Klasterisasi Daerah Rawan Bencana Alam Menggunakan Algoritma K-Means

Authors

  • Michael Kevin Adinata Institut Teknologi Nasional Malang
  • Ali Mahmudi Institut Teknologi Nasional Malang
  • Yosep Agus Pranoto Institut Teknologi Nasional Malang

DOI:

https://doi.org/10.29408/jit.v8i1.28196

Keywords:

BPBD, Clustering, Data Mining, East Java, K-Means Clustering, Natural Disasters

Abstract

East Java is a province with high vulnerability to disasters, such as floods, landslides, earthquakes, and strong winds, which have an impact on material losses, casualties, and deterioration of socio-economic conditions, especially in rural areas. The lack of mitigation strategies and resource allocation worsens disaster management. This study aims to classify disaster data using the K-Means algorithm to overcome the limitations of descriptive analysis conducted by BPBD East Java. The data used includes 1125 disaster events with variable disaster frequency, total damage, and the number of casualties per sub-district in East Java districts and cities during 2021-2022, obtained from the official website of the East Java BPBD. The K-Means algorithm was chosen because of its efficiency in managing big data and its flexibility in cluster formation. The results of the study show that in 2021, the region in East Java is divided into three clusters based on the level of disaster risk: Cluster 1 (low risk) with 192 sub-districts, Cluster 2 (medium risk) with 35 sub-districts, and Cluster 3 (high risk) with 10 sub-districts. In 2022, significant changes were seen in Cluster 1, which includes 462 sub-districts, Cluster 2 with 20 sub-districts, and Cluster 3 with 11 sub-districts. The results of this study are expected to support the government's decision-making priorities, especially in disaster management and resource allocation based on risk levels

References

R. S. Hidayat, M. R. Muttaqin, and D. Irmayanti, “Pengelompokan Daerah Rawan Bencana Di Jawa Tengah Menggunakan Algoritma K-Means Clustering,” Jurnal Mahasiswa Teknik Informatika, vol. 8, no. 5, 2024.

M. Firman, A. Halik, and L. Septiana, “Analisa Data Untuk Prediksi Daerah Rawan Bencana Alam Di Jawa Barat Menggunakan Algoritma K-Means Clustering,” Journal of Information System, Applied, Management, Accounting and Research, vol. 6, no. 4, pp. 856–870, 2022, doi: 10.52362/jisamar.v6i4.939.

I. Kadek, R. D. Putra, A. Faisol, and M. Orisa, “Penerapan K-Means Clustering Untuk Pemetaan Wilayah Rawan Bencana Alam Kota Malang,” Malang, Oct. 2024.

M. Ichsan, E. A. Wijaya, M. R. Mahendra, and F. A. Alfarouk, “Pengelompokan Data Wilayah Rawan Bencana Alam di Pulau Jawa,” Neptunus: Jurnal Ilmu Komputer Dan Teknologi Informasi, vol. 2, no. 3, pp. 46–51, Jun. 2024, doi: 10.61132/neptunus.v2i3.181.

R. B. Prasetyo, Y. A. Pranoto, and R. Primaswara Prasetya, “implementasi data mining menggunakan algoritma k-means clustering penyakit pasien rawat jalan pada klinik dr. Atirah desa sioyong, sulteng,” 2023.

R. Aisy, R. Kurniawan, J. Perjuangan No, and B. Karyamulya Kec Kesambi Kota Cirebon, “Klasterisasi Data Bencana Alam Di Kota Cirebon Menggunakan K-Means Clustering Berdasarkan Kawasan Dan Jenis Bencana,” 2024. [Online]. Available: https://data.cirebonkota.go.id/

H. Yusuf Heraldi, N. Churin Aprilia, dan Hasih Pratiwi, and P. Studi Statistika, “Analisis Cluster Intensitas Kebencanaan di Indonesia Menggunakan Metode K-Means,” Indonesian Journal of Applied Statistics, vol. 2, pp. 137–144, Nov. 2019.

B. Green, B. Yapen, A. Faisol, and Y. A. Pranoto, “Penerapan Algoritma K-Means Clustering Untuk Pengelompokkan Wilayah Rawan Bencana Alam Kabupaten Biak Numfor,” 2024.

A. Maulana, R. Danar Dana, and N. D. Nuris, “Implementasi Algoritma K-Means Clustering Dalam Pengelompokan Data Kerusakan Rumah Akibat Bencana Alam Di Kabupaten Cirebon,” 2024.

D. Rohman, R. Annisa, D. I. Efendi, and D. Solahudin, “Clustering Bencana Alam Menggunakan K-Means Pada Wilayah Jawa Barat,” Malang, Feb. 2024.

M. Iqbal Ramadhan, “Penerapan Data Mining Untuk Analisis Data Bencana Milik Bnpb Menggunakan Algoritma K-Means Dan Linear Regression,” 2017.

R. Amaliah, E. Tohidi, E. Wahyudin, and A. Rizki Rinaldi, “Pengelompokkan Data Bencana Alam Berdasarkan Wilayah Menggunakan Algoritma K-Means,” Malang, Dec. 2023.

H. Firdaus, “Tahun 2022 50 Analisa Cluster Menggunakan K-Means Dan Fuzzy C-Means Dalam Pengelompokan Provinsi Menurut Data Intesitas Bencana Alam Di Indonesia Tahun 2017-2021,” Jurnal Ilmiah Matematika, vol. 10, pp. 50–60, 2022.

M. Qusyairi, Zul Hidayatullah, and Arnila Sandi, “Penerapan K-Means Clustering Dalam Pengelompokan Prestasi Siswa Dengan Optimasi Metode Elbow,” Infotek: Jurnal Informatika dan Teknologi, vol. 7, no. 2, pp. 500–510, Jul. 2024, doi: 10.29408/jit.v7i2.26375.

A. muliawan Nur, M. Saiful2, H. Bahtiar, and Muhammad Taufik Hidayat, “Penerapan Algoritma K-Means Clustering Dalam Mengelompokkan Smartphone Yang Rekomendasi Berdasarkan Spesifikasi,” Infotek: Jurnal Informatika dan Teknologi, vol. 7, no. 2, pp. 478–488, Jul. 2024, doi: 10.29408/jit.v7i2.26283.

W. Purba, W. Siawin, M. Nababan, N. P. Dharshinni, and S. Aisyah, “Implementasi Data Mining Untuk Pengelompokkan Dan Prediksi Karyawan Yang Berpotensi Phk Dengan Algoritma K-Means Clustering,” JUSIKOM PRIMA, vol. 2, no. 1, Jul. 2018.

N. Komang Sri Julyantari et al., “Implementasi K-Means Untuk Pengelompokan Status Gizi Balita (Studi Kasus Banjar Titih)” Jurnal Janitra Informatika dan Sistem Informasi, vol. 1, no. 2, pp. 92–101, 2021, doi: 10.25008/janitra

Aris Sudianto, Lalu Kerta Wijaya, Jumawal Jumawal, and Mahpuz Mahpuz, “Penerapan Aplikasi Warung Media Berbasis Android Guna Meningkatkan Promosi dan Penjualan,” Infotek Jurnal Informatika dan Teknologi, vol. 7, no. 1, pp. 267–275, Jan. 2024, doi: https://doi.org/10.29408/jit.v7i1.24482.

Downloads

Published

20-01-2025

How to Cite

Michael Kevin Adinata, Ali Mahmudi, & Yosep Agus Pranoto. (2025). Klasterisasi Daerah Rawan Bencana Alam Menggunakan Algoritma K-Means. Infotek: Jurnal Informatika Dan Teknologi, 8(1), 250–260. https://doi.org/10.29408/jit.v8i1.28196

Similar Articles

<< < 3 4 5 6 7 8 9 10 11 12 > >> 

You may also start an advanced similarity search for this article.