Optimised Latin Hypercube Sampling Plan
Create an optimised Latin Hypercube Sampling Plan using a genetic based optimisation algorithm. The objective function is the inverse of the Audze-Eglais function defined as
\[\text{max } U = \text{max} \sum_{p=1}^P \sum_{q=p+1}^P L^2_{pq}\]
where $L^2_{pq}$ is the square of the Euclidean norm.
Note
This package maximises the inverse of the Audze-Eglais objective function.
Function
LatinHypercubeSampling.LHCoptim — Method.function LHCoptim(n::Int,d::Int,gens)Produce an optimized Latin Hyper Cube with d dimensions and n sample points. Optimization is run for gens generations.
Example
The LHCoptim function run for many generations to create an optimised 120 point plan in 2 dimensions.
julia> LHCoptim(120,2,gens)