A semi-supervised deep learning approach for vessel trajectory classification based on AIS data

被引:39
作者
Duan, Hongda [1 ,2 ]
Ma, Fei [3 ]
Miao, Lixin [2 ,3 ]
Zhang, Canrong [1 ,2 ]
机构
[1] Tsinghua Univ, Dept Ind Engn, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Res Ctr Modern Logist, Shenzhen Int Grad Sch, Shenzhen 518055, Peoples R China
[3] Tsinghua Univ, Tsinghua Berkeley Shenzhen Inst, Shenzhen 518055, Peoples R China
基金
中国国家自然科学基金;
关键词
Automatic identification system; Vessel trajectory classification; Deep learning; Semi-supervised learning; Variational autoencoder; IDENTIFICATION SYSTEM AIS;
D O I
10.1016/j.ocecoaman.2021.106015
中图分类号
P7 [海洋学];
学科分类号
0707 ;
摘要
Automatic identification system (AIS) refers to a new type of navigation aid system equipped in maritime vehicles to monitor ship performance. It provides trajectory information of vessels which can be used for the classification task. The classification results facilitate ocean surveillance and conservation, vessel management enhancement, fishery regulation, marine ecological sustainability, and nautical safety protection. Some progresses have been made based on machine learning or deep learning strategies to perform supervised learning by assuming that during the training process, the category labels of historical trajectory data are available. However, in reality, the label information may be difficult or expensive to obtain, resulting in that only a small part of the training data is labeled, and most of the training data is unlabeled. To address this issue, this paper proposes a semi-supervised deep learning approach to integrate the knowledge of unlabeled data for vessel trajectory classification. Here, we call our approach SSL-VTC. Specifically, we first extract vessel trajectories by integrating the kinematic and static information from historical AIS messages. Then, we design convolutional neural networks to extract feature representations from the vessel trajectories. Finally, we develop a semi-supervised learning algorithm based on the variational autoencoder to perform discriminative learning and generative learning simultaneously. In this way, our SSL-VTC framework can fully leverage the labeled data and unlabeled data during the training process. To the best of our knowledge, we are the first to utilize semi-supervised learning for vessel trajectory classification. Experimental results on the public AIS dataset show that our SSL-VTC can effectively extract feature representations from the AIS messages and its performance is significantly better than the traditional supervised learning methods. The approach and findings of this study provide important implications for researchers and stakeholders in the field of ocean management.
引用
收藏
页数:12
相关论文
共 77 条
[1]   Combining a cumulative risk index and species distribution data to identify priority areas for marine biodiversity conservation in the Black Sea [J].
Almpanidou, Vasiliki ;
Doxa, Aggeliki ;
Mazaris, Antonios D. .
OCEAN & COASTAL MANAGEMENT, 2020, 213
[2]   AN INTRODUCTION TO KERNEL AND NEAREST-NEIGHBOR NONPARAMETRIC REGRESSION [J].
ALTMAN, NS .
AMERICAN STATISTICIAN, 1992, 46 (03) :175-185
[3]   Marine resource management and fisheries governance in Belize exhibit a polycentric, decentralized, and nested institutional structure [J].
Alves, Catherine .
OCEAN & COASTAL MANAGEMENT, 2021, 211
[4]  
Arasteh Saeed, 2020, SIGSPATIAL '20: Proceedings of the 28th International Conference on Advances in Geographic Information Systems, P347, DOI 10.1145/3397536.3422267
[5]   Choose clean energy or green technology? Empirical evidence from global ships [J].
Bai, Xiwen ;
Hou, Yao ;
Yang, Dong .
TRANSPORTATION RESEARCH PART E-LOGISTICS AND TRANSPORTATION REVIEW, 2021, 151
[6]   Comparison of the Coupled Model for Oil spill Prediction (CMOP) and the Oil Spill Contingency and Response model (OSCAR) during the DeepSpill field experiment [J].
Barreto, Fernando T. C. ;
Dammann, Dyre O. ;
Tessarolo, Luciana F. ;
Skancke, Jorgen ;
Keghouche, Intissar ;
Innocentini, Valdir ;
Winther-Kaland, Nina ;
Marton, Luis .
OCEAN & COASTAL MANAGEMENT, 2021, 204
[7]  
Berthelot D, 2019, ADV NEUR IN, V32
[8]   Variational Inference: A Review for Statisticians [J].
Blei, David M. ;
Kucukelbir, Alp ;
McAuliffe, Jon D. .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2017, 112 (518) :859-877
[9]   Assessing the contribution to overfishing of small- and large-scale fisheries in two marine regions as determined by the weight of evidence approach [J].
Canovas-Molina, Almudena ;
Antonio Garcia-Charton, Jose ;
Garcia-Frapolli, Eduardo .
OCEAN & COASTAL MANAGEMENT, 2021, 213
[10]   A ship movement classification based on Automatic Identification System (AIS) data using Convolutional Neural Network [J].
Chen, Xiang ;
Liu, Yuanchang ;
Achuthan, Kamalasudhan ;
Zhang, Xinyu .
OCEAN ENGINEERING, 2020, 218