Destination Port Detection for Vessels: An Analytic Tool for Optimizing Port Authorities Resources

Port authorities have many challenges in congested ports to allocate their resources to provide a safe and secure loading/unloading procedure for cargo vessels. Selecting a destination port is the decision of a vessel master based on many factors such as weather, wavelength and changes of priorities. Having access to a tool which leverages Automatic Identification System (AIS) messages to monitor vessel’s movements and accurately predict their next destination port promotes an effective resource allocation process for port authorities. In this research, we propose a method, namely, Reference Route of Trajectory (RRoT) to assist port authorities in predicting inflow and outflow traffic in their local environment by monitoring AIS messages. Our RRo method creates a reference route based on historical AIS messages. It utilizes some of the best trajectory similarity measures to identify the destination of a vessel using their recent movement. We evaluated five different similarity measures such as Discrete Frechet Distance (DFD), Dynamic Time ´ Warping (DTW), Partial Curve Mapping (PCM), Area between two curves (Area) and Curve length (CL). Our experiments show that our method identifies the destination port with an accuracy of 98.97% and an f-measure of 99.08% using Dynamic Time Warping (DTW) similarity measure.





References:
[1] L. Qi and Z. ZHENG, “A measure of similarity between trajectories of
vessels,” Journal of Engineering Science and Technology Review, vol. 9,
pp. 17–22, 03 2016.
[2] E. Carlini, V. M. de Lira, A. Soares, M. Etemad, B. B. Machado, and
S. Matwin, “Uncovering vessel movement patterns from ais data with
graph evolution analysis.” in EDBT/ICDT Workshops, 2020.
[3] I. Varlamis, I. Kontopoulos, K. Tserpes, M. Etemad, A. Soares, and
S. Matwin, “Building navigation networks from multi-vessel trajectory
data,” GeoInformatica, pp. 1–29, 2020.
[4] M. Etemad, N. Zare, M. Sarvmaili, A. Soares, B. B. Machado, and
S. Matwin, “Using deep reinforcement learning methods for autonomous
vessels in 2d environments,” in Canadian Conference on Artificial
Intelligence. Springer, 2020, pp. 220–231.
[5] “Ais class a ship static and voyage related data (message 5),”
https://www.navcen.uscg.gov/?pageName=AISMessagesAStatic,
accessed: 2021-04-02.
[6] S. Kos, M. Vukic, and D. Brcic, “Use of universal protocol for entering ´
the port of destination in ais device,” 2013.
[7] G. K. D. de Vries, W. R. van Hage, and M. van Someren,
“Comparing vessel trajectories using geographical domain knowledge
and alignments,” in 2010 IEEE International Conference on Data
Mining Workshops, 2010, pp. 209–216.
[8] D. Alizadeh, A. A. Alesheikh, and M. Sharif, “Prediction of
vessels locations and maritime traffic using similarity measurement of
trajectory,” Annals of GIS, vol. 0, no. 0, pp. 1–12, 2020. [Online].
Available: https://doi.org/10.1080/19475683.2020.1840434
[9] R. Zhen, J. Yongxing, Q. Hu, Z. Shao, and N. Nikitakos, “Maritime
anomaly detection within coastal waters based on vessel trajectory
clustering and na¨ıve bayes classifier,” Journal of Navigation, vol. 70,
pp. 1–23, 01 2017.
[10] L. Alvares, V. Bogorny, and B. Kuijpers, “Towards semantic trajectory
knowledge discovery,” 10 2007.
[11] R. d. S. Mello, V. Bogorny, L. O. Alvares, L. H. Z. Santana,
C. A. Ferrero, A. A. Frozza, G. A. Schreiner, and C. Renso,
“Master: A multiple aspect view on trajectories,” Transactions in
GIS, vol. 23, no. 4, pp. 805–822, 2019. [Online]. Available:
https://onlinelibrary.wiley.com/doi/abs/10.1111/tgis.12526
[12] P. Sheng and J. Yin, “Extracting shipping route patterns by trajectory
clustering model based on automatic identification system data,”
Sustainability, vol. 10, p. 2327, 07 2018.
[13] M. Buchin, S. Dodge, and B. Speckmann, “Similarity of trajectories
taking into account geographic context,” Journal of Spatial Information
Science, vol. 9, 11 2014.
[14] M. Etemad, “Novel algorithms for trajectory segmentation based on
interpolation-based change detection strategies,” 2020.
[15] M. Etemad, Z. Etemad, A. Soares, V. Bogorny, S. Matwin, and L. Torgo,
“Wise sliding window segmentation: A classification-aided approach
for trajectory segmentation,” in Canadian Conference on Artificial
Intelligence. Springer, 2020, pp. 208–219.
[16] M. Etemad, A. Soares, E. Etemad, J. Rose, L. Torgo, and S. Matwin,
“Sws: an unsupervised trajectory segmentation algorithm based on
change detection with interpolation kernels,” GeoInformatica, pp. 1–21,
2020.
[17] Z. Xiu-Li and X. Wei-Xiang, “A clustering-based approach for
discovering interesting places in a single trajectory,” in 2009 second
international conference on intelligent computation technology and
automation, vol. 3. IEEE, 2009, pp. 429–432.
[18] Y. Zheng, X. Xie, W.-Y. Ma et al., “Geolife: A collaborative social
networking service among user, location and trajectory.” IEEE Data Eng.
Bull., vol. 33, no. 2, pp. 32–39, 2010.
[19] E. Carlini, V. Monteiro, A. Soares, M. Etemad, B. Machado, and
S. Matwin, “Uncovering vessel movement patterns from ais data with
graph evolution analysis,” in EDBT/ICDT Workshops, 01 2020.
[20] M. Etemad, “Novel algorithms for trajectory segmentation based on
interpolation-based change detection strategies,” Dalhousie Faculty
of Graduate Studies Online Theses 2020. [Online]. Available:
http://hdl.handle.net/10222/79941
[21] Q. Li, Y. Zheng, X. Xie, Y. Chen, W. Liu, and W.-Y. Ma, “Mining
user similarity based on location history,” in Proceedings of the
16th ACM SIGSPATIAL International Conference on Advances in
Geographic Information Systems, ser. GIS ’08. New York, NY, USA:
Association for Computing Machinery, 2008, p. 10. [Online]. Available:
https://doi.org/10.1145/1463434.1463477
[22] A. Palma, V. Bogorny, B. Kuijpers, and L. Alvares, “A clustering-based
approach for discovering interesting places in trajectories,” 03 2008, pp.
863–868.
[23] P. Senin, “Dynamic time warping algorithm review,” 01 2009.
[24] M. Frechet, “Sur quelques points du calcul fonctionnel,” ´ Rendiconti del
Circolo Matematico di Palermo (1884-1940), vol. 22, pp. 1–72.
[25] T. Eiter and H. Mannila, “Computing discrete frechet distance,” 05 1994.
[26] I. Cleasby, E. Wakefield, B. Morrissey, T. Bodey, S. Votier, S. Bearhop,
and K. Hamer, “Using time-series similarity measures to compare
animal movement trajectories in ecology,” Behavioral Ecology and
Sociobiology, vol. 73, 11 2019.
[27] C. Jekel, G. Venter, M. Venter, N. Stander, and R. Haftka, “Similarity
measures for identifying material parameters from hysteresis loops using
inverse analysis,” International Journal of Material Forming, vol. 12, 05
2019.
[28] H. Edelhoff, J. Signer, and N. Balkenhol, “Path segmentation for
beginners: An overview of current methods for detecting chang