Enhance the overall prediction capabilities of a surrogate model by the Universal Prediction distribution based Surrogate Modeling Adapative Refinement Strategy UP-SMART
upsmart(model, fun, nsteps, lower, upper, seed = 1, parinit = NULL, control = NULL, RefControl = NULL)
| model | the surrogate model |
|---|---|
| fun | the real function |
| nsteps | the number of points to be generated |
| lower | the lower bound of the design space |
| upper | the upper bound of the design space |
| seed | the random seed (default = 1) |
| parinit | inital points to be used in the optimization (default NULL) |
| control | the optimization control parameters (default NULL) |
| RefControl | the refienement criterion parameters (default NULL) |
list of generated points and their values and the last updated surrogate model
#' library(UP) d <- 2; n <- 16 X <- expand.grid(x1=s <- seq(0,1, length=5), x2=s) Xtest <- expand.grid(x1=seq(0,1,length=5), x2=seq(0,1,length=4)) Y <- apply(X, 1, branin) sm <- krigingsm$new() sm$setDOE(X,Y) sm$train() upsmart_res <- upsmart(sm,fun = branin,nsteps = 5, lower= c(0,0),upper = c(1,1))#> [1] "UP-SMART iteration : 1" #> [1] "UP-SMART iteration : 2" #> [1] "UP-SMART iteration : 3" #> [1] "UP-SMART iteration : 4" #> [1] "UP-SMART iteration : 5"print(upsmart_res$last$get_DOE())#> $x #> x1 x2 #> 1 0.0000000 0.0000000 #> 2 0.2500000 0.0000000 #> 3 0.5000000 0.0000000 #> 4 0.7500000 0.0000000 #> 5 1.0000000 0.0000000 #> 6 0.0000000 0.2500000 #> 7 0.2500000 0.2500000 #> 8 0.5000000 0.2500000 #> 9 0.7500000 0.2500000 #> 10 1.0000000 0.2500000 #> 11 0.0000000 0.5000000 #> 12 0.2500000 0.5000000 #> 13 0.5000000 0.5000000 #> 14 0.7500000 0.5000000 #> 15 1.0000000 0.5000000 #> 16 0.0000000 0.7500000 #> 17 0.2500000 0.7500000 #> 18 0.5000000 0.7500000 #> 19 0.7500000 0.7500000 #> 20 1.0000000 0.7500000 #> 21 0.0000000 1.0000000 #> 22 0.2500000 1.0000000 #> 23 0.5000000 1.0000000 #> 24 0.7500000 1.0000000 #> 25 1.0000000 1.0000000 #> 26 0.8818768 0.3738098 #> 27 0.1122530 0.1039815 #> 28 0.3790677 1.0000000 #> 29 0.6236599 0.0000000 #> 30 0.6362611 1.0000000 #> #> $y #> [1] 305.956302 80.060129 10.218600 20.597105 9.503736 191.588546 #> [7] 32.717656 3.185863 27.158559 2.943833 105.345789 13.500183 #> [13] 24.278127 61.845013 24.508931 47.228033 22.407710 73.495391 #> [19] 124.656467 74.199029 17.235277 59.440237 150.837655 215.592921 #> [25] 152.014126 23.531113 123.998113 118.075401 8.803617 193.809155 #>