Pengembangan Sistem Terintegrasi Identifikasi IUU Fishing dan Transshipment menggunakan Adaptive Neuro-Fuzzy Inference System (ANFIS) berbasis Data Automatic Identification System (AIS) pada Kondisi Anomali Trayektori

Putri, Hanifah Rasbini (2022) Pengembangan Sistem Terintegrasi Identifikasi IUU Fishing dan Transshipment menggunakan Adaptive Neuro-Fuzzy Inference System (ANFIS) berbasis Data Automatic Identification System (AIS) pada Kondisi Anomali Trayektori. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 02311840000057-Undergraduate_Thesis.pdf] Text
02311840000057-Undergraduate_Thesis.pdf - Accepted Version

Download (4MB)

Abstract

Luasnya wilayah laut Indonesia belum diimbangi dengan upaya pemerintah yang optimal terutama dalam segi teknologi dan pengawasan secara otomatis, sehingga perbuatan illegal mengenai pencurian ikan dan pemindahan muatan di wilayah laut Indonesia masih banyak terjadi. IUU fishing dan transshipment sering terjadi di perairan Indonesia dikarenakan ketidakmampuan perkembangan teknologi pemerintah dalam melacak pelaku IUU fishing dan transshipment. Kondisi anomali adalah keadaan terjadinya keganjilan pada pergerakan kapal yang keluar dari jalur referensinya. Kapal berlayar memiliki rute tersendiri dengan tujuan menghindari tabrakan antara kapal, meminimalisir kehabisan bahan bakar, dan menghindari kecelakaan lainnya. Rute kapal ini akan mempermudah kapal tetap dapat dipantau dan menjaga dari penjarahan yang terjadi di laut. Penelitian ini mengusulkan sebuah rancangan sistem terintegrasi identifikasi IUU fishing dan transshipment menggunakan ANFIS berbasis data AIS pada kondisi anomali trayektori. ANFIS merupakan sebuah fuzzy inference system yang diimplementasikan dalam kerangka jaringan adaptif. ANFIS berfungsi sebagai dasar untuk membangun seperangkat aturan fuzzy if-then dengan fungsi keanggotaan yang sesuai untuk menghasilkan pasangan input-output yang ditentukan. Data penelitian didapatkan dari situs marinetraffic.com, Marine Reliability and Safety Laboratory, dan penelitian sebelumnya. Sub sistem anomali dirancang menggunakan iForest, sub-sistem selection dan decision dirancang menggunakan ANFIS. Hasil validasi menunjukkan bahwa hasil sub-sistem anomali dapat digunakan sebagai masukan sistem identifikasi dan akurasi identifikasi IUU fishing dan transshipment sebesar 81.2605%.
===================================================================================================================================
The vastness of Indonesia's marine area has not been matched by optimal government efforts, especially in terms of technology and automatic supervision, so that illegal acts regarding theft of fish and transfer of cargo in Indonesian marine areas are still common. IUU fishing and transshipment often occur in Indonesian waters due to the inability of the government to develop technology in tracking IUU fishing and transshipment actors. Anomaly conditions are conditions where there is an oddity in the movement of the ship that is out of its reference path. Sailing ships have their own routes with the aim of avoiding collisions between ships, minimizing running out of fuel, and avoiding other accidents. The ship route will make it easier for ships to be monitored and guard against looting that occurs at sea. The study proposes an integrated system identification for IUU fishing and transshipment using ANFIS based on AIS data in trajectory anomaly conditions. ANFIS is a fuzzy inference system which is implemented in an adaptive network framework. ANFIS serves as the basis for constructing a set of fuzzy if then rules with appropriate membership functions to generate a specified input-output pair. The research data was obtained from the marinetraffic.com website, the Marine Reliability and Safety Laboratory, and previous research. Anomaly sub- system was designed using iForest, selection and decision sub- system was designed using ANFIS. The validation results show that the results of the anomaly sub- system can be used as input for the identification system and the identification accuracy of IUU fishing and transshipment is 81.2605%.

Item Type: Thesis (Other)
Additional Information: RSF 629.836 Put p-1 • 2022
Uncontrolled Keywords: Adaptive Neuro-Fuzzy Inference System (ANFIS), Anomaly Conditions, Automatic Identification System (AIS), Isolation Forest, IUU Fishing and Transshipment
Subjects: T Technology > TJ Mechanical engineering and machinery > TJ217 Adaptive control systems
Divisions: Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User: - Davi Wah
Date Deposited: 16 Oct 2024 03:34
Last Modified: 16 Oct 2024 03:34
URI: http://repository.its.ac.id/id/eprint/115745

Actions (login required)

View Item View Item