Dear Reader,
You will find in the associated text files ("nke-routines.R", and "nke-simulations.R") the materials needed for implementing the statistical methodology detailed in the paper
FERRATY F., ZULLO A., FAUVEL, M. Nonparametric regression on contaminated functional predictor with application to hyperspectral data (under revision)
This method aims to estimate the relationship between responses and corresponding contaminated curves (for instance the relationship between woody species identified during a field campaign and hyperspectral profiles extracted from a hyperspectral image collected by the HYSPEX sensors)
The file "nke-routines.R" contains the whole set of R routines dealing with NKE (Nested-Kernel Estimator) which includes several routines ("kernel_smoother", "nested.funopadi", "nested.funopare", "nke", "predict.npfda", "semimetric.L2" and "summary.npfda")
The file "nke-commandlines.R" contains all R commandlines allowing to implement the NKE methodology with different simulated datasets covering discrimination (i.e. responses = labels) as well as regression (scalar responses) setting.
How to use this material?
1) open an R session
2) follow the instructions given in the text file "nke-commandlines.R"
(copy-paste the R commandlines into your R session)
Copyright: these materials may be downloaded freely for your own personal study. Use for any commercial purpose is forbidden.