Implementasi Algoritma Gaussian Naive Bayes Classifier Untuk Prediksi Potensi Tsunami Berbasis Mikrokontroler

Dede Irawan Saputra; Dadang Lukman   Hakim

doi:10.55893/epsilon.v20i2.94

Dede Irawan Saputra Universitas Jenderal Achmad Yani
Dadang Lukman Hakim Universitas Jenderal Achmad Yani

DOI: https://doi.org/10.55893/epsilon.v20i2.94

Keywords: Gaussian Naive Bayes Classifier, Tsunami Potential, Microcontroller

Abstract

The classification carried out by the Gaussian Naive Bayes Classifier algorithm can use continuous data such as the parameters that are considered when a tsunami occurs. The data collected for the classification process is some earthquake data that has occurred in Indonesia in the last 20 years. Data from the occurrence of earthquakes that are taken include the time of occurrence, the place where the earthquake occurred, the magnitude of the earthquake, the depth of the earthquake, and also the distance from the epicenter to the nearest city where the earthquake occurred. The parameters needed in implementing the prediction process are the average value of the magnitude, the depth of the epicenter, and the distance to the epicenter. Next, the values of each standard deviation of magnitude, depth of the epicenter, and distance of the epicenter are also required. The microcontroller can implement the Probabilistic Density Function equation to calculate the potential for a tsunami. the microcontroller-based Gaussian Naive Bayes Classifier algorithm with the classification "Tsunami Potential" and "No Tsunami Potential" has an accuracy of 96%.

References

F. Handayani and S. Pribadi, “Implementasi Algoritma Naive Bayes Classifier dalam Pengklasifikasian Teks Otomatis Pengaduan dan Pelaporan Masyarakat melalui Layanan Call Center 110,” J. Tek. Elektro, vol. 7, no. 1, pp. 19–24, 2015.
[2] S. Bhatia and J. Malhotra, “Naïve bayes classifier for predicting the novel coronavirus,” in International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, 2021, no. Icicv, pp. 880–883, doi: 10.1109/ICICV50876.2021.9388410.
[3] D. Silahudin, Henderi, and A. Holidin, “Model expert system for diagnosis of COVID-19 using naïve bayes classifier,” in IOP Conference Series: Materials Science and Engineering, 2020, vol. 1007, no. 1, doi: 10.1088/1757-899X/1007/1/012067.
[4] H. Kamel, D. Abdulah, and J. M. Al-Tuwaijari, “Cancer Classification Using Gaussian Naive Bayes Algorithm,” in Proceedings of the 5th International Engineering Conference, 2019, pp. 165–170, doi: 10.1109/IEC47844.2019.8950650.
[5] G. Tzanos, C. Kachris, and D. Soudris, “Hardware Acceleration on Gaussian Naive Bayes Machine Learning Algorithm,” in International Conference on Modern Circuits and Systems Technologies, 2019, pp. 1–5, doi: 10.1109/MOCAST.2019.8741875.
[6] A. Charisma, E. Taryana, D. I. Saputra, M. B. Misuari, A. Setiawan, and F. Dharmawan, “Implementasi Sistem Komunikasi FM Pada Prototype Pendeteksi Dini Gempa,” PRotek J. Ilm. Tek. Elektro, vol. 7, no. 2, pp. 60–64, 2020, doi: 10.33387/protk.v7i2.1812.
[7] R. Prathivi, “Optimasi Algoritme Naive Bayes Untuk Klasifikasi Data Gempa Bumi di Indonesia Berdasarkan Hiposentrum,” Telematika, vol. 13, no. 1, pp. 36–43, 2020, doi: 10.35671/telematika.v13i1.928.
[8] J. Parningotan Sianipar, R. E. Saputra, and C. Setianingsih, “Waves With Multi-Sensor System Based on Web Application Using Naive Bayes Algorithm,” in e-Proceeding of Engineering, 2021, vol. 8, no. 5, pp. 6183–6188.
[9] Badan Meteorologi Klimatologi dan Geoofisika, “Indonesia Tsunami Early Warning System,” BMKG, 2022. https://inatews.bmkg.go.id/web/.
[10] F. N. Ernandi and . M., “Analisis Variasi a-Value dan b-Value Dengan Menggunakan Software Zmap V.6 Sebagai Indikator Potensi Gempa Bumi Di Wilayah Nusa Tenggara Barat,” Inov. Fis. Indones., vol. 9, no. 3, pp. 24–30, 2020, doi: 10.26740/ifi.v9n3.p24-30.
[11] D. Irawan Saputra, S. Sambasri, J. Maulana, C. Andi Mulyadi, and L. Aunillah, “Laboratorium Kit Sederhana Untuk Pengolahan Citra Digital dan Instrumentasi Cerdas,” 2019, doi: 10.5614/sniko.2018.19.