Abstract
The traditional modeling method of ship trajectory data is unable to deal with multiple features or ignore the temporal relationship. Moreover, due to the problems of data imbalance and lack of data labels, it is a great challenge to build ship behavior analysis and anomaly detection models based on trajectory data. Based on transfer learning and Transformer architecture, this paper proposes an anomaly detection method for adaptive Transformer model fitting trajectory timing distribution characteristics. Firstly, the trajectory data are preprocessed to simulate the characterization relationship of time-series data. Multiple different subsequences are divided by quantization of temporal distribution similarity and matching of temporal distribution. From the perspective of transfer learning, each subsequence is regarded as multiple source domains of independent distribution. The distribution correlation weight evaluation method is used to learn and fit the distribution characteristics of subsequences, to effectively describe the similarity and correlation effects between the distributions of each subsequence. At the same time, the attention mechanism is used to build the dynamic training Transformer network structure, mining the dependencies between data points in the sequence, and realizing a domain adaptive model that can effectively fit the multivariate characteristics of trajectory data. Finally, the anomaly detection task is completed by calculating the anomaly error. The example verification shows that, compared with the existing model, the model in this paper can more accurately realize the modeling of the normal trajectory motion characteristics, lay a foundation for the trajectory anomaly detection, and show a certain practical and engineering application value.
Kexin Li (1998-), master student.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang: Construction of intelligent transportation platform based on 5G vehicle network. Commun. Inf. Technol. (S2), 28–31 (2022)
Feng, W.: Exploration of 5G ultra-remote coverage technology and application scenarios. Commun. World 16, 47–49 (2022)
Theodoropoulos, P., Spandonidis, C.C., Giannopoulos, F., Fassois, S.: A deep learning-based fault detection model for optimization of shipping operations and enhancement of maritime safety. Sensors 21(16), 5658 (2021)
Tu, E., Zhang, G., Rachmawati, L., Rajabally, E., Huang, G.B.: Exploiting AIS data for intelligent maritime navigation: a comprehensive survey from data to methodology. IEEE Trans. Intell. Transp. Syst. 19(5), 1559–1582 (2017)
Lee, W., Cho, S.W.: AIS trajectories simplification algorithm considering topographic information. Sensors 22(18), 7036 (2022)
Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. (CSUR) 41(3), 1–58 (2009)
Gupta, M., Gao, J., Aggarwal, C.C., Han, J.: Outlier detection for temporal data: a survey. IEEE Trans. Knowl. Data Eng. 26(9), 2250–2267 (2013)
Liu, H., Li, X., Li, J., Zhang, S.: Efficient outlier detection for high-dimensional data. IEEE Trans. Syst. Man Cybern. Syst. 48(12), 2451–2461 (2017)
Zhang, Z., Zhu, M., Qiu, J., Liu, C., Zhang, D., Qi, J.: Outlier detection based on cluster outlier factor and mutual density. In: Peng, Hu., Deng, C., Wu, Z., Liu, Y. (eds.) ISICA 2018. CCIS, vol. 986, pp. 319–329. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-6473-0_28
Liu, H., Qiao, Y., Zhao, G., Cheng, J., Meng, Z.: Agricultural machinery abnormal trajectory recognition. Int. J. Mach. Learn. Comput. 11(4), 291–297 (2021)
Qiao, Z., Zhao, L., Gu, L., Jiang, X., Li, R., Ge, L.: Research on abnormal pedestrian trajectory detection of dynamic crowds in public scenarios. IEEE Sens. J. 21(20), 23046–23054 (2021)
Du, X., Yu, J., Chu, Z., Jin, L., Chen, J.: Graph autoencoder-based unsupervised outlier detection. Inf. Sci. 608, 532–550 (2022)
Wu, H., Tang, X., Wang, Z., Wang, N.: Uncovering abnormal behavior patterns from mobility trajectories. Sensors 21(10), 3520 (2021)
Meng, Tang, Wang: LSTM-AdaBoost vehicle trajectory prediction model considering lane change intention. Comput. Eng. Appl. 58(13), 280–287 (2022)
Wan, Pan, Zhen, Ship: Ship trajectory prediction based on CNN-GRU. J. Guangzhou Inst. Navig. 30(02), 12–18 (2022)
Cheng: Research on Collision Avoidance and Trajectory Prediction Technology of Aircraft Based on Machine Learning. Nanjing University of Posts and Telecommunications (2022)
Wang, Yuan, Li, Xiao: Ship trajectory prediction and navigation intention recognition in intersection waters. Traffic Inf. Saf. 40(04), 101–109 (2022)
Miguel, Á.D.M., José, M.A., Fernando, G.: Vehicles trajectory prediction using recurrent VAE network. IEEE Access 10, 32742–32749 (2022)
Lv, Z., Huang, X., Cao, W.: An improved GAN with transformers for pedestrian trajectory prediction models. Int. J. Intell. Syst. 37(8), 4417–4436 (2022)
Chen, Zhu, Yan: Ship track prediction based on LSTM. Mar. Eng. (06), 121–125 (2019)
Lu, J., Liu, A., Dong, F., Gu, F., Gama, J., Zhang, G.: Learning under concept drift: a review. IEEE Trans. Knowl. Data Eng. 31(12), 2346–2363 (2018)
Bertsimas, D., Sim, M., Zhang: Adaptive distributionally robust optimization. Manag. Sci. 65(2), 604–618 (2019)
Borgwardt, K.M., Gretton, A., Rasch, M.J.: Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics 22(14), 49–57 (2006)
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 Switzerland AG
About this paper
Cite this paper
Li, K. et al. (2023). The Abnormal Detection Method of Ship Trajectory with Adaptive Transformer Model Based on Migration Learning. In: Meng, X., et al. Spatial Data and Intelligence. SpatialDI 2023. Lecture Notes in Computer Science, vol 13887. Springer, Cham. https://doi.org/10.1007/978-3-031-32910-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-32910-4_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-32909-8
Online ISBN: 978-3-031-32910-4
eBook Packages: Computer ScienceComputer Science (R0)