Vol.11, No.4, November 2022.                                                                                                                                                                              ISSN: 2217-8309

                                                                                                                                                                                                                        eISSN: 2217-8333


TEM Journal



Association for Information Communication Technology Education and Science

Distance Analysis Measuring for Clustering using K-Means and Davies Bouldin Index Algorithm


Ali Idrus, Nafan Tarihoran, Ucup Supriatna, Ahmad Tohir, Suwarni Suwarni, Robbi Rahim


© 2022 Robbi Rahim, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)


Citation Information: TEM Journal. Volume 11, Issue 4, Pages 1871-1876, ISSN 2217-8309, DOI: 10.18421/TEM114-55, November 2022.


Received: 20 July 2022.

Revised:   09 September 2022.
Accepted:  27 September 2022.
Published: 25 November 2022.




The purpose of this research is to analyze mapping results in the form of clusters formed using clustering method measures. This is done to determine the connections that the existing clusters create. Some of the measurements used are mixed measurements, Bregman differences, and number measurements (Mixed Euclidean Distance, Generalized Divergence, Squared Euclidean Distance, Mahalanobis Distance, and Euclidean Distance). Distance measurement shall be applied on number with primary school facilities in Indonesia. The Davies Bouldin Index (DBI) is different from the cluster number test (k = 2-10) for each Distance Measure. The average DBI value in the type of measure (mixed measure) and numerical measurement (Mixed Euclidean Distance) is 0.54. The average DBI value in the type of measure (Bregman divergences) and numeric measurements (generalized IDivergence) is 0.66. The average DBI value is 0.77 for the measurement type (Bregman divergences) and numerical measurement (Squared Euclidean Distance). From the results, the measurement of distance with mixed measurement and the mixed Euclidean distance with the cluster number (k = 2), namely 0.269, have the best DBI value.


Keywords – – Distance Measure, K-Means, Davies Bouldin Index, Clustering.



Full text PDF >  



Copyright © 2022 UIKTEN
Copyright licence: All articles are licenced via Creative Commons CC BY-NC-ND 4.0 licence