WaveThresh
Help
wpst
Non-decimated wavelet packet transform.
DESCRIPTION
This function computes the non-decimated wavelet packet
transform as described by
Nason, Sapatinas and Sawczenko, 1998.
The non-decimated wavelet packet transform (NWPT)
contains all possible shifted versions
of the wavelet packet transform.
USAGE
wpst(data, filter.number=10, family="DaubLeAsymm", fsc=sqrt(2)/2)
REQUIRED ARGUMENTS
- data
- A vector containing the data you wish to decompose. The
length of this vector must be a power of 2.
OPTIONAL ARGUMENTS
- filter.number
- This selects the smoothness of wavelet that you
want to use in the decomposition. By default this is 10,
the Daubechies least-asymmetric orthonormal compactly supported wavelet
with 10 vanishing moments.
- family
- specifies the family of wavelets that you want to use.
The options are "DaubExPhase" and "DaubLeAsymm".
- fsc
- a constant supplied to the
constant
argument in the
filter.select function (and hence applies to all
the wavelet coefficients).
VALUE
An object of class wpst containing the discrete
packet-ordered non-decimated wavelet packet coefficients.
SIDE EFFECTS
None
DETAILS
This function computes the packet-ordered non-decimated wavelet packet
transform of data as described by
Nason, Sapatinas and Sawczenko, 1998.
It assumes periodic boundary conditions.
The order of computation of the NWPT is O(n^2)
if n is the number of input data points.
Packets can be extracted from the wpst object
produced by this function using the getpacket.wpst
function. Whole resolution levels of non-decimated wavelet packet coefficients
in time order can be obtained by using the
accessD.wpst function.
RELEASE
Version 3.8.8 Copyright Guy Nason 1997
SEE ALSO
accessD,
accessD.wpst,
filter.select,
getpacket,
getpacket.wpst,
wpst object,
EXAMPLES
#
# EXAMPLE pending
#