Analisis Perbandingan Metode DBSCAN dan Meanshift dalam Klasterisasi Data Gempa Bumi di Indonesia
DOI:
https://doi.org/10.47065/bulletincsr.v5i4.605Keywords:
Data Mining; DBSCAN; Earthquake; Meanshift; Silhouette ScoreAbstract
Indonesia is one of the countries with a high vulnerability to earthquakes due to its location at the convergence of three major tectonic plates: the Indo-Australian, Eurasian, and Pacific plates. As a result of this interaction, seismic activity is highly frequent across various regions. Understanding the distribution patterns of earthquakes is essential for disaster risk mitigation. One approach used to analyze these patterns is clustering, particularly using the DBSCAN and Meanshift algorithms, which can group spatial data without predefining the number of clusters. This study aims to compare the effectiveness of both algorithms in clustering earthquake data based on spatial parameters, namely latitude and longitude. Evaluation was conducted using cluster visualization and the Silhouette Score as the clustering validity metric. The results show that DBSCAN produces more optimal clustering with a Silhouette Score of 0.930028, higher than Meanshift's score of 0.90103. DBSCAN is also capable of detecting relevant outliers in earthquake analysis, while Meanshift generates more clusters but with less separation. Using spatial parameters such as latitude and longitude, DBSCAN is considered more effective in identifying the spatial distribution patterns of seismic activity in Indonesia based on earthquake data. This research supports the development of decision support systems for earthquake disaster mitigation and serves as a reference for selecting appropriate clustering methods for spatial data analysis.
Downloads
References
R. R. A. Rahman and A. W. Wijayanto, “Pengelompokan Data Gempa Bumi Menggunakan Algoritma DBSCAN,” J. Meteorol. dan Geofis., vol. 22, no. 1, p. 31, 2021, doi: 10.31172/jmg.v22i1.738.
Admin, “Pengertian Bencana,” Dinas Sosial, 2021. https://dinsos.bulelengkab.go.id/informasi/detail/artikel/pengertian-bencana-35#:~:text=Gempa bumi tektonik,kecil hingga yang sangat besar.
S. farisi Y, “Analisis Tingkat Kerentanan Fisik Dan Sosial Bencana Gempabumi Di” Swara Bhumi, vol. v, no. 9, 2020.
R. M. Taufiq, R. Firdaus, F. Handayani, P. F. Muarif, and R. R. Rizqy, “Density-Based Clustering untuk Pemetaan Daerah Rawan Gempa Bumi di Wilayah Sumatera Barat Menggunakan Metode DBSCAN,” Jurnal Fasilkom, vol. 14, no. 3, pp. 817–822, 2024.
M. Firdaus, “Data Mining,” 2023.
I. N. Simbolon and P. D. Friskila, “Analisis Dan Evaluasi Algoritma Dbscan (Density-Based Spatial Clustering Of Applications With Noise) Pada Tuberkulosis.” JITET, vol. 12, no. 3, 2024.
Sachinsoni, “Clustering Like a Pro: A Beginner’s Guide to DBSCAN,” Medium, 2023. https://medium.com/%40sachinsoni600517/clustering-like-a-pro-a-beginners-guide-to-DBSCAN-6c8274c362c4
“Meanshift,” Wikipedia. https://en.wikipedia.org/wiki/Mean_shift?utm_source=chatgpt.com
Admin, “Kupas Tuntas Algoritma Data Science dengan Mean-Shift Algorithm,” DQLab, 2021. https://dqlab.id/kupas-tuntas-algoritma-data-science-dengan-mean-shift-algorithm
A. N. Tahiyat, B. Maulana, A. E. Saputra, and L. Efrizoni, “Klasterisasi Lagu Populer dan Eksplorasi Subgenre Spotify 2024 dengan K-Medoids,” 2025.
T. A. Cinderatama and Y. Y. , Rinanza Zulmy Alhamri, “Implementasi Metode K-Means, DBSCAN, dan Meanshift untuk analisis jenis ancaman,” J. INOVTEK POLBENG - SERI Inform., vol. 7, no. 1, 2022.
R. Rianti, R. Andarsyah, and R. M. Awangga, “Penerapan PCA dan Algoritma Clustering untuk Analisis Mutu.pdf,” NUANSA Inform., 2024.
D. R. S. S. Wijayatia, Rika, “Clustering Data Campuran Numerik Dan Kategorik,” PRISMA, vol 6, 2023.
A. M. Afinda, “Supervised vs Unsupervised Learning: Mana yang Paling Cocok untuk Data Kamu?,” 2024. https://www.dicoding.com/blog/supervised-vs-unsupervised-learning-mana-yang-sesuai-untuk-data-kamu/
C. Ramadhani and I. M. B. Suksmadana, “Pengklasteran Kejadian Gempa Wilayah Indonesia Menggunakan Algoritma k-Means,” Dielektrika, vol. 8, no. 2. pp. 62–67, 2022
C. K. Saputra, “Perbandingan Hasil Segmentasi Citra dengan Metode K-means, Agglomerative Hierarchical, dan DBSCAN.” 2023
A. N. A. Maulidhia, R. Basya, Indri Ika Widyastuti Friska Intan Sukarno, and S. T. T. Brian, “Implementasi Perbandingan Algoritma k-Means dan DB-Scan Pada Beban Listrik Rumah Tangga.pdf.” INTEGER: Journal of Information Technology, 2025.
M. I. Awal Lidya Musaffak, Kartika Maulida Hindrayani, “Penerapan Metode Mean Shift Clustering Untuk Mengelompokkan Wilayah Berdasarkan Pengelolaan Sampah,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 9, no. 3, 2025.
Z. L. M. Nabila Dea Azahraa, M. F. Farizqia, Iqbal, and Kharisudina, “Segmentasi Pelanggan dengan Algoritma DBSCAN dan KMeans.pdf,” Prism. Pros. Semin. Nas. Mat., 2025.
J. Riyono, C. E. Pujiastuti, A. L. Riyana, And Putri, “Clustering Negara Berdasarkan Skor Pengendalian Konsumsi Tembakau,” J. Tek. Inform. Kaputama, vol. 8, no. 1, 2024.
C. Alkahfi, “Pengenalan Algoritma Clustering DBSCAN,” sains.data, 2024. https://sainsdata.id/machine-learning/13080/pengenalan-algoritma-clustering-DBSCAN/#:~:text=Keunggulan dan Keterbatasan DBSCAN,hasil berbeda tergantung titik awal
R. Azwarini, “Metode Clustering DBSCAN (Density-Based Spatial Clustering of Applications with Noise),” exsight.id. https://exsight.id/blog/2024/10/30/clustering-DBSCAN/
RIZUAN, “Penerapan Algoritma Mean-Shift Pada Clustering Penerima Bantuan Pangan Non Tunai Tugas Akhir,” J. Comput. Syst. Informatics, 2023.
T. Joshi, “Evaluating Clustering Algorithm — Silhouette Score,” Medium, 2021. https://tushar-joshi-89.medium.com/silhouette-score-a9f7d8d78f29
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Perbandingan Metode DBSCAN dan Meanshift dalam Klasterisasi Data Gempa Bumi di Indonesia
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2025 MHD Ade Setiawan, Fitri Insani, Yelfi Vitriani, Yusra
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
