The function extracts features from functional data based on the fast fourier transform. For more details refer to stats::fft.

extractFDAFourier(trafo.coeff = "phase")

Arguments

trafo.coeff (character(1)) Specifies which transformation of the complex frequency domain representation should be calculated as a feature representation. Must be one of “amplitude” or “phase”. Default is “phase”. The phase shift is returned in Rad, i.e. values lie in [-180, 180].

Value

(data.frame).

Other fda_featextractor: extractFDABsignal(), extractFDADTWKernel(), extractFDAFPCA(), extractFDAMultiResFeatures(), extractFDATsfeatures(), extractFDAWavelets()