Skip to main content
SpringerLink
Log in

Exploring autoregression patterns for automatic vessel type classification

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Automatic classification of vessel types in the maritime domain is one of the challenging problems due to the complexity of moving patterns in the ocean that are collected by the Automatic Identification System (AIS). In this study, we explore the usability of different patterns extracted from univariate and multivariate autoregressive modeling for classifying ship types. In order to assess the differentiation power of these features we apply different supervised machine learning classification algorithms and assess the performance of trajectory classification of four different vessel types. In addition, we study the effect of region specification for distinguishing the vessels. The proposed approach produced an accuracy of 86% which confirms that the features obtained from autoregression modeling can identify vessel types effectively. In addition, we demonstrate that the performance of classification can be enhanced further by considering the location of movement.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Data and code availability statement

The AIS data from 2020 used in these experiments is openly available at https://coast.noaa.gov/htdata/CMSP/AISDataHandler/2020/index.html.

Notes

  1. Invalid message is a message that presents negative values of Course Over Ground (COG), COG larger than 360 degrees.

  2. More in-depth details about the underlying mechanisms of each of these classifiers can be found in CM [4]

  3. The seed was fixed as 42 to allow reproducible results.

References

  1. Abdallah NB, Iphar C, Arcieri G, et al (2019) Fixing errors in the ais destination field. In: OCEANS 2019 - Marseille, pp 1–5, https://doi.org/10.1109/OCEANSE.2019.8867139

  2. Brandoli B, Raffaetà A, Simeoni M, et al (2022) From multiple aspect trajectories to predictive analysis: a case study on fishing vessels in the northern adriatic sea. GeoInformatica pp 1–29

  3. Cai J, Chen G, Lützen M et al (2021) A practical ais-based route library for voyage planning at the pre-fixture stage. Ocean Eng 236(109):478. https://doi.org/10.1016/j.oceaneng.2021.109478

    Article  Google Scholar 

  4. CM B (2010) Bishop pattern recognition and machine learning

  5. d’Afflisio E, Braca P, Millefiori LM et al (2018) Detecting anomalous deviations from standard maritime routes using the ornstein-uhlenbeck process. IEEE Trans Signal Process 66(24):6474–6487. https://doi.org/10.1109/TSP.2018.2875887

    Article  MathSciNet  Google Scholar 

  6. Damastuti N, Aisjah AS, Masroeri AA (2019) Classification of ship-based automatic identification systems using k-nearest neighbors. In: 2019 international seminar on application for technology of information and communication (iSemantic), IEEE, pp 331–335

  7. Damastuti N, Aisjah AS, Masroeri A (2021) Vessel classifying and trajectory based on automatic identification system data. In: IOP Conference Series: Earth and Environmental Science, IOP Publishing, p 012049

  8. Ferreira MD, Campbell JN, Matwin S (2022) A novel machine learning approach to analyzing geospatial vessel patterns using ais data. GIScience Remote Sens 59(1):1473–1490

    Article  Google Scholar 

  9. Forti N, Millefiori LM, Braca P et al (2020) Prediction of vessel trajectories from ais data via sequence-to-sequence recurrent neural networks. ICASSP 2020–2020 IEEE International Conference on Acoustics. Speech and Signal Processing (ICASSP), IEEE, pp 8936–8940

    Google Scholar 

  10. Ganesh E, Rajendran V, Ravikumar D et al (2021) Detection and route estimation of ship vessels using linear filtering and arma model from ais data. Int J Oceans Oceanogr 15(1):1–10

    Google Scholar 

  11. He H, Lin Y, Chen F et al (2017) Inshore ship detection in remote sensing images via weighted pose voting. IEEE Trans Geosci Remote Sens 55(6):3091–3107

    Article  Google Scholar 

  12. den Hollander RJ, van Rooij SB, van den Broek SP, et al (2021) Vessel classification for naval operations. In: Artificial intelligence and machine learning in defense applications III, SPIE, pp 115–132

  13. Hyndman RJ, Athanasopoulos G (2018) Forecasting: principles and practice. OTexts

  14. Iphar C, Ray C, Napoli A (2020) Data integrity assessment for maritime anomaly detection. Expert Syst Appl 147(113):219. https://doi.org/10.1016/j.eswa.2020.113219

    Article  Google Scholar 

  15. Kotovirta V, Jalonen R, Axell L et al (2009) A system for route optimization in ice-covered waters. Cold Reg Sci Technol 55(1):52–62. https://doi.org/10.1016/j.coldregions.2008.07.003

    Article  Google Scholar 

  16. Kraus P, Mohrdieck C, Schwenker F (2018) Ship classification based on trajectory data with machine-learning methods. In: 2018 19th international radar symposium (IRS), Universität Ulm

  17. Last P, Hering-Bertram M, Linsen L (2015) How automatic identification system (ais) antenna setup affects ais signal quality. Ocean Eng 100:83–89. https://doi.org/10.1016/j.oceaneng.2015.03.017

    Article  Google Scholar 

  18. Lee H, Lee S, Lee H (2007) The realization of the performance estimation system on ais sotdma algorithm. In: 2007 5th IEEE International Conference on Industrial Informatics, pp 405–410, https://doi.org/10.1109/INDIN.2007.4384791

  19. Lee JG, Han J, Li X et al (2008) Traclass: trajectory classification using hierarchical region-based and trajectory-based clustering. Proc VLDB Endow 1(1):1081–1094

    Article  Google Scholar 

  20. Li B, Morris J, Martin EB (2002) Model selection for partial least squares regression. Chemom Intell Lab Syst 64(1):79–89. https://doi.org/10.1016/S0169-7439(02)00051-5

    Article  Google Scholar 

  21. Li S, Zhou Z, Wang B et al (2016) A novel inshore ship detection via ship head classification and body boundary determination. IEEE Geosci Remote Sens Lett 13(12):1920–1924

    Article  Google Scholar 

  22. Mou JM, Van Der Tak C, Ligteringen H (2010) Study on collision avoidance in busy waterways by using ais data. Ocean Eng 37(5–6):483–490

    Article  Google Scholar 

  23. Ross SM (2014) Introduction to probability models. Academic press

  24. Sánchez Pedroche D, Amigo D, García J et al (2020) Architecture for trajectory-based fishing ship classification with ais data. Sensors 20(13):3782

    Article  Google Scholar 

  25. Shalev-Shwartz S, Ben-David S (2014) Understanding machine learning: from theory to algorithms. Cambridge university press

  26. Sheng K, Liu Z, Zhou D et al (2018) Research on ship classification based on trajectory features. J Navig 71(1):100–116

    Article  Google Scholar 

  27. Styhre L, Winnes H, Black J et al (2017) Greenhouse gas emissions from ships in ports–case studies in four continents. Transp Res Part D: Transp Environ 54:212–224. https://doi.org/10.1016/j.trd.2017.04.033

    Article  Google Scholar 

  28. Vieira FM, Vincent F, Tourneret JY, et al (2016) Ship detection using sar and ais raw data for maritime surveillance. In: 2016 24th European Signal Processing Conference (EUSIPCO), IEEE, pp 2081–2085

  29. Wolsing K, Roepert L, Bauer J et al (2022) Anomaly detection in maritime ais tracks: a review of recent approaches. J Marine Sci Eng 10(1):112

    Article  Google Scholar 

  30. Yan Z, Song X, Zhong H et al (2022) Ship classification and anomaly detection based on spaceborne ais data considering behavior characteristics. Sensors 22(20):7713

    Article  Google Scholar 

  31. Yang G, Li B, Ji S et al (2013) Ship detection from optical satellite images based on sea surface analysis. IEEE Geosci Remote Sens Lett 11(3):641–645

    Article  Google Scholar 

  32. Yang T, Wang X, Liu Z (2022) Ship type recognition based on ship navigating trajectory and convolutional neural network. J Marine Sci Eng 10(1):84

    Article  Google Scholar 

  33. Zg Zhang, Jc Yin, Nn Wang et al (2019) Vessel traffic flow analysis and prediction by an improved pso-bp mechanism based on ais data. Evol Syst 10:397–407

    Article  Google Scholar 

  34. Zhao X, Qian G (2014) On multivariate time series model selection involving many candidate var models. Eur J Pure Appl Math 7(1):1–21

    MathSciNet  Google Scholar 

  35. Zhou Y, Daamen W, Vellinga T et al (2019) Ship classification based on ship behavior clustering from ais data. Ocean Eng 175:176–187

    Article  Google Scholar 

Download references

Acknowledgements

We would like to thank Lubna Eljabu for helping us to manage the dataset.

Funding

We acknowledge the support of the Natural Sciences and Engineering Research Council of Canada (NSERC-Grant No. 550722).

Author information

Author notes

  1. Martha Dais Ferreira, Zahra Sadeghi have contributed equally to this work.

Authors and Affiliations

  1. Faculty of Computer Science, Dalhousie University, Halifax, Canada

    Martha Dais Ferreira, Zahra Sadeghi & Stan Matwin

Authors
  1. Martha Dais Ferreira
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zahra Sadeghi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Stan Matwin
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

M.F. and Z.S. contributed to the conceptualization; M.F. and Z.S. were involved in the methodology; M.F. and Z.S. contributed to the software; M.F., Z.S., and S.M. were involved in the validation; M.F. and Z.S. assisted in the formal analysis; M.F. and Z.S. were involved in the investigation; S.M. contributed to the resources; M.F. and Z.S. were involved in the data curation; M.F. and Z.S. assisted in the writing—original draft preparation; M.F., Z.S., and S.M. assisted in the writing—review and editing; M.F. and Z.S. contributed to the visualization; S.M. was involved in the supervision; S.M. assisted in the project administration; S.M. was involved in the funding acquisition. All authors have read and agreed to the published version of the manuscript.

Corresponding author

Correspondence to Martha Dais Ferreira.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Ethical Approval

Not Applicable

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ferreira, M.D., Sadeghi, Z. & Matwin, S. Exploring autoregression patterns for automatic vessel type classification. J Supercomput 80, 9532–9553 (2024). https://doi.org/10.1007/s11227-023-05826-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-023-05826-8

Keywords

Search

Navigation