Rani, Rosina Senista Tiwe (2024) Penerapan Data Mining Dalam Memprediksi Gempa Bumi Di Nusa Tenggara Timur Dengan Menggunakan Metode Naïve Bayes Dan K-Means Clustering. Undergraduate thesis, Fakultas Teknologi Informasi Universitas Merdeka Malang.

Preview	Text HALAMAN AWAL.pdf Download (593kB) | Preview
Preview	Text BAB I.pdf Download (1MB) | Preview
	Text BAB II.pdf Restricted to Repository staff only Download (1MB)
	Text BAB III.pdf Restricted to Repository staff only Download (1MB)
	Text BAB IV.pdf Restricted to Repository staff only Download (1MB)
	Text BAB V.pdf Restricted to Repository staff only Download (1MB)
Preview	Text DAFTAR PUSTAKA.pdf Download (1MB) | Preview
Preview	Text HASIL CEK PLAGIASI.pdf Download (153kB) | Preview

Abstract

Earthquakes are natural disasters that are difficult to predict bot in terms of timing and magnitude. The cause of earhquakes can originate from inense shaking due to the accumulation of energy within the lithosphere, which is then released onto the Earth’s surface with a certain magnitude. Indonesia, as a country located in the Ring of Fire and at the intersection of three major tectonic plates (Eurasian, Indo0Australian, and Pacific), frequently experiences earthquakes both tectonic and volcanic in nature, resulting in high damage and casualties. The process of earthquake occurrence is highly complex and difficult to directly observe due to the intricate interactions between materials and energy beneath the Earth’s surface. To date, there is no precise theory to accurately predict when and where earthquakes will occur. In this context, researches utilize earthquake data from the East Nusa Tenggara islands and apply data mining methods such Naïve Bayes and K-Means Clustering. Naïve bayes used to predict future earthquake events based on historical data using probabilities and statistic. K-Means Clustering in employed to group earthquake data into cluster based on specific characteristics. The research result indicate with a prediction vale of 0.907 and a confusion matrix achieving 90.74%. this indicates that 2022 had the highest number of both mild and major earthquakes in the past 11 years. Analysis using K Means Clustering also identifies patterns in the number of earthquakes each year, such as in 2022 where the clustering resulted in C1 with 67 mild earthquakes, C2 with 7 major earthquakes, and C3 5 mild earthquakes. Thus, this study demonstrates that the combination of Naïve Bayes and K Means Clustering is effective for predicting and analyzing earthquake events in this region. This research provides a foundation for further development in enhancing prediction capabilities and risk mitigation againts earthquake disasters in the future.

Actions (login required)

View Item