Learn R Programming

Rwave (version 1.2)

gcrcrec: Crazy Climbers Reconstruction by Penalization

Description

Reconstructs a real valued signal from ridges found by crazy climbers on a gabor transform.

Usage

gcrcrec(siginput, inputgt, beemap, nvoice, freqstep, scale, compr,
bstep=5, ptile=0.01, epsilon=0, fast=TRUE, para=5, minnbnodes=3,
hflag=FALSE, real=FALSE, plot=2)

Arguments

siginput
original signal.
inputgt
Gabor transform.
beemap
occupation measure, output of crc.
nvoice
number of frequencies.
freqstep
sampling step for frequency axis.
scale
size of windows.
compr
compression rate to be applied to the ridges.
bstep
size (in the time direction) of the steps for chaining.
ptile
threshold of ridge
epsilon
constant in front of the smoothness term in penalty function.
fast
if set to TRUE, uses trapezoidal rule to evaluate $Q_2$.
para
scale parameter for extrapolating the ridges.
minnbnodes
minimal number of points per ridge.
hflag
if set to FALSE, uses the identity as first term in the kernel. If not, uses $Q_1$ instead.
real
if set to TRUE, uses only real constraints.
plot
1{ displays signal,components, and reconstruction one after another. } 2{displays signal, components and reconstruction. }

Value

  • Returns a structure containing the following elements:
  • recreconstructed signal.
  • orderedimage of the ridges (with different colors).
  • comp2D array containing the signals reconstructed from ridges.

Details

When ptile is high, boundary effects may appeare. para controls extrapolation of the ridge.

References

See discussions in the text of ``Practical Time-Frequency Analysis''.

See Also

crc, cfamily, crcrec, scrcrec.