Perancangan Sistem Identifikasi dan Prediksi IUU Transshipment Untuk Mengatasi Anomali Data Trayektori Dengan Faktor Cuaca Angin Menggunakan Metode Neural Network

Azizah, Siti Nur (2023) Perancangan Sistem Identifikasi dan Prediksi IUU Transshipment Untuk Mengatasi Anomali Data Trayektori Dengan Faktor Cuaca Angin Menggunakan Metode Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 02311940000039-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (4MB) | Request a copy

Abstract

Indonesia merupakan negara kepulauan dengan luas perairan terbesar di dunia. Namun, dengan luas perairan tersebut, Indonesia juga memiliki kerugian yang sangat tinggi di sektor kelautan dan perikan yang disebut Illegal, Unregulated, Unreported (IUU) Fishing dan Trasshipment. Penelitian ini dilakukan dengan merancang sistem identifikasi yang mampu memberikan prediksi dan keputusan apakah kapal yang sedang berlayar tersebut melakukan IUU Transhipment dengan memperhatikan kondisi anomali data trayektori dari jalur yang seharusnya secara disengaja atau karena gangguan cuaca angin. Sistem terdiri dari 3 sub-sistem, yaitu sub-sistem anomali dengan input selisih jarak jalur referensi dengan jalur real dan kecepatan angin untuk deteksi keadaan anomali trayektori, Sub-sistem selection dengan input selisih jarak dua kapal, dan selisih heading kapal untuk deteksi dua kapal dalam kondisi waspada, dan sub-sistem decision dengan input selisih jarak dua kapal, selisih heading kapal dan selisih kecepatan kapal untuk memutuskan kedua kapal melakukan IUU atau tidak. Sistem dirancang dengan metode Neural Networkdengan arsitektur sub-sistem anomali 2-1-20 dengan fungsi aktivasi Relu, optimizer Adam dengan akurasi sistem 99,537 %. Arsitektur sub-sistem selection yaitu 2-1-50 dengan fungsi aktivasi Relu, optimizer RMSprop dengan akurasi 98,726 %. Untuk arsitektur sub-sistem decision yaitu 3-1-50 dengan fungsi aktivasi Tanh, optimizer Adam dengan akurasi 95,01 %. Berdasarkan uji data dari semua skenario pergerakan kapal didapatkan akurasi keputusan sistem secara keseluruhan sebesar 91,67 %. ================================================================================================================================
Indonesia is an archipelagic country with vast inland and archipelagic waters, making it the largest archipelagic state in the world. However, despite its extensive maritime area, Indonesia also faces significant losses in the marine and fisheries sector, namely Illegal, Unregulated, Unreported (IUU) Fishing and Transshipment. This study was conducted by designing an identification system capable of predicting and determining whether a sailing vessel is involved in IUU Transshipment, considering anomalous trajectory data conditions resulting from intentional deviations or weather disturbances. The system consists of three sub systems: the anomali sub-system, which utilizes the difference between the reference route and the actual route, as well as wind speed, to detect trajectory anomalies; the selection sub-system, which uses the difference in distance between two vessels and their heading difference to detect vessels in an alert condition; and the decision sub-system, which considers the difference in distance, heading, and speed between two vessels to determine whether both vessels are engaged in IUU activities or not. The system is designed using the Neural Networkmethod, with the architecture of the anomali sub-system being 2-1-20, employing the Relu activation function and the Adam optimizer, achieving a system accuracy of 99.537%. The selection sub-system has an architecture of 2-1-50, using the Relu activation function and the RMSprop optimizer, with an accuracy of 98.726%. The decision sub-system has an architecture of 3-1-50, utilizing the Tanh activation function and the Adam optimizer, with an accuracy of 95.01%. Based on the test data from all ship movement skenarios, the overall accuracy of the system's decisions is determined to be 91.67%.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	AIS, Trajectory Anomali, Anomali Trayektori, IUU Transshipment dan Neural Network.
Subjects:	T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T58.62 Decision support systems
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User:	Siti Nur Azizah
Date Deposited:	25 Jul 2023 02:20
Last Modified:	25 Jul 2023 02:20
URI:	http://repository.its.ac.id/id/eprint/99297

Actions (login required)

View Item