ptwgrid: Calculate RMS or WCC values on a grid
In ptw: Parametric Time Warping

Description Usage Arguments Details Value Author(s) See Also Examples

Calculates values of the chosen optimization criterion (RMS or WCC) on a grid defined by the coefficients of the warping function.

ptwgrid(ref, samp, selected.traces,
	coef.mins, coef.maxs, coef.lengths, 
	optim.crit = c("WCC", "RMS"), 
	smooth.param = 1e05, 
	trwdth = 20)

`ref`	reference. Either a vector (containing one reference signal) or a matrix (one reference per row). If more than one reference is specified, the number of reference signals must equal the number of sample signals
`samp`	sample. A vector (containing one sample signal) or a matrix (one sample per row). If more than one sample is specified, the number of sample signals must equal the number of reference signals
`selected.traces`	optional vector containing the row numbers to use from `ref` (if more than one reference signal is specified) and `samp`
`coef.mins`	a vector containing the respective minimal values of coefficients for the grid. The first number is the minimal zeroth-order coefficient (i.e., a constant shift); further numbers indicate the minimal linear, quadratic, ... stretches
`coef.maxs`	a vector containing the maximal values of coefficients for the grid
`coef.lengths`	a vector of the same length as coef.maxs and coef.mins containing the number of steps in which to vary the respective coefficients between their minimum and maximum value
`optim.crit`	either `"WCC"` or `"RMS"`. In both cases, the optimal value of the alignment leads to a value of 0. For "WCC", this means that `1 - WCC` is optimized rather than `WCC` (where the optimal value equals 1)
`smooth.param`	smoothing parameter for smoothing the reference and sample when `optim.crit` equals `"RMS"`. If no smoothing is required, set this to 0

trwdth

the width of the triangle in the WCC criterion during the optimization, given as a number of data points. Default: 20

In contrast to ptw, only the three situations leading to one warping function are distinguished here:

One sample and one reference;
Several samples, warped to an equal number of references (pair-wise);
Several samples, warped to a single reference.

Which situation is applicable is determined from the dimensions of ref and samp.

An array of dimension length(coef.mins) and maximal indices per dimension specified by coef.lengths

Tom Bloemberg, Jan Gerretzen, Ron Wehrens

ptw

  ## Not run: 
  data(gaschrom)
  mygrid <- ptwgrid(gaschrom[1,], gaschrom[16,],
                    coef.mins = c(-10, .9), coef.max = c(10, 1.1),
                    coef.lengths = c(21, 21))
  image(seq(-10, 10, length = 21),
        seq(.9, 1.1, length = 21),
        mygrid)

## End(Not run)