Advertisement

Evolving Systems

, Volume 7, Issue 1, pp 29–40 | Cite as

Real-time vessel behavior prediction

  • Dimitrios ZissisEmail author
  • Elias K. Xidias
  • Dimitrios Lekkas
Original Paper

Abstract

Vessel traffic management systems (VTMS) and vessel traffic monitoring information systems (VTMIS) have been available for a number of years now. These systems have significantly contributed to increasing the efficiency and safety of operations at sea. However, nowadays, risks at sea are once again on the rise, thus demanding an evolution in VTMS and VTMIS, such that they can support a human operator’s better understanding of the complex reality at sea and enhance his or her decision-making in light of danger. A critical requirement of such systems, is that they exhibit the ability to for-see unfolding cautious and potentially hazardous situations, so as to propose measures of danger avoidance. In this study, we employ machine learning, and specifically artificial neural networks, as a tool to add predictive capacity to VTMIS. The main objective of this study is to implement a publicly accessible, web-based system capable of real time learning and accurately predicting any vessels future behavior in low computational time. This work describes our approach, design choices, implementation and evaluation details, while we present a proof of concept prototype system. Our proposal can potentially be used as the predictive foundation for various intelligent systems, including vessel collision prevention, vessel route planning, operation efficiency estimation and even anomaly detection systems.

Keywords

Vessel behavior prediction Machine learning Web based intelligent systems Artificial neural networks Web based machine learning Applied soft computing MarineTraffic 

Notes

Acknowledgments

This work was supported in part by MarineTraffic Research.

References

  1. ANAVE (2013) Merchant marine and maritime transport 2012/2013Google Scholar
  2. Azoff EM (1994) Neural network time series forecasting of financial marketsGoogle Scholar
  3. Bevilacqua V (2006) Hidden markov models for recognition using artificial neural networks. International conference of intellignet computing. Springer, Berlin, p 1331Google Scholar
  4. Bomberger N, Rhodes B, Seibert M, Waxman A (2006) Associative learning of vessel motion patterns for maritime situation awareness. 2006 9th international conference information fusion. IEEE, pp 1–8Google Scholar
  5. Box GEP, Jenkins GM, Reinsel GC (1994) Time series analysis, forecasting and control, 3rd edn. Englewood Cliffs, Prentice HallGoogle Scholar
  6. Braga AP, Ludermir TB, Carvalho ACPLF (2000) Artificial neural networks. LTC, Rio de Janeiro Google Scholar
  7. Cai Q, He H, Man H (2013) Spatial outlier detection based on iterative self-organizing learning model. Neurocomputing 117:161–172. doi: 10.1016/j.neucom.2013.02.007 CrossRefGoogle Scholar
  8. Chadwick J, Snyder T, Panda H (2012) Programming ASP.NET MVC 4: developing Real-world web applications with ASP.NET MVC. p 492Google Scholar
  9. Ebada AMAM (2005) Prediction of ship turning manoeuvre using artificial neural networks. 8th Numer. Towing Tank SympGoogle Scholar
  10. Endsley MR (1988) Design and evaluation for situation awareness enhancement. Proc Hum Factors Ergon Soc Annu Meet 32:97–101. doi: 10.1177/154193128803200221 Google Scholar
  11. Galloway J, Haack P, Wilson B, Allen KS (2012) Professional ASP.NET MVC 4 (Wrox Professional Guides). p 504Google Scholar
  12. Gomes GSS, Ludermir TB (2013) Optimization of the weights and asymmetric activation function family of neural network for time series forecasting. Expert Syst Appl 40:6438–6446CrossRefGoogle Scholar
  13. Gomes L, Faria P, Morais H et al (2014) Distributed, agent-based intelligent system for demand response program simulation in smart grids. IEEE Intell Syst 29:56–65. doi: 10.1109/MIS.2013.2 Google Scholar
  14. Heaton J (2008) Introduction to neural networks for C#, 2nd Edn. Heaton Research, p 428. http://www.amazon.com/Introduction-Neural-Networks-2nd-Edition/dp/1604390093
  15. Heaton J (2011) Programming neural networks with Encog3 in C#, 2nd Edn. Heaton Research, p 240. http://www.amazon.com/Programming-Neural-Networks-Encog3-2nd/dp/1604390263
  16. Karlaftis MG, Vlahogianni EI (2011) Statistical methods versus neural networks in transportation research: differences, similarities and some insights. Transp Res Part C Emerg Technol 19:387–399CrossRefGoogle Scholar
  17. Karlik B, Olgac AV (2010) Performance analysis of various activation functions in generalized MLP architectures of neural networks. Int J Artif Intell Expert Syst 1:111Google Scholar
  18. Krishnakumar K (2003) Intelligent systems for aerospace engineering—an overview. National Aeronautics & Space Administration, Moffet field Ca Ames Research Center Google Scholar
  19. Lagerweij R, Vries G de, Someren M van (2009) Learning a model of ship movements. Thesis for Bachelor of Science-Artificial Intelligence, University of AmsterdamGoogle Scholar
  20. Laxhammar R, Falkman G, Sviestins E (2015) Anomaly detection in sea traffic–a comparison of the gaussian mixture model and the kernel density estimator. In: 12th international conference on information fusion, 2009. FUSION '09. IEEE, Seattle, WA, pp 756–763Google Scholar
  21. Lopez A, Perez R, Moreno B (2011) Forecasting Performance and M-Competition. Does the accuracy measure matter? Int. Stat. Inst. Proc. 58th World Stat. CongrGoogle Scholar
  22. Makridakis S, Hibon M (2000) The M3-competition: results, conclusions and implications. Int J Forecast 16:451–476. doi: 10.1016/S0169-2070(00)00057-1 CrossRefGoogle Scholar
  23. Makridakis S, Andersen A, Carbone R et al (1982) The accuracy of extrapolation (time series) methods: results of a forecasting competition. J Forecast 1:111–153. doi: 10.1002/for.3980010202 CrossRefGoogle Scholar
  24. Makridakis S, Chatfield C, Hibon M et al (1993) The M2-competition: a real-time judgmentally based forecasting study. Int J Forecast 9:5–22. doi: 10.1016/0169-2070(93)90044-N CrossRefGoogle Scholar
  25. Mostafa MM (2004) Forecasting the Suez Canal traffic: a neural network analysis. Marit Policy Manag 31:139–156. doi: 10.1080/0308883032000174463 CrossRefGoogle Scholar
  26. Nicolau V, Aiordachioaie D, Popa R (2004) Neural network prediction of the wave influence on the yaw motion of a ship. 2004 IEEE international joint conference neural networks (IEEE Cat. No. 04CH37541). IEEE, pp 2801–2806Google Scholar
  27. Pankratz A (1983) Forecasting with univariate box-jenkins models: concepts and cases. Wiley, New YorkCrossRefGoogle Scholar
  28. Perera LP, Oliveira P, Guedes Soares C (2012) Maritime traffic monitoring based on vessel detection, tracking, state estimation, and trajectory prediction. IEEE Trans Intell Transp Syst 13:1188–1200. doi: 10.1109/TITS.2012.2187282 CrossRefGoogle Scholar
  29. Rhodes BJ, Bomberger NA, Zandipour M (2007) Probabilistic associative learning of vessel motion patterns at multiple spatial scales for maritime situation awareness. 2007 10th International conference information fusion. IEEE, pp 1–8Google Scholar
  30. Riedmiller M, Braun H (1993) A direct adaptive method for faster backpropagation learning: the RPROP algorithm. IEEE international conference neural networks. IEEE, pp 586–591Google Scholar
  31. Rothblum AM (2002) Human error and marine safety. 2ND Int. Work. Hum. FACTORS OFFSHORE OperGoogle Scholar
  32. Santos B, Lunday K (2009) Maritime domain awareness. Coast Guard J Saf Secur Sea, In: Proceedings of marine safety and security council, p 66Google Scholar
  33. Simsir U, Ertugrul S (2009) Prediction of manually controlled vessels’ position and course navigating in narrow waterways using artificial neural networks. Appl Soft Comput 9:1217–1224CrossRefGoogle Scholar
  34. Souza BA, Brito NSD, Neves WLA, et al (2004) Comparison between backpropagation and RPROP algorithms applied to fault classification in transmission lines. 2004 IEEE international joint conference neural networks (IEEE Cat. No.04CH37541). IEEE, pp 2913–2918Google Scholar
  35. Stopford M (2009) Maritime Economics, 3rd edn. Routledge, p 840Google Scholar
  36. US Department of Homeland Security (2005) National plan to achieve maritime domain awareness (MDA)Google Scholar
  37. Verber D (2012) Implementation of massive artificial neural networks with CUDA. Cut Edge Res New Technol. doi: 10.5772/2431 Google Scholar
  38. Westrenen F, Praetorius G (2012) Maritime traffic management: a need for central coordination? Cogn Technol Work. doi: 10.1007/s10111-012-0244-5 Google Scholar
  39. Zandipour M, Rhodes B, Bomberger N (2008) Probabilistic prediction of vessel motion at multiple spatial scales for maritime situation awareness. 11th international conference information fusionGoogle Scholar
  40. Zhang G, Eddy Patuwo B, Hu MY (1998) Forecasting with artificial neural networks: the state of the art. Int J Forecast 14:35–62CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Dimitrios Zissis
    • 1
    Email author
  • Elias K. Xidias
    • 1
  • Dimitrios Lekkas
    • 1
  1. 1.Department of Product and Systems Design EngineeringUniversity of the AegeanSyrosGreece

Personalised recommendations