Klasifikasi Gempa Bumi Berdasarkan Magnitudo Menggunakan Metode Logistic Regression

Salma Mar’atuzzulfa(1*), Rastri Prathivi(2), S Susanto(3),

(1) Universitas Semarang, Indonesia
(2) Universitas Semarang, Indonesia
(3) Universitas Semarang, Indonesia
(*) Corresponding Author

Abstract


The purpose of this study is to categorize areas in Indonesia that are potentially prone to earthquakes using the logistic regression algorithm. Variables such as latitude, longitude, depth, and magnitude are used to analyze 118 data points of natural disasters that occurred in Indonesia in 2023. As much as 40% of the data is used for testing, while 60% is used for training. The magnitudes are high, medium, and low. The logistic regression method is used to determine the level of health in the area and assess the relationship between variables. The study's findings indicate that the model has an accuracy of 93.62%, precision of 94%, recall of 93%, and F1 skor of 93% overall. In addition, the evaluation of the model's kinerja using the confusion matrix indicates that algorithms might associate a given category with a high sensitivity to error. By identifying data points and creating Logistic regression can assist in developing more effective bencana mitigation strategies by identifying data points and producing accurate predictions. As a result, it is believed that the general public can reduce the amount of dampak gempa bumi.

Full Text:

PDF

References


R. Maharani, A. Hutagaol, V. T. Lana, Z. Azzahra, and R. Kurniawan, “Penerapan Machine Learning dalam Prediksi Klasifikasi Big Data Kedalaman Gempa Bumi di Indonesia Tahun 2015-2024,” vol. 2024, no. Senada, pp. 42–51, 2024.

F. Pikriyati, “Perbandingan Algoritma Regresi Linear Dan Polynomial Pada Prediksi Kasus Gempa Bumi Di Indonesia,” vol. V, pp. 87–93, 2024.

D. Christianto, N. Tarmidzi, and S. Atmaja, “Manajemen Penyebaran Informasi Gempabumi di Media Televisi oleh Badan Meteorologi, Klimatologi dan Geofisika,” Buana Komun. (Jurnal Penelit. dan Stud. Ilmu Komunikasi), vol. 4, no. 2, p. 138, 2023, doi: 10.32897/buanakomunikasi.2023.4.2.2786.

A. Tania, T. Handhayani, and J. Hendryli, “Perbandingan Antara Algoritma K-Means Dan Algoritma Bisecting K-Means Dalam Menganalisis Gempa Bumi Di Indonesia,” Simtek J. Sist. Inf. dan Tek. Komput., vol. 8, no. 2, pp. 265–270, 2023, doi: 10.51876/simtek.v8i2.205.

I. Irawan, Y. Subiakto, and B. Kustiawan, “Manajemen Mitigasi Bencana Pada Pendidikan Anak Usia Dini untuk Mengurangi Risiko Bencana Gempa Bumi,” PENDIPA J. Sci. Educ., vol. 6, no. 2, pp. 609–615, 2022, doi: 10.33369/pendipa.6.2.609-615.

N. S. Bengi, S. Syamsul, and N. Nasri, “Prototype Sistem Pendeteksi Gempa Bumi Dan Peringatan Dini Berbasis Internet of Things,” J. TEKTRO, vol. 8, no. 1, pp. 138–144, 2024.

R. Wahyu Pratama, Y. Herry Chrisnanto, and G. Gunawan, “Klasifikasi Efek Kerusakan Gempa Bumi Berdasarkan Skala Modified Mercalli Intensity Menggunakan Algoritma Multiclass Support Vector Machine,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 2, pp. 1739–1745, 2024, doi: 10.36040/jati.v8i2.9211.

R. S. Tantika and A. Kudus, “Penggunaan Metode Support Vector Machine Klasifikasi Multiclass pada Data Pasien Penyakit Tiroid,” Bandung Conf. Ser. Stat., vol. 2, no. 2, pp. 159–166, 2022, doi: 10.29313/bcss.v2i2.3590.

A. Prasetio, M. M. Effendi, and M. N. Dwi M, “Analisis Gempa Bumi Di Indonesia Dengan Metode Clustering,” Bull. Inf. Technol., vol. 4, no. 3, pp. 338–343, 2023, doi: 10.47065/bit.v4i3.820.

J. S. Hutagalung and Rasiban, “Analisis Sentimen Keuangan (Data Fiqa and Financial Phrasebank) Menggunakan Algoritma Logistic Regression Dan Support Vector Machine,” J. Indones. Manaj. Inform. dan Komun., vol. 4, no. 3, pp. 1654–1669, 2023, doi: 10.35870/jimik.v4i3.404.

I. A. Ricky, I. F. Hanif, F. N. Hasan, E. S. Sinduningrum, Z. Halim, and N. Nunik, “Analisis Sentimen Opini Masyarakat Terkait Penyelenggaraan Sistem Elektronik Menggunakan Metode Logistic Regression,” J. Linguist. Komputasional, vol. 5, no. 2, p. 77, 2022, [Online]. Available: https://t.co/23c4krbjp

Greessheilla Phylosta P.B and Rido Febryansyah, “Permohonan Pinjaman Pada Koperasi Simpan Pinjam,” Ilmudata.org, vol. 2, no. 12, pp. 1–12, 2022.

A. R. C. Adi, “Analisis Kepuasan Pelayanan Rumah Sakir Mitra Husada Pringsewi Menggunakaan Metode Logistic Regression,” J. Ilmu Data, vol. 2, no. 12, pp. 1–11, 2022, [Online]. Available: http://ilmudata.org/index.php/ilmudata/article/view/290%0Ahttp://ilmudata.org/index.php/ilmudata/article/download/290/276

M. Fahmuddin, M. K. Aidid, and M. J. Taslim, “Implementasi Analisis Regresi Logistik Dengan Metode Machine Learning Untuk Mengklasifikasi Berita Di Indonesia,” VARIANSI J. Stat. Its Appl. Teach. Res., vol. 5, no. 03, pp. 155–162, 2023, doi: 10.35580/variansiunm116.

H. M. Ibrahim, H. Skovorodnikov, and H. Alkhzaimi, “Resilience evaluation of memristor based PUF against machine learning attacks,” Sci. Rep., vol. 14, no. 1, p. 23962, 2024, doi: 10.1038/s41598-024-73839-1.

D. N. Ardelia, H. D. Arifin, S. Daniswara, and A. P. Sari, “Klasifikasi Harga Ponsel Menggunakan Algoritma Logistic Regression,” vol. 04, no. 01, pp. 37–43, 2024.




DOI: https://doi.org/10.30645/kesatria.v6i1.564

DOI (PDF): https://doi.org/10.30645/kesatria.v6i1.564.g559

Refbacks

  • There are currently no refbacks.


Published Papers Indexed/Abstracted By: