Development of Machine Learning Strategy for Predicting the Risk Range of Ship’s Berthing Velocity
Ships are prone to accidents when approaching in a berthing velocity greater than that allowed when determining the risk range corresponding to a port. Therefore, this study develops a machine learning strategy to predict the risk range of an unsafe berthing velocity when the ship approaches in port...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | Journal of Marine Science and Engineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-1312/8/5/376 |
id |
doaj-2782ed253ed149cfa2b9f92a5d14e970 |
---|---|
record_format |
Article |
spelling |
doaj-2782ed253ed149cfa2b9f92a5d14e9702021-04-02T12:17:58ZengMDPI AGJournal of Marine Science and Engineering2077-13122020-05-01837637610.3390/jmse8050376Development of Machine Learning Strategy for Predicting the Risk Range of Ship’s Berthing VelocityHyeong-Tak Lee0Jeong-Seok Lee1Woo-Ju Son2Ik-Soon Cho3Ocean Science and Technology School, Korea Maritime & Ocean University, Busan 49112, KoreaGraduate School, Korea Maritime & Ocean University, Busan 49112, KoreaGraduate School, Korea Maritime & Ocean University, Busan 49112, KoreaDivision of Global Maritime Studies, Korea Maritime & Ocean University, Busan 49112, KoreaShips are prone to accidents when approaching in a berthing velocity greater than that allowed when determining the risk range corresponding to a port. Therefore, this study develops a machine learning strategy to predict the risk range of an unsafe berthing velocity when the ship approaches in port. To perform analysis, the input parameters were based on the factors affecting the berthing velocity, and the output parameter, i.e., the berthing velocity, was measured at a tanker terminal in the Republic of Korea. Nine machine learning classification algorithms were used to analyze each model, and the top four optimal models were selected through evaluation methods based on the confusion matrix. As a result of the analysis, extra trees, random forest, bagging, and gradient boosting classifiers were identified as good models. As a result of testing using the receiving operator characteristic curve, it was confirmed that the area under the curve of the most dangerous range of berthing velocity was the highest, thus, the risk range was appropriately classified. As such, the derived models can classify and predict the risk range of unsafe berthing velocity before approaching a port; therefore, it is possible to safely berth a ship.https://www.mdpi.com/2077-1312/8/5/376berthing velocitysafely berthmachine learningconfusion matrixclassification |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hyeong-Tak Lee Jeong-Seok Lee Woo-Ju Son Ik-Soon Cho |
spellingShingle |
Hyeong-Tak Lee Jeong-Seok Lee Woo-Ju Son Ik-Soon Cho Development of Machine Learning Strategy for Predicting the Risk Range of Ship’s Berthing Velocity Journal of Marine Science and Engineering berthing velocity safely berth machine learning confusion matrix classification |
author_facet |
Hyeong-Tak Lee Jeong-Seok Lee Woo-Ju Son Ik-Soon Cho |
author_sort |
Hyeong-Tak Lee |
title |
Development of Machine Learning Strategy for Predicting the Risk Range of Ship’s Berthing Velocity |
title_short |
Development of Machine Learning Strategy for Predicting the Risk Range of Ship’s Berthing Velocity |
title_full |
Development of Machine Learning Strategy for Predicting the Risk Range of Ship’s Berthing Velocity |
title_fullStr |
Development of Machine Learning Strategy for Predicting the Risk Range of Ship’s Berthing Velocity |
title_full_unstemmed |
Development of Machine Learning Strategy for Predicting the Risk Range of Ship’s Berthing Velocity |
title_sort |
development of machine learning strategy for predicting the risk range of ship’s berthing velocity |
publisher |
MDPI AG |
series |
Journal of Marine Science and Engineering |
issn |
2077-1312 |
publishDate |
2020-05-01 |
description |
Ships are prone to accidents when approaching in a berthing velocity greater than that allowed when determining the risk range corresponding to a port. Therefore, this study develops a machine learning strategy to predict the risk range of an unsafe berthing velocity when the ship approaches in port. To perform analysis, the input parameters were based on the factors affecting the berthing velocity, and the output parameter, i.e., the berthing velocity, was measured at a tanker terminal in the Republic of Korea. Nine machine learning classification algorithms were used to analyze each model, and the top four optimal models were selected through evaluation methods based on the confusion matrix. As a result of the analysis, extra trees, random forest, bagging, and gradient boosting classifiers were identified as good models. As a result of testing using the receiving operator characteristic curve, it was confirmed that the area under the curve of the most dangerous range of berthing velocity was the highest, thus, the risk range was appropriately classified. As such, the derived models can classify and predict the risk range of unsafe berthing velocity before approaching a port; therefore, it is possible to safely berth a ship. |
topic |
berthing velocity safely berth machine learning confusion matrix classification |
url |
https://www.mdpi.com/2077-1312/8/5/376 |
work_keys_str_mv |
AT hyeongtaklee developmentofmachinelearningstrategyforpredictingtheriskrangeofshipsberthingvelocity AT jeongseoklee developmentofmachinelearningstrategyforpredictingtheriskrangeofshipsberthingvelocity AT woojuson developmentofmachinelearningstrategyforpredictingtheriskrangeofshipsberthingvelocity AT iksooncho developmentofmachinelearningstrategyforpredictingtheriskrangeofshipsberthingvelocity |
_version_ |
1721569548307529728 |