kpeaks : an R package for quick selection of k for cluster analysis

Cebeci, Zeynel and Cebeci, Cagatay; (2019) kpeaks : an R package for quick selection of k for cluster analysis. In: 2018 International Conference on Artificial Intelligence and Data Processing - Proceedings. IEEE, TUR. ISBN 9781538668788 (https://doi.org/10.1109/IDAP.2018.8620896)

[thumbnail of Cebeci-Cebeci-AIDP2018-kpeaks-an-R-package-for-quick-selection-of-k-for-cluster-analysis]
Preview
 Text. Filename: Cebeci_Cebeci_AIDP2018_kpeaks_an_R_package_for_quick_selection_of_k_for_cluster_analysis.pdf
Accepted Author Manuscript
Download (404kB)| Preview

Abstract

The argument k is a mandatory user-specified input argument for the number of clusters which is required to start all of the partitioning clustering algorithms. In unsupervised learning applications, an optimal value of this argument is generally determined by using any of the internal validity indexes. However, the determination of k with aid of these indexes are computationally very expensive because they compute a k value using the results after several runs of a clustering algorithm. On the contrary, the package 'kpeaks' enables to estimate k before starting a clustering session. It is based on a simple novel technique using the descriptive statistics of peak counts of the features in datasets. In this paper, we introduce and illustrate the details of R package 'kpeaks' as an implementation for quick selection of the number of clusters for starting cluster algorithms.

  • Item type:Book Section
    ID code:67870
    Dates:
    Date
    Event
    24 January 2019
    Published
    15 August 2018
    Accepted
    Notes:© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
    Subjects:Technology > Electrical engineering. Electronics Nuclear engineering
    Department:Faculty of Engineering > Electronic and Electrical Engineering
    Depositing user: Pure Administrator
    Date deposited:16 May 2019 08:43
    Last modified:11 Nov 2024 15:17
    Related URLs:
    URI:https://strathprints.strath.ac.uk/id/eprint/67870
CORE (COnnecting REpositories)