Home > Archive > 2016 > Volume 6 Number 1 (Feb. 2016) >
IJMLC 2016 Vol.6(1): 62-66 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2016.6.1.573

Predicting Anchorage Duration of Commercial Vessels

Milad Malekipirbazari, Vural Aksakalli, and Y. Volkan Aydogdu

Abstract—Seaborne transportation accounts for more than 90% of world’s trade. Anchorages serve as a temporary waiting area for commercial vessels for reasons such as supply, waiting for passage, and as refuge from bad weather. In many anchorages, authorities do not pose any restrictions on the anchorage duration and incoming vessels are not obligated to disclose an estimated duration time, which makes it difficult to manage traffic flow inside the anchorage in an efficient manner. In this study, we first provide a brief statistical analysis on an anchorage dataset for Istanbul Strait anchorages between 2006 and 2014. Next, using this dataset, we propose a data mining framework for predicting anchorage duration for an incoming vessel, which is critical for efficient anchorage planning. Our results indicate that decision trees provide superior prediction performance compared to alternative methods and reason of anchorage has the highest association with anchorage duration.

Index Terms—Anchorage, Istanbul Strait, decision tree.

M. Malekipirbazari and V. Aksakalli are with the Department of Industrial Engineering, Istanbul Sehir University, Istanbul, 34662 Turkey (e-mail: miladmalekipirbazari@std.sehir.edu.tr, aksakalli@sehir.edu.tr).
Y. V. Aydogdu is with the Maritime Faculty, Istanbul Technical University, Istanbul, 34940 Turkey (e-mail: yvaydogu@itu.edu.tr).


Cite: Milad Malekipirbazari, Vural Aksakalli, and Y. Volkan Aydogdu, "Predicting Anchorage Duration of Commercial Vessels," International Journal of Machine Learning and Computing vol.6, no. 1, pp. 62-66, 2016.

General Information

  • E-ISSN: 2972-368X
  • Abbreviated Title: Int. J. Mach. Learn.
  • Frequency: Quaterly
  • DOI: 10.18178/IJML
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals LibraryCNKI.
  • E-mail: ijml@ejournal.net

Article Metrics in Dimensions