DCEM: Clustering for Multivariate and Univariate Data Using Expectation Maximization Algorithm

Implements the Improved Expectation Maximisation EM* and the traditional EM algorithm for clustering finite gaussian mixture models for both multivariate and univariate datasets. The initialization is done by randomly selecting the samples from the dataset as the mean (meu) of the Gaussian(s). This version implements the faster alternative EM* that avoids revisiting data by leveraging the heap structure. The algorithm returns a set of Gaussian parameters-posterior probabilities, mean (meu), co-variance matrices (multivariate)/standard-deviation (univariate) and priors. Reference: Hasan Kurban, Mark Jenne, Mehmet M. Dalkilic (2016) <doi:10.1007/s41060-017-0062-1>. This work is partially supported by NCI Grant 1R01CA213466-01.

Version: 2.0.2
Depends: R (≥ 3.2.0)
Imports: mvtnorm (≥ 1.0.7), matrixcalc (≥ 1.0.3), MASS (≥ 7.3.49), Rcpp (≥ 1.0.2)
LinkingTo: Rcpp
Suggests: knitr, rmarkdown
Published: 2020-04-07
Author: Sharma Parichit [aut, cre, ctb], Kurban Hasan [aut, ctb], Jenne Mark [aut, ctb], Dalkilic Mehmet [aut]
Maintainer: Sharma Parichit <parishar at iu.edu>
BugReports: https://github.iu.edu/parishar/DCEM/issues
License: GPL-3
URL: https://github.iu.edu/parishar/DCEM
NeedsCompilation: yes
Materials: README NEWS
CRAN checks: DCEM results


Reference manual: DCEM.pdf
Vignettes: DCEM
Package source: DCEM_2.0.2.tar.gz
Windows binaries: r-prerelease: DCEM_2.0.2.zip, r-release: DCEM_2.0.2.zip, r-oldrel: DCEM_2.0.2.zip
macOS binaries: r-prerelease: DCEM_2.0.2.tgz, r-release: DCEM_2.0.2.tgz, r-oldrel: DCEM_2.0.1.tgz
Old sources: DCEM archive


Please use the canonical form https://CRAN.R-project.org/package=DCEM to link to this page.