Search for collections on Unika Repository

COMPARATIVE CLUSTERING ANALYSIS OF EARTHQUAKE PATTERNS IN INDONESIA USING KMEDOIDS AND K-MEANS++

WIBOWO, GREGORIUS ARDHITO MAHENDRA (2025) COMPARATIVE CLUSTERING ANALYSIS OF EARTHQUAKE PATTERNS IN INDONESIA USING KMEDOIDS AND K-MEANS++. S1 thesis, UNIVERSITAS KATOLIK SOEGIJAPRANATA.

[img]
Preview
Text
21.K1.0049_GREGORIUS ARDHITO MAHENDRA WIBOWO_COVER.pdf

Download (500kB) | Preview
[img] Text
21.K1.0049_GREGORIUS ARDHITO MAHENDRA WIBOWO_BAB I.pdf
Restricted to Registered users only

Download (414kB)
[img] Text
21.K1.0049_GREGORIUS ARDHITO MAHENDRA WIBOWO_BAB II.pdf
Restricted to Registered users only

Download (485kB)
[img] Text
21.K1.0049_GREGORIUS ARDHITO MAHENDRA WIBOWO_BAB III.pdf
Restricted to Registered users only

Download (515kB)
[img] Text
21.K1.0049_GREGORIUS ARDHITO MAHENDRA WIBOWO_BAB IV.pdf
Restricted to Registered users only

Download (608kB)
[img] Text
21.K1.0049_GREGORIUS ARDHITO MAHENDRA WIBOWO_BAB V.pdf
Restricted to Registered users only

Download (405kB)
[img]
Preview
Text
21.K1.0049_GREGORIUS ARDHITO MAHENDRA WIBOWO_DAPUS.pdf

Download (473kB) | Preview
[img] Text
21.K1.0049_GREGORIUS ARDHITO MAHENDRA WIBOWO_LAMP.pdf
Restricted to Registered users only

Download (541kB)

Abstract

Indonesia is a country that is susceptible to earthquakes. This is because of its geographical location on the Pacific Ring of Fire and the junction of three major tectonic plates. The purpose of this study is to see what are the best algorithms to cluster earthquakes in Indonesia and to identify the region that had the most earthquakes. The data is obtained from Meteorology, Climatology, and Geophysics Agency (BMKG) repositories containing 10,354 earthquakes data from January to December 2023. This study was conducted using Kmedoids and K-means++ as the algorithms. The results showed that the K-means++ algorithm is better at clustering this dataset with a Silhouette Score of 0.589 at K=6, while K-medoids at K=4 had 0.561. This indicates that K-means++ is better at grouping similar data and distinguishing it from others. Furthermore, this study found that the Banda Sea and around the North Sulawesi had a particular high seismic activity. These results have significant implications for disaster risk reduction and mitigation efforts, especially areas where it is susceptible to earthquakes.

Item Type: Thesis (S1)
Subjects: 000 Computer Science, Information and General Works > 004 Data processing & computer science
Divisions: Faculty of Computer Science > Department of Informatics Engineering
Depositing User: ms. Wiwien Vieragustin
Date Deposited: 11 Jul 2025 01:11
Last Modified: 11 Jul 2025 01:11
URI: http://repository.unika.ac.id/id/eprint/37294
Keywords: UNSPECIFIED

Actions (login required)

View Item View Item