PL EN


Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
2020 | 27 | 1 |
Tytuł artykułu

Neural network ensemble approach to pushed convoys dispatching problems

Treść / Zawartość
Warianty tytułu
Języki publikacji
EN
Abstrakty
EN
This paper investigates the use of neural networks (NNs) for the problem of assigning push boats to barge convoys in inland waterway transportation (IWT). Push boat‒barge convoy assignmentsare part of the daily decision-making process done by dispatchers in IWT companiesforwhich a decision support tool does not exist. The aim of this paper is to develop a Neural Network Ensemble (NNE) model that will be able to assist in push boat‒barge convoy assignments based on the push boat power.The primary objective of this paper is to derive an NNE model for calculation of push boat Shaft Powers (SHPs) by using less than 100% of the experimental data available. The NNE model is applied to a real-world case of more than one shipping company from the Republic of Serbia, which is encountered on the Danube River. The solution obtained from the NNE model is compared toreal-world full-scale speed/power measurements carried out on Serbian push boats,as well as with the results obtained from the previous NNE model. It is found that the model is highly accurate, with scope for further improvements
Słowa kluczowe
Wydawca
-
Rocznik
Tom
27
Numer
1
Opis fizyczny
p.70-82,fig.,ref.
Twórcy
autor
  • Faculty of Transport and Traffic Engineering, University of Belgrade, Vojvode Stepe 305, 11000 Belgrade, Republic of Serbia
autor
  • Faculty of Transport and Traffic Engineering, University of Belgrade, Vojvode Stepe 305, 11000 Belgrade, Republic of Serbia
autor
  • Faculty of Transport and Traffic Engineering, University of Belgrade, Vojvode Stepe 305, 11000 Belgrade, Republic of Serbia
Bibliografia
  • 1. Alfandari L., Davidovic T., Furini F., Ljubic I., Maras V., Martin S. (2019):Tighter MIP models for Barge Container Ship Routing. Omega, 82,38–54.
  • 2. Botta M. (2001): Resampling vs reweighting in boosting a relational weak learner. In Proceedings of the 7th Congress of the Italian Association for Artificial Intelligence on Advances in Artificial Intelligence,Springer-Verlag,London, UK, p. 70–80.
  • 3. Burrill L. C. (1943):Developments in Propeller Design and Manufacture for Merchant Ships. Transactions, Institute of Marine Engineers, London, Vol. 55. p. 106–136.
  • 4. Colic V. (2006):Research of navigational, technical, energetic and propulsive characteristics of Danube towboats. Faculty of Transport and Traffic Engineering (in Serbian), University of Belgrade, Belgrade, p 350.
  • 5. Couser P.R., Mason A. (2004): Artificial Neural Networks for Hull Resistance Prediction. Computer Applications and Information Technology in the Maritime Industries (COMPIT’04), 9-12 May, Siguenza, Spain.
  • 6. Drucker H. (1997): Improving regressors using boosting techniques. Proceedings of the Fourteenth International Conference on Machine Learning, 107–115.
  • 7. Efron B., Tibshirani R. (1993):An Introduction to the Bootstrap. Chapman & Hall, New York, p.456.
  • 8. Kohavi R. (1995): A study of cross-validation and bootstrap for accuracy estimation and model selection. Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence. San Mateo, CA: Morgan Kaufmann. Vol. 2 (12), 1137–1143.
  • 9. Maras V., Lazic J., Davidovic T., Mladenovic T.N. (2013):Routing of barge container ships by mixed-integer programming. Appl. Soft Comput., 13, 3515–3528.
  • 10. Parks A.I., Sobey A.J., Hudson D.A. (2018):Physics-based shaft power prediction for large merchant ships using neural networks. Ocean Engineering, 166, 92–104.
  • 11. Radonjic A., Vukadinovic K.(2015):Application of Ensemble Neural Networks to Prediction of Towboat Shaft Power.J. Mar. Sci. Technol., 20, 64–80.
  • 12. Reich Y., Berai S.V. (2000):A methodology for building neural networks model from empirical engineering data.Engineering Applications of Artificial Intelligence, 13(6), 685–694.
  • 13. Ren L., Zhao Z. (2002):An optimal neural network and concrete strength modeling. Advances in Engineering Software, 33(3), 117–130.
  • 14. Riedmiller M., Braun H. (1993): A direct adaptive method for faster backpropagation learning: The RPROP algorithm. Proceedings of the IEEE International Conference on Neural Networks, San Francisco, CA, USA, 28 March-1 April 1993,pp. 586–591.
  • 15. Schwenk H., Bengio Y. (2000):Boosting Neural Networks. Neural Computation, 12(8), 1869-1887.
  • 16. Seiffer C., Khoshgoftaar T.M., Van Hulse J., Napolitano A. (2008): Resampling or Reweighting: A Comparison of Boosting Implementations. 20th IEEE International Conference on Tools with Artificial Intelligence, p. 445–451.
  • 17. Solomatine D.P., Shrestha D.L. (2004): AdaBoost.RT: a boosting algorithm for regression problems.Proceedings of International Joint Conference on Neural Network, Vol. 2, 1163–1168.
  • 18. Tupper E.C., Rawson K.J. (2001):Basic Ship Theory. 5th Edition, Elsevier, p.784.
  • 19. Vaganov G.I., Voronin V.F., Shanchurova V.K. (1986):Tyaga Sudov: myehtodeka i premyehreh vihpolnyehneya sudovih tyagovih raschyehtov (Ship propulsion: methodology and examples of the ship propulsion calculations).Transport, Moscow, p. 201 (In Russian).
  • 20. Vukadinovic K., Teodorovic D., Pavkovic G. (1997):A neural network approach to the vessel dispatching problem. Eur. J. Oper. Res., 102, 473–487.
  • 21. Xu Y., Goodacre R. (2018):On Splitting Training and Validation Set: A Comparative Study of Cross –Validation, Bootstrap and Systematic Sampling for Estimating the Generalization Performance of Supervised Learning. Journal of Analysis and Testing, 2, 249 262.
  • 22. Young Y. L. (2002):Numerical Modeling of Supercavitating and Surface-Piercing Propellers. PhD thesis, Environmental and Water Resources Engineering,Department of Civil Engineering, University of Texas at Austin, Austin, USA.
  • 23. Zhang G., Eddy Patuwo B., Hu M. Y. (1998):Forecasting with artificial neural networks: The state of the art.International Journal of Forecasting, 14, 35–62.
Typ dokumentu
Bibliografia
Identyfikatory
Identyfikator YADDA
bwmeta1.element.agro-05305e6b-2c38-4c02-9eb9-405adbf091ab
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.