Jamali, Muhammad Mukhlis (2020) Perancangan Integrasi Sistem dengan Prediktor untuk Identifikasi Terjadinya IUU Fishing dan Transhipment Berbasis Data Automatic Identification System (AIS) Menggunakan Neural Networks. Other thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
02311640000065-Undergraduate_Thesis.pdf Download (3MB) | Preview |
Abstract
Eksploitasi sumber kekayaan alam maritim di Indonesia masih banyak terjadi. Upaya pengawasan terhadap praktik illegal fishing dan transhipment masih kurang optimal karena keterbatasan kemampuan instrumen pengawasan. Terjadinya hilangnya / losses data Automatic Identification System (AIS) berdampak pada kelemahan di dalam sistem monitoring gerakan kapal. Kelemahan sistem pada penelitian sebelumnya, dengan tanpa memperhatikan adanya losses data sehingga secara real identifikasi terhadap illegal fishing dan transhipment, menjadi kurang akurat dan valid. Penelitian tugas akhir ini melakukan perancangan integrasi sistem dengan prediktor untuk identifikasi terjadinya praktik illegal fishing dan transhipment berbasis data AIS dengan adanya data AIS yang hilang. Prediktor dirancang menggunakan recurrent neural networks (RNN) dan integrasi sistem dirancang menggunakan artificial neural networks (ANN). Prediktor dan integrasi sistem disimulasikan, diuji dan divalidasi menggunakan data kapal real yang melakukan praktik illegal fishing dan transhipment dari pusat data marinetraffic.com dan NASDEC-ITS. Hasil validasi menunjukkan bahwa hasil prediksi dari prediktor bisa digunakan sebagai masukan integrasi sistem identifikasi dan akurasi pada identifikasi illegal fishing dan transhipment sebesar 99.64%.
======================================================================================================================
Exploitation of maritime natural resources in Indonesia is still widespread. Efforts to monitor illegal fishing and transhipment practices are still less than optimal due to the limited ability of monitoring instruments. The loss of data Automatic Identification System (AIS) has an impact on weakness in the ship's motion monitoring system. The weakness of the system in the previous research, without regard to data losses so that in real identification of illegal fishing and transhipment, it becomes less accurate and valid. This research designs system integration with predictors to identify the occurrence of illegal fishing and transshipment in the presence of missing AIS data. Predictors are designed using recurrent neural networks (RNN) and system integration is designed using artificial neural networks (ANN). Predictors and system integration are simulated, tested and validated using data of real ship that committed illegal fishing and transhipment from the marinetraffic.com and NASDEC-ITS data centers. The validation results show that the predictor results from the predictor can be used as input for system integration and the accuracy of the identification of illegal fishing and transhipment is 99.64%.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Artificial Neural Networks (ANN), Automatic Identification System (AIS), illegal transhipment, IUU fishing, prediktor data hilang, Recurrent Neural Networks (RNN), sistem identifikasi, Artificial Neural Networks (ANN), Automatic Identification System (AIS), identification systems, illegal transhipment, IUU fishing, missing data predictors, Recurrent Neural Networks (RNN) |
| Subjects: | T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T58.62 Decision support systems V Naval Science > V Naval Science (General) |
| Divisions: | Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis |
| Depositing User: | Muhammad Mukhlis Jamali |
| Date Deposited: | 06 Aug 2020 01:31 |
| Last Modified: | 26 May 2023 13:39 |
| URI: | http://repository.its.ac.id/id/eprint/77035 |
Actions (login required)
 |
View Item |