Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Exploiting multiclass classification algorithms for the prediction of ship routes: a study in the area of Malta

Exploiting multiclass classification algorithms for the prediction of ship routes: a study in the... Ship route prediction (SRP) is a quite complicated task, which enables the determination of the next position of a ship after a given period of time, given its current position. This paper aims to describe a study, which compares five families of multiclass classification algorithms to perform SRP.Design/methodology/approachTested algorithm families include: Naive Bayes (NB), nearest neighbors, decision trees, linear algorithms and extension from binary. A common structure for all the algorithm families was implemented and adapted to the specific case, according to the test to be done. The tests were done on one month of real data extracted from automatic identification system messages, collected around the island of Malta.FindingsExperiments show that K-nearest neighbors and decision trees algorithms outperform all the other algorithms. Experiments also demonstrate that linear algorithms and NB have a very poor performance.Research limitations/implicationsThis study is limited to the area surrounding Malta. Thus, findings cannot be generalized to every context. However, the methodology presented is general and can help other researchers in this area to choose appropriate methods for their problems.Practical implicationsThe results of this study can be exploited by applications for maritime surveillance to build decision support systems to monitor and predict ship routes in a given area. For example, to protect the marine environment, the use of SRP techniques could be used to protect areas at risk such as marine protected areas, from illegal fishing.Originality/valueThe paper proposes a solid methodology to perform tests on SRP, based on a series of important machine learning algorithms for the prediction. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Systems and Information Technology Emerald Publishing

Exploiting multiclass classification algorithms for the prediction of ship routes: a study in the area of Malta

Download PDF
19 pages

Loading next page...
 
/lp/emerald-publishing/exploiting-multiclass-classification-algorithms-for-the-prediction-of-owORplLboA
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
1328-7265
eISSN
1328-7265
DOI
10.1108/jsit-10-2019-0212
Publisher site
See Article on Publisher Site

Abstract

Ship route prediction (SRP) is a quite complicated task, which enables the determination of the next position of a ship after a given period of time, given its current position. This paper aims to describe a study, which compares five families of multiclass classification algorithms to perform SRP.Design/methodology/approachTested algorithm families include: Naive Bayes (NB), nearest neighbors, decision trees, linear algorithms and extension from binary. A common structure for all the algorithm families was implemented and adapted to the specific case, according to the test to be done. The tests were done on one month of real data extracted from automatic identification system messages, collected around the island of Malta.FindingsExperiments show that K-nearest neighbors and decision trees algorithms outperform all the other algorithms. Experiments also demonstrate that linear algorithms and NB have a very poor performance.Research limitations/implicationsThis study is limited to the area surrounding Malta. Thus, findings cannot be generalized to every context. However, the methodology presented is general and can help other researchers in this area to choose appropriate methods for their problems.Practical implicationsThe results of this study can be exploited by applications for maritime surveillance to build decision support systems to monitor and predict ship routes in a given area. For example, to protect the marine environment, the use of SRP techniques could be used to protect areas at risk such as marine protected areas, from illegal fishing.Originality/valueThe paper proposes a solid methodology to perform tests on SRP, based on a series of important machine learning algorithms for the prediction.

Journal

Journal of Systems and Information Technology – Emerald Publishing

Published: Dec 11, 2020

Keywords: Machine learning; Ship route prediction; Multiclass classification; Maritime surveillance

References

  • Mining Maritime vessel traffic: promises, challenges, techniques
    Cazzanti, L.; Pallotta, G.
  • SMOTE: synthetic minority over-sampling technique
    Chawla, N.V.; Bowyer, K.W.; Hall, L.O.; Kegelmeyer, W.P.
  • Marine protected areas – a multidisciplinary approach
    Claudet, J.
  • Machine learning for vessel trajectories using compression, alignments and domain knowledge
    de Vries, G.K.D.; van Someren, M.
  • Vessel track information mining using AIS data
    Deng, F.; Guo, S.; Deng, Y.; Chu, H.; Zhu, Q.; Sun, F.
  • A two-layer Wang-Mendel fuzzy approach for predicting the residuary resistance of sailing yachts
    Fan, Z.; Chiong, R.; Hu, Z.; Dhakal, S.; Lin, Y.
  • Chapter V: safety of navigation
  • Bayesian approach to ship speed prediction based on operational data
    Krata, P.; Vettor, R.; Soares, C.G.
  • A K-nearest neighbor classifier for ship route prediction
    Lo Duca, A.; Bacciu, C.; Marchetti, A.
  • Impacts of marine protected areas on fishing communities
    Mascia, M.B.; Claus, C.; Naidoo, R.
  • Survey on multiclass classification methods
    Mohamed, A.
  • Vessel pattern knowledge discovery from ais data: a framework for anomaly detection and route prediction
    Pallotta, G.; Vespe, M.; Bryan, K.
  • Maritime traffic monitoring based on vessel detection, tracking, state estimation, and trajectory prediction
    Perera, L.P.; Oliveira, P.; Soares, C.G.
  • Remote sensing for Maritime monitoring and vessel prompt identification
    Reggiannini, M.; Righi, M.; Tampucci, M.; Bedini, L.; Di Paola, C.; Martinelli, M.; Mercurio, C.; Salerno, E.; Choro, K.; Kopel, M.; Kukla, E.; Siemiski, A.
  • Remote sensing for Maritime prompt monitoring
    Reggiannini, M.; Righi, M.; Tampucci, M.; Lo Duca, A.; Bacciu, C.; Bedini, L.; D’Errico, A.; Di Paola, C.; Marchetti, A.; Martinelli, M.; Mercurio, C.
  • Probabilistic associative learning of vessel motion patterns at multiple spatial scales for Maritime situation awareness
    Rhodes, B.; Bomberger, N.; Zandipour, M.
  • Detecting anomalies from a multitarget tracking output
    Ristic, B.
  • Ship trajectory uncertainty prediction based on a Gaussian process model
    Rong, H.; Teixeira, A.P.; Soares, C.G.
  • A systematic analysis of performance measures for classification tasks
    Sokolova, M.; Lapalme, G.
  • Addressing ecosystem effects of fishing using marine protected areas
    Sumaila, U.R.; Guinette, S.; Alder, J.; Chuenpagdee, R.
  • Automatic Maritime traffic synthetic route: a framework for route prediction
    Tafa, L.N.; Su, X.; Hong, J.; Choi, C.
  • Ship movement prediction using k-NN method
    Virjonen, P.; Nevalainen, P.; Pahikkala, T.; Heikkonen, J.
  • Support-vector networks
    Cortes, C.; Vapnik, V.
  • Induction of decision trees
    Quinlan, J.R.
  • In defense of one-vs-all classification
    Rifkin, R.; Klautau, A.
  • Solving large scale linear prediction problems using stochastic gradient descent algorithms
    Zhang, T.