K-means clustering for SAT-AIS data analysis
Tóm tắt
The paper deals with a problem of automatic identification system (AIS) data analysis, especially eliminating the impact of AIS packet collision and detecting existing outliers in AIS data. To solve this problem, a clustering-based approach is proposed. AIS is a system that supports the exchange of information between vessels about their trajectories, e.g. position, speed or course. However, SAT-AIS, which enables the system to work on a global scale, struggles against packet collisions due to the fact that the satellite, which receives AIS data from ships, has a field of view that covers multiple areas that are not synchronized among themselves. As a result, the received data is difficult to process by AIS receivers, because most of the messages have a character of noise. In this paper, results of a computational experiment using k-means algorithm for packet recovery and for dealing with noise have been presented. The outcome proves that a clustering-based approach could be used as an initial step in AIS packet reconstruction, when the original data is incorrect.
Tài liệu tham khảo
Brownlee J (2017) Why one-hot encode data in machine learning? Mach Learn Mast. https://machinelearningmastery.com/why-one-hot-encode-data-in-machine-learning Accessed 13 December 2019
Czarnowski I (2019) A cluster-based approach to maritime data analysis: the case of SAT-AIS data analysis. In: Proceedings of the international association of maritime Universities (IAMU) conference, pp 182–190
European Space Agency (2019) Satellite - automatic identification system (SAT-AIS) overview. European space agency website. https://artes.esa.int/sat-ais/overview. Accessed 13 December 2019
exactEarth (2015) Satellite AIS. An exactEarth Technical White Paper. exactEarth Website. https://cdn2.hubspot.net/hubfs/183611/Old%20Content/Landing_Page_Documents/Satellite_AIS_White_Paper_Final-1.pdf. Accessed 06 July 2020
He YK, Zhang D, Zhang JF, Zhang MY (2019) Ship route planning using historical trajectories derived from AIS data. Int J Marine Navig Saf Sea Transport 13(1):69–76. https://doi.org/10.12716/1001.13.01.06
International Maritime Organisation (IMO) (2019) Automatic identification systems (AIS). IMO Website. http://www.imo.org/en/OurWork/Safety/Navigation/Pages/AIS.aspx. Accessed 13 December 2019
International Telecommunications Union (2014) Recommendation ITU-R M.1371-5 (02/2014). https://www.itu.int/dms_pubrec/itu-r/rec/m/R-REC-M.1371-5-201402-I!!PDF-E.pdf. Accessed 13 December 2019
Lane RO, Nevell DA, Hayward SD, Beaney TW (2010) Maritime anomaly detection and threat assessment. In: 2010 13th Conference on IEEE Information Fusion (FUSION). https://doi.org/10.1109/ICIF.2010.5711998
Liang M, Liu RW, Zhong Q, Liu J, Zhang J (2019) Neural network-based automatic reconstruction of missing vessel trajectory data. In: 2019 IEEE 4th International Conference on Big Data Analytics (ICBDA). https://doi.org/10.1109/ICBDA.2019.8713215
Mieczyńska M, Czarnowski I (2019) A cluster-based approach for AIS data analysis and vessel trajectory reconstruction. In: PP-RAI’2019 polskie porozumienie na rzecz rozwoju sztucznej inteligencji conference proceedings, pp 103–106
Millefiori LM, Zissis D, Cazzanti L, Arcieri G (2016) A distributed approach to estimating sea port operational regions from lots of AIS data. In: 2016 IEEE International Conference on Big Data (Big Data). https://doi.org/10.1109/BigData.2016.7840774
Pallotta G, Vespe M, Bryan K (2013) Traffic route extraction and anomaly detection from AIS data. 2COST MOVE Workshop on Moving Objects at Sea
Pallotta G, Vespe M, Bryan K (2013) Vessel pattern knowledge discovery from AIS data: a framework for anomaly detection and route prediction, Entropy. https://doi.org/10.3390/e15062218
Prevost R, Coulon M, Bonacci D, LeMaitre J, Millerioux J, Tourneret J (2012) Extended constrained Viterbi algorithm for AIS signals received by satellite. In: 2012 IEEE First AESS European Conference on Satellite Telecommunications (ESTEL). https://doi.org/10.1109/ESTEL.2012.6400111
Seta T, Matsukura H, Aratani T, Tamura K (2016) An estimation method of message receiving probability for a satellite automatic identification system using a binomial distribution model. Sci J Marit Univ Szczecin 46(118):101–107
Swetha GM, Hemavathy K, Natarajan S (2018) Overcome message collisions in satellite automatic ID systems, Informa PLC Microwave & RF. https://www.mwrf.com/systems/overcome-message-collisions-satellite-automatic-id-systems. Accessed 13 December 2019
Wawrzaszek R, Waraksa M, Kalarus M, Juchnikowski G, Gorski T (2019) Detection and decoding of AIS navigation messages by a low earth orbit satellite. In: Sasiadek J (ed) Aerospace robotics III. GeoPlanet: earth and planetary sciences. Springer, Cham. https://doi.org/10.1007/978-3-319-94517-0_4
Wierzchon ST, Klopotek M (2015) Algorithms of cluster analysis. Institute of Computer Science Polish Academy of Science, Warsaw
Zhang W, Goerlandt F, Montewka J, Kujala P (2015) A method for detecting possible near miss ship collisions from AIS data, Ocean Eng. https://doi.org/10.1016/j.oceaneng.2015.07.046