Perbandingan Metode Regresi Logistik dan Artificial Neural Network (ANN) Dalam Klasifikasi Gempa Bumi Berpotensi Tsunami di Indonesia

Khairunnisa, Afifah (2026) Perbandingan Metode Regresi Logistik dan Artificial Neural Network (ANN) Dalam Klasifikasi Gempa Bumi Berpotensi Tsunami di Indonesia. Bachelor thesis, Institut Teknologi Kalimantan.

[img] Text
02221002_cover.pdf
Restricted to Repository staff only until 3 October 2028.

Download (359kB) | Request a copy
[img] Text
02221002__statement_of_authenticity.pdf
Restricted to Repository staff only until 3 October 2028.

Download (269kB) | Request a copy
[img] Text
02221002_publishing_agreement.pdf
Restricted to Repository staff only until 3 October 2028.

Download (260kB) | Request a copy
[img] Text
02221002_approval_sheet.pdf
Restricted to Repository staff only until 3 October 2028.

Download (289kB) | Request a copy
[img] Text
02221002_preface.pdf
Restricted to Repository staff only until 3 October 2028.

Download (229kB) | Request a copy
[img] Text
02221002_abstract_id.pdf
Restricted to Repository staff only until 3 October 2028.

Download (279kB) | Request a copy
[img] Text
02221002_abstract_en.pdf
Restricted to Repository staff only until 3 October 2028.

Download (232kB) | Request a copy
[img] Text
02221002_table_of_content.pdf
Restricted to Repository staff only until 3 October 2028.

Download (313kB) | Request a copy
[img] Text
02221002_illustrations.pdf
Restricted to Repository staff only until 3 October 2028.

Download (263kB) | Request a copy
[img] Text
02221002_tables.pdf
Restricted to Repository staff only until 3 October 2028.

Download (273kB) | Request a copy
[img] Text
02221002_notations.pdf
Restricted to Repository staff only until 3 October 2028.

Download (247kB) | Request a copy
[img] Text
02221002_chapter_1.pdf
Restricted to Repository staff only until 3 October 2028.

Download (696kB) | Request a copy
[img] Text
02221002_chapter_2.pdf
Restricted to Repository staff only until 3 October 2028.

Download (1MB) | Request a copy
[img] Text
02221002_chapter_3.pdf
Restricted to Repository staff only until 3 October 2028.

Download (591kB) | Request a copy
[img] Text
02221002_chapter_4.pdf
Restricted to Repository staff only until 3 October 2028.

Download (1MB) | Request a copy
[img] Text
02221002_coclusions.pdf
Restricted to Repository staff only until 3 October 2028.

Download (423kB) | Request a copy
[img] Text
02221002_bibliography.pdf
Restricted to Repository staff only until 3 October 2028.

Download (348kB) | Request a copy
[img] Text
02221002_enclosure.pdf
Restricted to Repository staff only until 3 October 2028.

Download (786kB) | Request a copy
[img] Text
02221002_paper.pdf
Restricted to Repository staff only until 3 October 2028.

Download (1MB) | Request a copy
[img] Text
02221002_presentation.pdf
Restricted to Repository staff only until 3 October 2028.

Download (1MB) | Request a copy
[img] Text
02221002_Form. TA-020.pdf
Restricted to Repository staff only until 3 October 2028.

Download (294kB) | Request a copy

Abstract

Indonesia merupakan salah satu negara dengan potensi tsunami yang tinggi akibat aktivitas tektonik pada zona subduksi dan sesar aktif yang tersebar di berbagai wilayah pesisir. Dengan kondisi tersebut, diperlukan adanya analisis berbasis data untuk memahami pola gempa bumi potensi tsunami antarwilayah agar masyarakat teredukasi untuk meningkatkan kesiapsiagaaan dalam menghadapi kemungkinan terjadinya tsunami. Penelitian ini bertujuan untuk membandingkan kinerja hasil Regresi Logistik dan Artificial Neural Network (ANN) dalam klasifikasi gempa bumi berpotensi tsunami di Indonesia. Data yang digunakan terdiri dari 782 data kejadian gempa bumi dari website Kaggle sebagai data training dan data validasi dengan proporsi 80:20, serta 626 data kejadian gempa bumi dari website USGS sebagai data testing dengan parameter lintang (Latitude), bujur (Longitude), kedalaman (Depth), magnitudo (Magnitude), Number of Seismic Station (Nst) dan jarak episentrum gempa dengan stasiun seismic terdekat (Dmin). Sebelum pemodelan, data numerik dinormalisasi menggunakan Teknik Z-Score. Hasil penelitian menunjukkan bahwa model ANN memiliki performa yang lebih optimal dibandingkan model LR pada sebagian besar metrik evaluasi. Model LR menghasilkan nilai accuracy sebesar 82,8%, precision sebesar 72.9%, recall sebesar 88.5%, F1-Score sebesar 80% dan ROC-AUC sebesar 88.3%. Sementara itu, model ANN berhasil memperoleh nilai accuracy sebesar 83.4%, precision sebesar 72.7%, recall sebesar 91.8%, F1-Score sebesar 81,1% dan nilai ROC-AUC sebesar 89.8%. Berdasarkan hasil evaluasi tersebut, model ANN memberikan kinerja lebih baik daripada Regresi Logistik sehingga model ANN tersebut direkomendasikan sebagai model klasifikasi gempa bumi berpotensi tsunami pada penelitian ini.

Item Type: Thesis (Bachelor)
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Jurusan Matematika dan Teknologi Informasi > Matematika
Depositing User: Afifah Khairunnisa
Date Deposited: 14 Jul 2026 07:55
Last Modified: 14 Jul 2026 07:55
URI: http://repository.itk.ac.id/id/eprint/27146

Actions (login required)

View Item View Item