kpeaks: Determination of K Using Peak Counts of Features for Clustering

The number of clusters (k) is needed to start all the partitioning clustering algorithms. An optimal value of this input argument is widely determined by using some internal validity indices. Since most of the existing internal indices suggest a k value which is computed from the clustering results after several runs of a clustering algorithm they are computationally expensive. On the contrary, the package 'kpeaks' enables to estimate k before running any clustering algorithm. It is based on a simple novel technique using the descriptive statistics of peak counts of the features in a data set.

Version: 1.1.0
Depends: R (≥ 3.3.0)
Imports: graphics, stats, utils, methods
Published: 2020-02-08
DOI: 10.32614/CRAN.package.kpeaks
Author: Zeynel Cebeci [aut, cre], Cagatay Cebeci [aut]
Maintainer: Zeynel Cebeci <zcebeci at>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
Citation: kpeaks citation info
Materials: NEWS
CRAN checks: kpeaks results


Reference manual: kpeaks.pdf


Package source: kpeaks_1.1.0.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): kpeaks_1.1.0.tgz, r-oldrel (arm64): kpeaks_1.1.0.tgz, r-release (x86_64): kpeaks_1.1.0.tgz, r-oldrel (x86_64): kpeaks_1.1.0.tgz
Old sources: kpeaks archive

Reverse dependencies:

Reverse imports: inaparc


Please use the canonical form to link to this page.