Algoritma Machine Learning Dalam Melakukan Prediksi Pemilihan Konfigurasi Kapal Tunda Di Pelabuhan Tanjung Priok

Yulianto, Budi Tri (2024) Algoritma Machine Learning Dalam Melakukan Prediksi Pemilihan Konfigurasi Kapal Tunda Di Pelabuhan Tanjung Priok. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6032211150-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (1MB) | Request a copy

Abstract

Pelayanan pemanduan dan penundaan di Pelabuhan Tanjung Priok dilakukan oleh executive planner, seorang executive planner bertanggung jawab terhadap kegiatan penerimaan dan meneliti permintaan pelayanan pemanduan dan penundaan kapal serta menetapkan rencana pelayanan pemanduan dan penundaan kapal di Pelabuhan. Salah satu langkah yang dibutuhkan dalam proses penetapan kapal tunda dalam pelayanan jasa penundaan yaitu pemilihan konfigurasi Kapal Tunda. Pada penelitian untuk membuat pemodelan prediksi penentuan konfigurasi Kapal Tunda menggunakan metode Support Vector Machine (SVM) dan Naïve Bayes Classifier. Hasil perbandingan antara SVM dan NBC didapatkan bahwa SVM memberikan hasil yang lebih baik dengan parameter optimal pada kernel Linier dengan seleksi fitur pada C = 10 nilai precision sebesar 84,7 %, recall 84,7 %, F1-score 88,7% dan akurasi yang cukup tinggi sebesar 88,7%.
========================================================================================================================
The service of Pilotage and Tug Assist at the Port of Tanjung Priok by executive planner, an executive planner responsible for receiving and verifying requests for Pilotage and Tug Assist and establishing plans for it at the Port. One of the steps needed in the process of determining tugboats in Tug Assist services is the selection of Tugboats Configuration. This Study aim to create a predictive model for determining Tugboat Configurations, Support Vector Machine (SVM) and Naïve Bayes Classifier methods were utilized. The comparison results between SVM and NBC showed that SVM better results with optimal parameters in the Linear kernel, with feature selection at C = 10, with a precision value of 84.7%, recall of 84.7%, an F1-score of 88.7%, and a sufficiently high accuracy of 88.7%.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Pelabuhan, Kapal Tunda, Prediksi, Support Vector Machine, Naïve Bayes. Port, Tugboat, Prediction, Support Vector Machine, Naïve Bayes.
Subjects:	H Social Sciences > HE Transportation and Communications H Social Sciences > HE Transportation and Communications > HE551 Cargo handling. Harbors--Management.
Divisions:	Interdisciplinary School of Management and Technology (SIMT) > 61101-Master of Technology Management (MMT)
Depositing User:	Budi Tri Yulianto
Date Deposited:	31 Jul 2024 04:20
Last Modified:	31 Jul 2024 04:20
URI:	http://repository.its.ac.id/id/eprint/110882

Actions (login required)

View Item