Skip to main content
SpringerLink
Log in

LSTM vs CNN in Real Ship Trajectory Classification

  • Conference paper
  • First Online:
16th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2021) (SOCO 2021)

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 1401))

Abstract

Ship type identification in a maritime context can be critical to the authorities to control the activities being carried out. Although Automatic Identification Systems (AIS) has been mandatory for certain vessels if a vessel does not have them voluntarily or not, it can lead to a whole set of problems, so the use of tracking alternatives such as radar is fully complementary. However, radars provide positions, but not what they are detecting. Having systems capable of adding categorical information to radar detections of vessels makes it possible to increase control of the activities being carried out, improve safety in maritime traffic, and optimize on-site inspection resources on the part of the authorities. This paper addresses the binary classification problem (fishing ships versus all other vessels) using unbalanced data from real vessel trajectories. It is performed from a Deep Learning (DL) approach comparing two of the main trends, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM). In this paper it is proposed the weighted Cross-Entropy (WCE) methodology and compared with classical data balancing strategies. Both networks show high performance when applying WCE compared to the classical machine learning approaches and classical balancing techniques. This work is shown to be a novel approach to the international problem of identifying fishing ships without contexts.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 219.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 279.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Reference

  1. Upton, S., Vitalis, V.: Stopping the high seas robbers: coming to grips with illegal, unreported and unregulated fisheries on the high seas. In: Round Table on Sustainable Devlopment. The Sustainable Dev. Glob. Fish. with Part. Ref. to Enforc. [Against Illegal, Unreport. Unregulated Fish. High Seas, p. 18, 06 June 2003

    Google Scholar 

  2. Tai, T.H., Kao, S.M., Ho, W.C.: International soft laws against IUU fishing for sustainable marine resources: adoption of the voluntary guidelines for flag state performance and challenges for Taiwan. Sustainability 12(15) (2020)

    Google Scholar 

  3. Ilnyckyj, M.: The legality and sustainability of European Union fisheries policy in West Africa. MIT Int. Rev. 33–41 (2007)

    Google Scholar 

  4. E. Commission: International fisheries relations/Fact Sheets on the European Union/European Parliament (2021). https://www.europarl.europa.eu/factsheets/en/sheet/119/international/fisheries/relations. Accessed 08 June 2021

  5. Food and Agriculture Organization of the United Nations. The fight to save our oceans/FAO Stories/Food and Agriculture Organization of the United Nations (2021). http://www.fao.org/fao-stories/article/en/c/1136937. Accessed 08 June 2021

  6. Sumaila, U.R., Zeller, D., Hood, L., Palomares, M.L.D., Li, Y., Pauly, D.: Illicit trade in marine fish catch and its effects on ecosystems and people worldwide. Sci. Adv. 6(9) (2020)

    Google Scholar 

  7. Pedroche, D.S., Amigo, D., García, J., Molina, J.M.: Architecture for trajectory-based fishing ship classification with AIS data. Sensors (Switzerland) 20(13), 1–21 (2020)

    Google Scholar 

  8. Danish Maritime Authority: AIS data sets. AIS data (2021). https://dma.dk/SikkerhedTilSoes/Sejladsinformation/AIS/Sider/default.aspx. Accessed 07 June 2021

  9. Salvadorrgarcíaa, A., Pratii, M.R., Franciscooherrera, B.: Learning from Imbalanced Data Sets. Springer, Heidelberg (2018)

    Google Scholar 

  10. Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. Ecol. Appl. 30(2), 321–357 (2020)

    MATH  Google Scholar 

  11. Kraus, P., Mohrdieck, C., Schwenker, F.: Ship classification based on trajectory data with machine-learning methods. In: Proceedings International Radar Symposium, vol. 2018, pp. 1–10, June 2018

    Google Scholar 

  12. Kontopoulos, I., Chatzikokolakis, K., Tserpes, K., Zissis, D.: Classification of vessel activity in streaming data. In: DEBS 2020 – Proceedings of the 14th ACM International Conference on Distributed and Event-Based Systems, pp. 153–164 (2020)

    Google Scholar 

  13. Sheng, K., Liu, Z., Zhou, D., He, A., Feng, C.: Research on ship classification based on trajectory features. J. Navig. 71(1), 100–116 (2018)

    Article  Google Scholar 

  14. Ljunggren, H.: Using deep learning for classifying ship trajectories. In: 2018 21st International Conference on Information Fusion, FUSION 2018, pp. 2158–2164 (2018)

    Google Scholar 

  15. Kim, K., Lee, K.M.: Convolutional neural network-based gear type identification from automatic identification system trajectory data. Appl. Sci. 10(11), 4010 (2020)

    Google Scholar 

  16. Hochreiter, S., Urgen Schmidhuber, J.: Long short-term Memory. Neural Comput. 9(8), 1735–1780 (1997)

    Google Scholar 

  17. Srisukkham, W., Pipanmaekaporn, L., Kamonsantiroj, S.: A recurrent neural network model for detecting fishing gear patterns. ICIC Express Lett. 15(6), 627–637 (2021)

    Google Scholar 

  18. Zhou, X., Liu, Z., Wang, F., Xie, Y., Zhang, X.: Using deep learning to forecast maritime vessel flows. Sensors (Switzerland) 20(6), 1–17 (2020)

    Google Scholar 

  19. Ye, Q., Shu, L., Zhang, W.: Extrinsic calibration of a monocular camera and a single line scanning LiDAR. In: Proceedings of 2019 IEEE International Conference on Mechatronics Automation ICMA 2019, pp. 1047–1054 (2019)

    Google Scholar 

  20. Swetha, S., Balasubramanian, V.N., Jawahar, C.V.: Sequence-to-sequence learning for human pose correction in videos. In: Proceedings of 4th Asian Conference on Pattern Recognition, ACPR 2017, pp. 268–273 (2018)

    Google Scholar 

  21. Núñez, J.C., Cabido, R., Vélez, J.F., Montemayor, A.S., Pantrigo, J.J.: Multiview 3D human pose estimation using improved least-squares and LSTM networks. Neurocomputing 323, 335–343 (2019)

    Article  Google Scholar 

  22. Ho, Y., Wookey, S.: The real-world-weight cross-entropy loss function: modeling the costs of mislabeling. IEEE Access. 8, 4806–4813 (2020)

    Article  Google Scholar 

  23. Aurelio, Y.S., de Almeida, G.M., de Castro, C.L., Braga, A.P.: Learning from imbalanced data sets with weighted cross-entropy function. Neural Process. Lett. 50(2), 1937–1949 (2019). https://doi.org/10.1007/s11063-018-09977-1

    Article  Google Scholar 

  24. Rezaei-Dastjerdehei, M.R., Mijani, A., Fatemizadeh, E.: Addressing imbalance in multi-label classification using weighted cross entropy loss function. In: 27th National and 5th International Conference of Biomedical Engineering ICBME 2020, pp. 333–338, November 2020

    Google Scholar 

  25. Rudy, S.H., Nathan Kutz, J., Brunton, S.L.: Deep learning of dynamics and signal-noise decomposition with time-stepping constraints. J. Comput. Phys. 396, 483–506 (2019)

    Google Scholar 

  26. Llerena, J.P.L., Herrero, J.G., Molina, J.M.M.: Forecasting nonlinear systems with LSTM: analysis and comparison with EKF. Sensors 21(5), 1–29 (2021)

    Article  Google Scholar 

  27. Beale, M.H., Hagan, M.T., Demuth, H.B.: Neural Network ToolboxTM User’s Guide R2013b. Mathworks Inc., Natick (2013)

    Google Scholar 

  28. Krizhevsky, B.A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2012)

    Article  Google Scholar 

  29. Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: 3rd International Conference Learning Representations ICLR 2015 - Conference Track Proceeding, pp. 1–15 (2015)

    Google Scholar 

  30. Song, X., et al.: Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model. J. Pet. Sci. Eng. 186, 106682 (2019)

    Google Scholar 

  31. Rezaei-Dastjerdehei, M.R., Mijani, A., Fatemizadeh, E.: Addressing imbalance in multi-label classification using weighted cross entropy loss function. In: 27th National and 5th International Iranian Conference of Biomedical Engineering, ICBME 2020, pp. 333–338 (2020)

    Google Scholar 

Download references

Acknowledgments

We would like to thank David Sánchez and Daniel Amigo for sharing a set of trajectories used in their published work [7].

Funding

This research was funded by public research projects of Spanish Ministry of Economy and Competitivity (MINECO), reference TEC2017‐88048‐C2‐2‐R and by the Madrid Government under the Multiannual Agreement with UC3M in the line of Excellence of University Professors (EPUC3M17), and in the context of the V PRICIT (Regional Program of Research and Technological Innovation). This work has been supported by the Madrid Government (Comunidad de Madrid-Spain) under the Multiannual Agreement with UC3M in the line of Excellence of University Professors (EPUC3MXX), and in the context of the V PRICIT (Regional Programme of Research and Technological Innovation).

Author information

Authors and Affiliations

  1. GIAA Group, Universidad Carlos III de Madrid, 28231, Madrid, Spain

    Juan Pedro Llerena, Jesús García & José Manuel Molina

Authors
  1. Juan Pedro Llerena
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jesús García
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. José Manuel Molina
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Juan Pedro Llerena .

Editor information

Editors and Affiliations

  1. Faculty of Engineering, University of Deusto, Bilbao, Spain

    Hugo Sanjurjo González

  2. Faculty of Engineering, University of Deusto, Bilbao, Spain

    Iker Pastor López

  3. Faculty of Engineering, University of Deusto, Bilbao, Spain

    Pablo García Bringas

  4. Department of Industrial Engineering, University of A Coruña, Ferrol, Spain

    Héctor Quintián

  5. BISITE Research Group, University of Salamanca, Salamanca, Spain

    Emilio Corchado

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Llerena, J.P., García, J., Molina, J.M. (2022). LSTM vs CNN in Real Ship Trajectory Classification. In: Sanjurjo González, H., Pastor López, I., García Bringas, P., Quintián, H., Corchado, E. (eds) 16th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2021). SOCO 2021. Advances in Intelligent Systems and Computing, vol 1401. Springer, Cham. https://doi.org/10.1007/978-3-030-87869-6_6

Download citation

Publish with us

Policies and ethics

Search

Navigation