Skripsi

PENERAPAN ALGORITMA RANDOM FOREST DAN K-NEAREST NEIGHBORS DALAM MEMPREDIKSI GEMPA BUMI DI SUMATERA BAGIAN SELATAN

---

Earthquakes occur due to the impact of volcanic activity in mountainous areas. Sumatra Island is one of the islands that has earthquake activity that occurs quite frequently, especially in the South Sumatra region. This research aims to get accurate results based on the best algorithm in predicting earthquakes in Southern Sumatra to determine the prediction of earthquakes in Southern Sumatra using machine learning algorithms. Earthquake data for the Southern Sumatra region used was taken from 1900 to 2022 with parameters such as date, time, latitude, longitude, depth, magnitude and place. Evaluation of the prediction results of random forest and K-Nearest Neighbor algorithms is done using confusion matrix. The evaluation results of the random forest algorithm get an accuracy value of 94.78% and the accuracy of the K-Nearest Neighbor algorithm is 95.14%. The precision value of random forest is 93% and the precision value of K-Nearest Neighbors is 92%. The recall and f1 score values in random forest and K-Nearest Neighbors have the same value which is 95% for recall and 93% for f1-score. The K-Nearest Neighbor algorithm has a higher accuracy value than the random forest algorithm, so it can be concluded that the algorithm is more accurate than the random forest algorithm.

---

Availability

Detail Information

Series Title

-

Call Number

T1521082024

Publisher

Indralaya : Prodi Ilmu Fisika, Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Sriwijaya., 2024

Collation

xiv, 105 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

551.220 285 07

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Ilmu Fisika
Algoritma Random Forest

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment