Jurnal Algoritma, Logika dan Komputasi

 Natural disaster is an event that cannot be avoided, therefore a mapping of occurrence of the natural disaster is needed. In additional to mapping, clustering of natural disaster events is also needed to determine which areas have low to high intensity events. In performing the clustering, a method or algorithm can be used, namely the k-means algorithm.

In the research conducter, the scope of natural disasters is West Java Province with the attributes used are floods, landslides and tornadoes. And also from this research, it was conducted to find out how many optimal number of clusters that can be clustered.

The method that used  in this study is the K-Means algorithm which is used to perform clustering. The Elbow method is used to determine the optimal K value from the dataset by calculate the SSE (Sum Square Error) of each predetermined cluster.

From the result of its application, the K-Means algorithm can cluster datasets of Natural Disaster in West Java with predetermined attributes. Based on the calculation results from the elbow method, the value of K from the dataset is 4. And from the research conducter, the accuracy rate of each cluster is 0,04% to 0,56%.

Keywords:  K-Means, Natural Disaster, Elbow Method, Cluster, Machine Learning

Martini, “Identifikasi Sumber Bencana Alam Dan Upaya Penanggulangannya Di Sulawesi Tengah,” J. Infrastruktur, Tek. SIpil Univ. Tadulako, Palu., vol. 1, pp. 96–102, 2011, [Online]. Available: http://jurnal.untad.ac.id/jurnal/index.php/JTSI/article/view/689/593.

D. Arifin, “Sebanyak 2.925 Bencana Alam Terjadi Pada 2020 di Tanah Air, Bencana Hidrometeorologi Mendominasi,” BNPB, 2020. https://www.bnpb.go.id/berita/sebanyak-2-925-bencana-alam-terjadi-pada-2020-di-tanah-air-bencana-hidrometeorologi-mendominasi (accessed Oct. 07, 2021).

A. Priambodo, N. Widyaningrum, and H. K. Rahmat, “Strategi Komando Resor Militer 043/ Garuda Hitam dalam Penanggulangan Bencana Alam di Provinsi Lampung,” Perspektif, vol. 9, no. 2, pp. 307–313, 2020, doi: 10.31289/perspektif.v9i2.3588.

M. R. Muttaqin and M. Defriani, “Algoritma K-Means untuk Pengelompokan Topik Skripsi Mahasiswa,” Ilk. J. Ilm., vol. 12, no. 2, pp. 121–129, 2020, doi: 10.33096/ilkom.v12i2.542.121-129.

P. Bradley, K. Bennett, and A. Demiriz, “Constrained k-means clustering,” Tech. Rep., p. 9, 2000, [Online]. Available: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.3257.

I. Bin Mohamad and D. Usman, “Standardization and its effects on K-means clustering algorithm,” Res. J. Appl. Sci. Eng. Technol., vol. 6, no. 17, pp. 3299–3303, 2013, doi: 10.19026/rjaset.6.3638.

J. A. Ginting and A. M. Jadera, “Analisa Indeks Vegetasi Menggunakan Citra Satelit Lansat 7 dan Lansat 8 Menggunakan Metode K-Means di Kawasan Gunung Sinabung,” Indones. J. Comput. Model., vol. 1, no. 1, pp. 42–48, 2018, doi: 10.24246/j.icm.2018.v1.i1.p42-48.

G. Hamerly and C. Elkan, “Learning the in -means,” Adv. Neural Inf. Process. Syst., 2004.

W. Sutikno, J. F. Palandi, and C. A. Oktavia, “Klasifikasi E-book Berbahasa Inggris Dengan Menggunakan Metode K-Means Clustering Studi Kasus Perpustakaan STIKI Malang,” J-Intech, vol. 7, no. 01, pp. 80–85, 2019, doi: 10.32664/j-intech.v7i01.409.

N. Putu, E. Merliana, and A. J. Santoso, “Analisa Penentuan Jumlah Cluster Terbaik pada Metode K-Means,” pp. 978–979.

A. B. H. Kiat, Y. Azhar, and V. Rahmayanti, “PENERAPAN METODE K-MEANS DENGAN METODE ELBOW UNTUK SEGMENTASI PELANGGAN MENGGUNAKAN MODEL RFM(Recency, Frequency, & Monetary),” J. Repos., vol. 2, no. 7, p. 945, 2020, doi: 10.22219/repositor.v2i7.973.

N. T. Hartanti, “Metode Elbow dan K-Means Guna Mengukur Kesiapan Siswa SMK Dalam Ujian Nasional,” J. Nas. Teknol. dan Sist. Inf., vol. 6, no. 2, pp. 82–89, 2020, doi: 10.25077/teknosi.v6i2.2020.82-89.