An Ensemble Classification Method Based on a Stacking Strategy for Ship Type Classification with AIS Data

Ship type (e.g., Cargo, Tanker and Fishing) classification is crucial for marine management, environmental protection, and maritime safety, as it enhances navigation safety and aids regulatory agencies in combating illegal activities. Traditional ship type classification methods with AIS data are of...

Full description

Saved in:
Bibliographic Details
Main Authors: Lei Deng, Shichen Yang, Limin Jia, Danyang Geng
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/13/5/886
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257270648078336
author Lei Deng
Shichen Yang
Limin Jia
Danyang Geng
author_facet Lei Deng
Shichen Yang
Limin Jia
Danyang Geng
author_sort Lei Deng
collection DOAJ
description Ship type (e.g., Cargo, Tanker and Fishing) classification is crucial for marine management, environmental protection, and maritime safety, as it enhances navigation safety and aids regulatory agencies in combating illegal activities. Traditional ship type classification methods with AIS data are often plagued by problems such as data imbalance, insufficient feature extraction, reliance on single-model approaches, or unscientific model combination methods, which reduce the accuracy of classification. In this paper, we propose an ensemble classification method based on a stacking strategy to overcome these challenges. We apply the SMOTE technique to balance the dataset by generating minority class samples. Then, a more comprehensive ship behavior model is developed by combining static and dynamic features. A stacking strategy is adopted for the classification, integrating multiple tree structure-based classifiers to improve classification performance. The experimental results show that the ensemble classification method based on the stacking strategy outperforms traditional classifiers such as CatBoost, Random Forest, Decision Tree, LightGBM, and the ensemble classification method, especially in terms of improving classification precision, recall, F1 score, ROC curve, and AUC. This method improves the accuracy of ship type recognition, and it is suitable to real-time online classification, which is helpful for applications in marine safety monitoring, law enforcement, and illegal fishing detection.
format Article
id doaj-art-8026afbb05674bd2b567472afa545ccc
institution OA Journals
issn 2077-1312
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-8026afbb05674bd2b567472afa545ccc2025-08-20T01:56:28ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-04-0113588610.3390/jmse13050886An Ensemble Classification Method Based on a Stacking Strategy for Ship Type Classification with AIS DataLei Deng0Shichen Yang1Limin Jia2Danyang Geng3School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Mathematics and Statistics, Lanzhou University, Lanzhou 730000, ChinaSchool of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, ChinaChina Transport Informatics National Engineering Laboratory Co., Ltd., Beijing 100094, ChinaShip type (e.g., Cargo, Tanker and Fishing) classification is crucial for marine management, environmental protection, and maritime safety, as it enhances navigation safety and aids regulatory agencies in combating illegal activities. Traditional ship type classification methods with AIS data are often plagued by problems such as data imbalance, insufficient feature extraction, reliance on single-model approaches, or unscientific model combination methods, which reduce the accuracy of classification. In this paper, we propose an ensemble classification method based on a stacking strategy to overcome these challenges. We apply the SMOTE technique to balance the dataset by generating minority class samples. Then, a more comprehensive ship behavior model is developed by combining static and dynamic features. A stacking strategy is adopted for the classification, integrating multiple tree structure-based classifiers to improve classification performance. The experimental results show that the ensemble classification method based on the stacking strategy outperforms traditional classifiers such as CatBoost, Random Forest, Decision Tree, LightGBM, and the ensemble classification method, especially in terms of improving classification precision, recall, F1 score, ROC curve, and AUC. This method improves the accuracy of ship type recognition, and it is suitable to real-time online classification, which is helpful for applications in marine safety monitoring, law enforcement, and illegal fishing detection.https://www.mdpi.com/2077-1312/13/5/886ship type classificationstacking strategyensemble learningmarine trafficdata imbalance
spellingShingle Lei Deng
Shichen Yang
Limin Jia
Danyang Geng
An Ensemble Classification Method Based on a Stacking Strategy for Ship Type Classification with AIS Data
Journal of Marine Science and Engineering
ship type classification
stacking strategy
ensemble learning
marine traffic
data imbalance
title An Ensemble Classification Method Based on a Stacking Strategy for Ship Type Classification with AIS Data
title_full An Ensemble Classification Method Based on a Stacking Strategy for Ship Type Classification with AIS Data
title_fullStr An Ensemble Classification Method Based on a Stacking Strategy for Ship Type Classification with AIS Data
title_full_unstemmed An Ensemble Classification Method Based on a Stacking Strategy for Ship Type Classification with AIS Data
title_short An Ensemble Classification Method Based on a Stacking Strategy for Ship Type Classification with AIS Data
title_sort ensemble classification method based on a stacking strategy for ship type classification with ais data
topic ship type classification
stacking strategy
ensemble learning
marine traffic
data imbalance
url https://www.mdpi.com/2077-1312/13/5/886
work_keys_str_mv AT leideng anensembleclassificationmethodbasedonastackingstrategyforshiptypeclassificationwithaisdata
AT shichenyang anensembleclassificationmethodbasedonastackingstrategyforshiptypeclassificationwithaisdata
AT liminjia anensembleclassificationmethodbasedonastackingstrategyforshiptypeclassificationwithaisdata
AT danyanggeng anensembleclassificationmethodbasedonastackingstrategyforshiptypeclassificationwithaisdata
AT leideng ensembleclassificationmethodbasedonastackingstrategyforshiptypeclassificationwithaisdata
AT shichenyang ensembleclassificationmethodbasedonastackingstrategyforshiptypeclassificationwithaisdata
AT liminjia ensembleclassificationmethodbasedonastackingstrategyforshiptypeclassificationwithaisdata
AT danyanggeng ensembleclassificationmethodbasedonastackingstrategyforshiptypeclassificationwithaisdata