Abstract
Ship trajectory data contains a lot of valuable information, but abnormal data is inevitably generated in the process of data acquisition. A Temporal Convolutional Network (TCN) model-based method for detecting ship trajectory anomalies is proposed in this paper to avoid adverse effects on subsequent data analysis. First, a sliding time window algorithm is designed to extract the trajectory-subsequence because ship trajectories are time-series data. Then input the normal trajectory to train the TCN model. The model will learn the kinematic characteristics of the normal trajectory. When inputting an abnormal trajectory, the model reconstructs the anomalous trajectory and detects the anomaly by the reconstruction error. In addition, the multi-dimensional features of the trajectory are analyzed, and the identification of anomalies is based on the reconstruction error of each feature. With a recall of 93.51 and an F1 score of 0.913, the algorithm has significantly improved its performance in comparison with the LSTM model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Mao, S., Tu, E., Zhang, G., Rachmawati, L., Rajabally, E., Huang, G.-B.: An automatic identification system (AIS) database for maritime trajectory prediction and data mining. In: Cao, J., Cambria, E., Lendasse, A., Miche, Y., Vong, C.M. (eds.) Proceedings of ELM-2016. PALO, vol. 9, pp. 241–257. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-57421-9_20
Shi, J.H., Liu, Z.J.: Deep learning in unmanned surface vehicles collision-avoidance pattern based on AIS big data with double GRU-RNN. J. Mar. Sci. Eng. 8(9), 682 (2020)
Murray, B., Perera, L.P.: A dual linear autoencoder approach for vessel trajectory prediction using historical AIS data. Ocean Eng. 209, 107478 (2020)
Gaglione, D., et al.: Bayesian information fusion and multitarget tracking for maritime situational awareness. IET Radar Sonar Navig. 14(12), 1845–1857 (2020)
Zhou, Y., Daamen, W., Vellinga, T., Hoogendoorn, S.P.: Ship classification based on ship behavior clustering from AIS data. Ocean Eng. 175, 176–187 (2019)
Wu, J., Wu, C., Liu, W., Guo, J.: Automatic detection and restoration algorithm for trajectory anomalies of ship AIS. Navig. China 40(1), 8–12 (2017)
Han, J., Pei, J., Kamber, M.: Data Mining: Concepts and Techniques. Elsevier (2011)
Zhu, J., Jiang, W., Liu, A., Liu, G., Zhao, L.: Effective and efficient trajectory outlier detection based on time-dependent popular route. World Wide Web 20(1), 111–134 (2016). https://doi.org/10.1007/s11280-016-0400-6
Barnett, V., Lewis, T.: Outliers in Statistical Data, 3rd edn. John Wiley & Sons, Chichester (1994)
Knorr, E.M., Ng, R.T.: Finding intensional knowledge of distance-based outliers. In: Vldb. Citeseer, vol. 99, pp. 211–222 (1999)
Nguyen, H., Tran, K.P., Thomassey, S., Hamad, M.: Forecasting and Anomaly Detection approaches using LSTM and LSTM Autoencoder techniques with the applications in supply chain management. Int. J. Inf. Manage. 57, 102282 (2021)
Liu, H., Liu, Y., Li, B., Qi, Z.: Ship abnormal behavior detection method based on optimized GRU network. J. Mar. Sci. Eng. 10(2), 249 (2022)
Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. ar**v preprint ar**v:1803.01271 (2018)
Yan, J., Mu, L., Wang, L., Ranjan, R., Zomaya, A.Y.: Temporal convolutional networks for the advance prediction of ENSO. Sci. Rep. 10(1), 1–15 (2020)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. ar**v preprint ar**v:1511.07122 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hao, J., Zhang, H. (2023). Ship Trajectory Anomaly Detection Based on TCN Model. In: Yan, L., Duan, H., Deng, Y. (eds) Advances in Guidance, Navigation and Control. ICGNC 2022. Lecture Notes in Electrical Engineering, vol 845. Springer, Singapore. https://doi.org/10.1007/978-981-19-6613-2_341
Download citation
DOI: https://doi.org/10.1007/978-981-19-6613-2_341
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-6612-5
Online ISBN: 978-981-19-6613-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)