Author
Oruç, Muhammet Furkan, Altan, Yiğit Can
Publication Date
2023-07-01
Publication Place
-
Elsevier
Subject
Autonomous Vessels, Clustering, Machine Learning, Maritime Risk, Risky Encounter, Strait of Istanbul
Type
Periodical
Language
English
Digital
Yes
Manuscript
No
Library
Özyeğin University
Library Asset ID
0957-4174
Record ID
ec2f2388-4a1f-4d74-9380-5a7868ab0d33
Library Location
Civil Engineering
Date
2023-07-01
Sample Text
As the maritime traffic is getting denser, the number of encounters is increasing. The aim of this study is to develop a prediction model to classify encounters as risky or non-risky when two ships encounter in a certain buffer zone. A novel methodology is proposed to integrate three-dimensional clustering in the algorithm training process. K-means clustering, and ensemble machine learning algorithms-based prediction framework is developed to overcome class imbalance. The methodology is tested in the Strait of Istanbul (SOI) and parameters are generated from a long-term AIS dataset. Framework is validated via cross validation techniques. Precision, Recall, Accuracy and ROC-AUC Score are used as measures to evaluate models. Benchmark models are generated, and the most advanced model successfully predicts each 4 out of 5 risky encounters without the knowledge of distance between two ships. Eliminating distance from decision factors provides an action period before risky encounters. Therefore, proposed framework can be a guide for autonomous vessels for safe navigation and maritime authorities to improve maritime safety.
DOI
10.1016/j.eswa.2023.119728
Cilt
221
