SC.MEB {SC.MEB}

SC.MEB.

Description

SC.MEB implements the model SC-MEB, spatial clustering with hidden Markov random field using empirical Bayes.

Usage

SC.MEB(
  y,
  Adj_sp,
  beta_grid = seq(0, 4, 0.2),
  K_set = 2:10,
  parallel = TRUE,
  num_core = 5,
  PX = TRUE,
  maxIter_ICM = 10,
  maxIter = 50
)

Arguments

y

is n-by-d PCs.

Adj_sp

is a sparse matrix of neighborhood. It is often generated from function find_neighbors2 or getneighborhood_fast.

beta_grid

is a numeric vector specifying the smoothness parameter of Random Markov Field. The default is seq(0,4,0.2).

K_set

is an integer vector specifying the numbers of mixture components (clusters) for which the BIC is to be calculated. The default is K = 2:10.

parallel

is a logical value to decide whether the function SC.MEB run in parallel. The default is TRUE.

num_core

is an integer value to decide how many cores are used to run SC.MEB in parallel.

PX

is a logical value to decide whether to use parameter expansion in EM algorithm

maxIter_ICM

is the maximum iteration of ICM algorithm. The default is 10.

maxIter

is the maximum iteration of EM algorithm. The default is 50.

Details

SC.MEB can implements the model SC-MEB in parallel which can improve the speed of the computation.

Value

a list, We briefly explain the output of the SC.MEB.

The item 'x' contains clustering results.

The item 'gam' is the posterior probability matrix.

The item 'ell' is the opposite log-likelihood.

The item 'mu' is the mean of each component.

The item 'sigma' is the variance of each component.

References

Yang Y, Shi X, Zhou Q, et al. SC-MEB: spatial clustering with hidden Markov random field using empirical Bayes[J]. bioRxiv, 2021.

Examples

y = matrix(rnorm(50, 0, 1), 25,2)
pos = cbind(rep(1:5, each=5), rep(1:5, 5))
Adj_sp = getneighborhood_fast(pos, 1.2)
beta_grid = c(0.5,1)
K_set = 2:3
out = SC.MEB(y, Adj_sp, beta_grid, K_set, TRUE, 2)