRUE) light.return (default: TRUE) bias.correct (default: FALSE) checkNames (default: FALSE) For more details, one can check km.

Value

S4 An object of class mkm-class

Examples

# ------------------------
# The Nowacki Beam
# ------------------------
n <- 10
d <- 2
doe <- replicate(d,sample(0:n,n))/n
res <- t(apply(doe, 1, nowacki_beam))
model <- mkm(doe, res, modelcontrol = list(objective = 1:2))

coldfir3/moko documentation built on May 13, 2019, 8:49 p.m.