Predicting the risky encounters without distance knowledge between the ships via machine learning algorithms

Name: Predicting the risky encounters without distance knowledge between the ships via machine learning algorithms
Author: Oruç, Muhammet Furkan, Altan, Yiğit Can

İsim	Predicting the risky encounters without distance knowledge between the ships via machine learning algorithms
Yazar	Oruç, Muhammet Furkan, Altan, Yiğit Can
Basım Tarihi:	2023-07-01
Basım Yeri	- Elsevier
Konu	Autonomous Vessels, Clustering, Machine Learning, Maritime Risk, Risky Encounter, Strait of Istanbul
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	0957-4174
Kayıt Numarası	ec2f2388-4a1f-4d74-9380-5a7868ab0d33
Lokasyon	Civil Engineering
Tarih	2023-07-01
Örnek Metin	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

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Predicting the risky encounters without distance knowledge between the ships via machine learning algorithms

Yazar Oruç, Muhammet Furkan, Altan, Yiğit Can

Basım Tarihi 2023-07-01

Basım Yeri - Elsevier

Konu Autonomous Vessels, Clustering, Machine Learning, Maritime Risk, Risky Encounter, Strait of Istanbul

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 0957-4174

Kayıt Numarası ec2f2388-4a1f-4d74-9380-5a7868ab0d33

Lokasyon Civil Engineering

Tarih 2023-07-01

Örnek Metin 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