umpcaBasis {MFPCA} | R Documentation |
Calculate an uncorrelated multilinear principal component basis representation for functional data on two-dimensional domains
Description
This function calculates an uncorrelated multilinear principal component
analysis (UMPCA) representation for functional data on two-dimensional
domains. In this case, the data can be interpreted as images with S1 x
S2
pixels (assuming nObsPoints(funDataObject) = (S1, S2)
), i.e. the
total observed data are represented as third order tensor of dimension
N x S1 x S2
. The UMPCA of a tensor of this kind is calculated via the
UMPCA function, which is an R
-version of the analogous
functions in the UMPCA
MATLAB toolbox by Haiping Lu (Link:
https://www.mathworks.com/matlabcentral/fileexchange/35432-uncorrelated-multilinear-principal-component-analysis-umpca,
see also references).
Usage
umpcaBasis(funDataObject, npc)
Arguments
funDataObject |
An object of class |
npc |
An integer, giving the number of principal components to be calculated. |
Value
scores |
A matrix of scores (coefficients) with dimension
|
B |
A matrix containing the scalar product of all pairs of basis functions. |
ortho |
Logical, set to |
functions |
A functional data object, representing the functional principal component basis functions. |
Warning
As this algorithm aims more at uncorrelated features than at an optimal reconstruction of the data, hence it might give poor results when used for the univariate decomposition of images in MFPCA. The function therefore throws a warning.
References
Haiping Lu, K.N. Plataniotis, and A.N. Venetsanopoulos, "Uncorrelated Multilinear Principal Component Analysis for Unsupervised Multilinear Subspace Learning", IEEE Transactions on Neural Networks, Vol. 20, No. 11, Page: 1820-1836, Nov. 2009.