Detecting Potential Vessel Loitering Behavior from Ship Trajectories Using a Hybrid Rule-Based and Neural Network Approach
Keywords:
Automatic identification system, ship trajectory, loitering, rule-based, neural networkAbstract
Vessel loitering behavior is one of the essential indicators in detecting suspicious maritime activities, such as illegal fishing, smuggling, and territorial waters violations. Loitering is characterized by slow movements and random changes in direction and lasts for an extended period. This research aims to automatically identify potential vessel loitering behavior based on trajectory data from the Automatic Identification System (AIS) with a hybrid approach that combines rule-based methods and neural network models. AIS data is collected from Udayana University Receiver Base Station within a specific period and consists of millions of ship position data. The initial process includes data cleansing, trajectory extraction, trajectory cleaning, and loitering feature extraction based on temporal and spatial parameters. A rule based approach is used to identify loitering candidates at the loitering extraction stage, which is used to label trajectory data as loitering or not. The labeled data is then trained to automatically train a neural network-based classification model to recognize loitering patterns. The model evaluation results showed excellent performance, with accuracy, precision, recall, and F1-score on the test data.References
W. M. Wijaya dan Y. Nakamura, “Loitering behavior detection by spatiotemporal characteristics quantification based on the dynamic features of Automatic Identification System (AIS) messages,” PeerJ Comput. Sci., vol. 9, 2023, doi: 10.7717/peerj-cs.1572.
Z. Zhang, L. Huang, X. Peng, Y. Wen, dan L. Song, “Loitering behavior detection and classification of vessel movements based on trajectory shape and Convolutional Neural Networks,” Ocean Eng., vol. 258, 2022, doi: 10.1016/j.oceaneng.2022.111852.
R. K. Sira, I. M. Tanjavur, M. S. Guru Prasad, A. Rajan, Laxman, dan T. G. Mohan Kumar, “A Comprehensive Approach for Detecting and Classifying Loitering Events in Fishing Vessels Using Supervised and Semi-Supervised Learning,” 2023, doi: 10.1109/ASIANCON58793.2023.10269886.
A. A. Masroeri, A. S. Aisjah, V. Agam, M. Pradenta, dan M. A. Samudya, “Analysis of fuzzy logic systems types 1 and 2 in identifying of IUU fishing and transshipment: a case study in Indonesia’s vulnerable waters,” IOP Conf. Ser. Earth Environ. Sci., vol. 972, no. 1, hal. 12060, 2022, doi: 10.1088/1755-1315/972/1/012060.
L. Deng, Y. Niu, L. Jia, W. Liu, dan Y. Zang, “A Hybrid Rule-Based and Data-Driven Approach to Illegal Transshipment Identification with Interpretable Behavior Features,” Sensors, vol. 22, no. 24. 2022, doi: 10.3390/s22249581.
K. Boerder, N. A. Miller, dan B. Worm, “Global hot spots of transshipment of fish catch at sea,” Sci. Adv., vol. 4, no. 7, 2018, doi: 10.1126/sciadv.aat7159.
P. Bernabé, A. Gotlieb, B. Legeard, D. Marijan, F. Sem-Jacobsen, dan H. Spieker, “Detecting Intentional AIS Shutdown in Open Sea Maritime Surveillance Using Self-Supervised Deep Learning,” IEEE Trans. Intell. Transp. Syst., 2023, doi: 10.1109/TITS.2023.3322690.
F. Mazzarella, M. Vespe, A. Alessandrini, D. Tarchi, G. Aulicino, dan A. Vollero, “A novel anomaly detection approach to identify intentional AIS on-off switching,” Expert Syst. Appl., vol. 78, 2017, doi: 10.1016/j.eswa.2017.02.011.
A. Nurfalah, S. H. Supangkat, dan E. Mulyana, “Real-Time AIS Anomaly Detection in Maritime Tactical Data System Using AIS/Radar Track Association Approach,” 2023, doi: 10.1109/ICISS59129.2023.10291906.
D. Anne, Suhardi, dan W. Muhamad, “Prediction of Ship Track Anomaly based on AIS data using Long Short-Term Memory (LSTM) and DBSCAN,” 2022, doi: 10.1109/ICITSI56531.2022.9970940.
G. Huang, S. Lai, C. Ye, dan H. Zhou, “Ship trajectory anomaly detection based on multi-feature fusion,” 2021, doi: 10.1109/SMDS53860.2021.00020.
M. P. Handayani, G. Antariksa, dan J. Lee, “Anomaly detection in vessel sensors data with unsupervised learning technique,” 2021, doi: 10.1109/ICEIC51217.2021.9369822.
B. Zhang, H. Ren, P. Wang, dan D. Wang, “Research Progress on Ship Anomaly Detection Based on Big Data,” in Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS, 2020, vol. 2020-October, doi: 10.1109/ICSESS49938.2020.9237642.
L. Xie dkk., “A novel model for ship trajectory anomaly detection based on gaussian mixture variational autoencoder,” IEEE Trans. Veh. Technol., vol. 72, no. 11, 2023, doi: 10.1109/TVT.2023.3284908.
C. Zhang, S. Liu, M. Guo, dan Y. Liu, “A novel ship trajectory clustering analysis and anomaly detection method based on AIS data,” Ocean Eng., vol. 288, hal. 116082, Nov 2023, doi: 10.1016/J.OCEANENG.2023.116082.
Z. Wang, M. K. Dahouda, H. Hwang, dan I. Joe, “Explanatory LSTM-AE-Based Anomaly Detection for Time Series Data in Marine Transportation,” IEEE Access, vol. 13, hal. 23195–23208, 2025, doi: 10.1109/ACCESS.2025.3535695.
K. Leon-López, S. Fabre, F. Manzoni, L. Mirambell, dan J.-Y. Tourneret, “A Multiscale Anomaly Detection Framework for AIS Trajectories via Heat Graph Laplacian Diffusion,” in 2024 32nd European Signal Processing Conference (EUSIPCO), 2024, hal. 2337–2341, doi: 10.23919/EUSIPCO63174.2024.10715305.
P. Zhao, S. Qin, A. Bai, dan J. Yang, “A CAE-Based Method for Anomaly Detection in Ship Trajectories,” in 2024 9th International Conference on Intelligent Computing and Signal Processing (ICSP), 2024, hal. 1709–1713, doi: 10.1109/ICSP62122.2024.10743945.
