Deep Learning for Vessel Trajectory Prediction Using Clustered AIS Data
Accurate vessel track prediction is key for maritime traffic control and management. Accurate prediction results can enable collision avoidance, in addition to being suitable for planning routes in advance, shortening the sailing distance, and improving navigation efficiency. Vessel track prediction...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/16/2936 |
| _version_ | 1797431961610878976 |
|---|---|
| author | Cheng-Hong Yang Guan-Cheng Lin Chih-Hsien Wu Yen-Hsien Liu Yi-Chuan Wang Kuo-Chang Chen |
| author_facet | Cheng-Hong Yang Guan-Cheng Lin Chih-Hsien Wu Yen-Hsien Liu Yi-Chuan Wang Kuo-Chang Chen |
| author_sort | Cheng-Hong Yang |
| collection | DOAJ |
| description | Accurate vessel track prediction is key for maritime traffic control and management. Accurate prediction results can enable collision avoidance, in addition to being suitable for planning routes in advance, shortening the sailing distance, and improving navigation efficiency. Vessel track prediction using automatic identification system (AIS) data has attracted extensive attention in the maritime traffic community. In this study, a combining density-based spatial clustering of applications with noise (DBSCAN)-based long short-term memory (LSTM) model (denoted as DLSTM) was developed for vessel prediction. DBSCAN was used to cluster vessel tracks, and LSTM was then used for training and prediction. The performance of the DLSTM model was compared with that of support vector regression, recurrent neural network, and conventional LSTM models. The results revealed that the proposed DLSTM model outperformed these models by approximately 2–8%. The proposed model is able to provide a better prediction performance of vessel tracks, which can subsequently improve the efficiency and safety of maritime traffic control. |
| first_indexed | 2024-03-09T09:52:54Z |
| format | Article |
| id | doaj.art-6e0418d035574bec9eeb99f33d3a913f |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T09:52:54Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-6e0418d035574bec9eeb99f33d3a913f2023-12-01T23:57:39ZengMDPI AGMathematics2227-73902022-08-011016293610.3390/math10162936Deep Learning for Vessel Trajectory Prediction Using Clustered AIS DataCheng-Hong Yang0Guan-Cheng Lin1Chih-Hsien Wu2Yen-Hsien Liu3Yi-Chuan Wang4Kuo-Chang Chen5Department of Information Management, Tainan University of Technology, Tainan 71002, TaiwanDepartment of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, TaiwanDepartment of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, TaiwanDepartment of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, TaiwanDepartment of Business Administration, CTBC Business School, Tainan 709, TaiwanDepartment of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, TaiwanAccurate vessel track prediction is key for maritime traffic control and management. Accurate prediction results can enable collision avoidance, in addition to being suitable for planning routes in advance, shortening the sailing distance, and improving navigation efficiency. Vessel track prediction using automatic identification system (AIS) data has attracted extensive attention in the maritime traffic community. In this study, a combining density-based spatial clustering of applications with noise (DBSCAN)-based long short-term memory (LSTM) model (denoted as DLSTM) was developed for vessel prediction. DBSCAN was used to cluster vessel tracks, and LSTM was then used for training and prediction. The performance of the DLSTM model was compared with that of support vector regression, recurrent neural network, and conventional LSTM models. The results revealed that the proposed DLSTM model outperformed these models by approximately 2–8%. The proposed model is able to provide a better prediction performance of vessel tracks, which can subsequently improve the efficiency and safety of maritime traffic control.https://www.mdpi.com/2227-7390/10/16/2936automatic identification systemdensity-based spatial clustering of applications with noiselong short-term memory |
| spellingShingle | Cheng-Hong Yang Guan-Cheng Lin Chih-Hsien Wu Yen-Hsien Liu Yi-Chuan Wang Kuo-Chang Chen Deep Learning for Vessel Trajectory Prediction Using Clustered AIS Data Mathematics automatic identification system density-based spatial clustering of applications with noise long short-term memory |
| title | Deep Learning for Vessel Trajectory Prediction Using Clustered AIS Data |
| title_full | Deep Learning for Vessel Trajectory Prediction Using Clustered AIS Data |
| title_fullStr | Deep Learning for Vessel Trajectory Prediction Using Clustered AIS Data |
| title_full_unstemmed | Deep Learning for Vessel Trajectory Prediction Using Clustered AIS Data |
| title_short | Deep Learning for Vessel Trajectory Prediction Using Clustered AIS Data |
| title_sort | deep learning for vessel trajectory prediction using clustered ais data |
| topic | automatic identification system density-based spatial clustering of applications with noise long short-term memory |
| url | https://www.mdpi.com/2227-7390/10/16/2936 |
| work_keys_str_mv | AT chenghongyang deeplearningforvesseltrajectorypredictionusingclusteredaisdata AT guanchenglin deeplearningforvesseltrajectorypredictionusingclusteredaisdata AT chihhsienwu deeplearningforvesseltrajectorypredictionusingclusteredaisdata AT yenhsienliu deeplearningforvesseltrajectorypredictionusingclusteredaisdata AT yichuanwang deeplearningforvesseltrajectorypredictionusingclusteredaisdata AT kuochangchen deeplearningforvesseltrajectorypredictionusingclusteredaisdata |