Izvorni znanstveni članak
https://doi.org/10.17818/NM/2024/1.4
Maritime Data Mining for Marine Safety Based on Deep Learning: Southern Vietnam Case Study
Tuan-Anh Pham
; a) Artificial Intelligence in Transportation Research Group, Ho Chi Minh City University of Transport, Ho Chi Minh City, Viet Nam, b) Southern Vietnam Maritime Safety Corporation
Xuan-Kien Dang
orcid.org/0000-0002-5367-3992
; Artificial Intelligence in Transportation Research Group, Ho Chi Minh City University of Transport, Ho Chi Minh City, Viet Nam
Žarko Koboević
orcid.org/0000-0002-2884-5932
; University of Dubrovnik, Dubrovnik, Croatia
Viet-Dung Do
orcid.org/0000-0001-7581-2212
; Artificial Intelligence in Transportation Research Group, Ho Chi Minh City University of Transport, Ho Chi Minh City, Viet Nam
Thi-Duyen Anh Pham
; Artificial Intelligence in Transportation Research Group, Ho Chi Minh City University of Transport, Ho Chi Minh City, Viet Nam
Sažetak
High-speed passenger vessels, integrated river and sea vessels, container vessels, oil tankers, and other underwater vehicles operating in maritime traffic are among the types of vessels that must be equipped with AIS and VHF. The safety of navigation is one of the major problems in the maritime sector, particularly in Vietnam. Furthermore, marine traffic in the seaport zone is a common and difficult issue to manage in areas with a high volume of vessel traffic, mostly in places where the infrastructure supporting navigation is inadequately developed to meet the rapidly growing demands of the contemporary world. Therefore, it is necessary to create an integrated maritime management system to improve the efficiency of data exploitation and support maritime safety. To address this challenge, this study suggests a Maritime Traffic State Prediction (MTSP) model to predict traffic conditions in the channels where real-time data collection is insufficient in some specific locations. We recommend a deep learning method using Long Short-Term Memory (LSTM) networks to predict the safe path of the vessel in case of missing data segments. The findings have shown that the proposed approach encourages the mining of historical vessel data for maritime traffic, is ready to be applied, and can easily be implemented in a computer program or a web-based app.
Ključne riječi
maritime traffic state prediction; data mining; long short-term memory network; navigational channels
Hrčak ID:
316336
URI
Datum izdavanja:
12.3.2024.
Posjeta: 56 *