Type: Package
Title: Three Dimensional Functional Component Analysis
Version: 1.0
Date: 2018-07-09
Author: Nan Lin, Momiao Xiong
Maintainer: Nan Lin <edmondlinnan@gmail.com>
Description: Run three dimensional functional principal component analysis and return the three dimensional functional principal component scores. The details of the method are explained in Lin et al.(2015) <doi:10.1371/journal.pone.0132945>.
License: GPL-2 | GPL-3
Depends: graphics, grDevices, stats, utils
NeedsCompilation: no
Packaged: 2018-07-09 22:49:27 UTC; nan
Repository: CRAN
Date/Publication: 2018-07-10 15:20:09 UTC

Three Dimensional Functional Component Analysis

Description

Run three dimensional functional principal component analysis and return the three dimensional functional principal component scores. The details of the method are explained in Lin et al.(2015) <doi:10.1371/journal.pone.0132945>.

Details

The DESCRIPTION file:

Package: FPCA3D
Type: Package
Title: Three Dimensional Functional Component Analysis
Version: 1.0
Date: 2018-07-09
Author: Nan Lin, Momiao Xiong
Maintainer: Nan Lin <edmondlinnan@gmail.com>
Description: Run three dimensional functional principal component analysis and return the three dimensional functional principal component scores. The details of the method are explained in Lin et al.(2015) <doi:10.1371/journal.pone.0132945>.
License: GPL-2|GPL-3
Depends: graphics, grDevices, stats, utils

Index of help topics:

FFT2FS_3D               Three dimensional Fourier Series
FPCA3D-package          Three Dimensional Functional Component Analysis
FPCA_3D_score           Three Dimensional Functional Component Analysis

data_in = array(runif(4000,0,1),dim=c(10,10,10,4)) test = FPCA_3D_score(data_in,0.8)

Author(s)

Nan Lin, Momiao Xiong

Maintainer: Nan Lin <edmondlinnan@gmail.com>

References

Lin N, Jiang J, Guo S, Xiong M. Functional Principal Component Analysis and Randomized Sparse Clustering Algorithm for Medical Image Analysis. PLOS ONE. 2015;10(7):e0132945.

See Also

FFT2FS_3D, FPCA_3D_score

Examples

data_in = array(runif(4000,0,1),dim=c(10,10,10,4))
test = FPCA_3D_score(data_in,0.8)

Three dimensional Fourier Series

Description

Calculate the three dimensional Fourier series coeffiients of the input three dimensional array.

Usage

FFT2FS_3D(A)

Arguments

A

A three dimensional numerical data array. For example, A can be the data array of an three dimensional image.

Details

Calcualte the three dimensional numerical data array. The input A array can be any three dimensional data array. For image input data, the input should be data array only without any header information.

Value

A three dimensional Fourier series coefficients array of the input A data array.

References

Lin N, Jiang J, Guo S, Xiong M. Functional Principal Component Analysis and Randomized Sparse Clustering Algorithm for Medical Image Analysis. PLOS ONE. 2015;10(7):e0132945.

Examples

test_data = array(runif(1000,0,1),dim = c(10,10,10))
rlt = FFT2FS_3D(test_data)

Three Dimensional Functional Component Analysis

Description

Calculation of three dimensional functional principal component scores for a series of three dimensional array data.

Usage

FPCA_3D_score(X, prop)

Arguments

X

The input data array. X is a four dimensional data array. The first three dimensional data represents the three dimensional data array for each observation. The fourth dimention represents the observations.

prop

The prespecified proportion of variance the calcuatled functional principal component scores can explain in the functional domain.

Details

Calculate the three dimensional functional principal component scores for a series of three dimensional data.

Value

A two dimensional score matrix. The row of the score matrix represents each individual and the column of the score matrix represent each component score.

References

Lin N, Jiang J, Guo S, Xiong M. Functional Principal Component Analysis and Randomized Sparse Clustering Algorithm for Medical Image Analysis. PLOS ONE. 2015;10(7):e0132945.

Examples

data_in = array(runif(4000,0,1),dim=c(10,10,10,4))
test = FPCA_3D_score(data_in,0.8)