Finding Optimal Contextual Parameters for Real-Time Vessel Position Prediction Using Deep Learning

Document Type : Original Article

Authors

1 Full Prof., Dep. of Geomatics Engineering, K.N. Toosi University of Technology, Tehran

2 K. N. Toosi University of Technology

Abstract

About 80% of world transportation happens at sea. Therefore the safety of vessels, in particular
during vessels’ movement, is crucially important. As different contextual parameters affect vessels’
movement, selecting optimal contextual parameters is one of the main changes in vessels’ Context-
Aware movement analysis. Toward this end, a Long Short-Term Memory (LSTM) network is used
for wrapper feature selection to identify optimal contextual parameters for vessels’ movement
prediction. To do this, the Automatic Identification System (AIS) dataset from the eastern coast of the
United States of America collected from December 2017 is used. All possible combinations of three
contextual parameters, including speed, course and vessels’ presence probability in different positions
at sea, were evaluated using the wrapper method in the LSTM network. In all evaluations, 70% of
data was used for training and the remaining for cross-validation. The results selected speed and
presence probability as optimal contextual parameters for vessel movement prediction. The model
trained with optimal contextual parameters is 26.98% more accurate than a model trained with all
available contextual parameters and 16.14% better than a model without contextual parameters.
Therefore, selecting optimal parameters from available contextual parameters can help improve the
accuracy of vessels’ predictions. Keywords: Context-Aware, Long Short-Term Memory, Automatic
Identification System, wrapper, Movement prediction, Context.

Keywords


Abdelaal, M., Fränzle, M. & Hahn, A., 2018, Nonlinear Model Predictive Control for Trajectory Tracking and Collision Avoidance of Underactuated Vessels with Disturbances, Ocean Engineering, 160, PP. 168-180.
Ahearn, S.C., Dodge, S., Simcharoen, A., Xavier, G. & Smith., J.L.D., 2017, A Context-Sensitive Correlated Random Walk: A New Simulation Model for Movement, International Journal of Geographical Information Science, 31(5), PP. 867-883.
Alessandrini, A., Mazzarella, F. & Vespe, M., 2018, Estimated Time of Arrival Using Historical Vessel Tracking Data, IEEE Transactions on Intelligent Transportation Systems, 20(1), PP. 7-15.
Bitner-Gregerse, E.M., Soares, C.G. & Vantorre, M., 2016, Adverse Weather Conditions for Ship Manoeuvrability, Transportation Research Procedia, 14, PP. 1631-1640.
Buchin, M., Dodge, S. & Speckmann, B., 2014, Similarity of Trajectories Taking into Account Geographic Context, Journal of Spatial Information Science, 2014(9), PP. 101-124.
Chatzikokolakis, K., Zissis, D., Spiliopoulos, G. & Tserpes, K., 2018, Mining Vessel Trajectory Data for Patterns of Search and Rescue, EDBT/ICDT Workshops.
de Vries, G.K.D. & van Someren, M., 2012, Machine Learning for Vessel Trajectories Using Compression, Alignments and Domain Knowledge, Expert Systems with Applications, 39(18), PP. 13426-13439.
Filtz, E., de la Cerda, E.S., Weber, M. & Zirkovits, D., 2015, Factors Affecting Ocean-Going Cargo Ship Speed and Arrival Time, Advanced Information Systems Engineering Workshops, Cham, Springer International Publishing.
Gao, M., Shi, G. & Li, S., 2018, Online Prediction of Ship Behavior with Automatic Identification System Sensor Data Using Bidirectional Long Short-Term Memory Recurrent Neural Network, Sensors, 18(12) P. 4211.
Jozefowicz, R., Zaremba, W. & Sutskever, I., 2015, An empirical Exploration of Recurrent Network Architectures, International Conference on Machine Learning, PMLR.
Kim, K.-I. & Lee, K.M., 2018, Context-Aware Information Provisioning for Vessel Traffic Service Using Rule-Based and Deep Learning Techniques, International Journal of Fuzzy Logic and Intelligent Systems, 18(1), PP. 13-19.
 
Kjerstad, Ø.K. & Breivik, M., 2010, Weather Optimal Positioning Control for Marine Surface Vessels, IFAC Proceedings, 43(20), PP. 114-119.
Kuhn, M. & Johnson, K., 2013, Applied Predictive Modeling, Springer.
Lee, H., Aydin, N., Choi, Y., Lekhavat, S. & Irani, Z., 2018, A Decision Support System for Vessel Speed Decision in Maritime Logistics Using Weather Archive Big Data, Computers & Operations Research, 98, PP. 330-342.
Liu, Y. & Hansen, M., 2018, Predicting Aircraft Trajectories: A Deep Generative Convolutional Recurrent Neural Networks Approach, arXiv Preprint, arxiv: 1812.11670.
McClintock, B.T., Johnson, D.S., Hooten, M.B., Ver Hoef, J.M. & Morales, J.M., 2014, When to Be Discrete: The Importance of Time Formulation in Understanding Animal Movement, Movement Ecology, 2(1), PP. 1-14.
Mehri, S., Alesheikh, A.A. & Basiri, A., 2021, A Contextual Hybrid Model for Vessel Movement Prediction, IEEE Access, 9, PP. 45600-45613.
Nguyen, D.-D., Le Van, C. & Ali, M.I., 2018a, Vessel Trajectory Prediction using Sequence-to-Sequence Models over Spatial Grid, Proceedings of the 12th ACM International Conference on Distributed and Event-based Systems, ACM.
Nguyen, D., Vadaine, R., Hajduch, G., Garello, R. & Fablet, R., 2018b, An AIS-Based Deep Learning Model for Vessel Monitoring, NATO CRME Maritime Big Data Workshop, La Spezia, Italy.
NOAA, 2018, AIS Data for 2017, from https://coast.noaa.gov/htdata/CMSP/AISDataHandler/2017/index.html.
Palmer, J.R., Espenshade, T.J., Bartumeus, F., Chung, C.Y., Ozgencil, N.E. & Li, K., 2013,  New Approaches to Human Mobility: Using Mobile Phones for Demographic Research, Demography, 50(3), PP. 1105-1128.
 
Perez, T., Smogeli, O., Fossen, T. & Sorensen, A.J., 2006, An Overview of the Marine Systems Simulator (MSS): A Simulink Toolbox for Marine Control Systems, Modeling, Identification and Control, 27(4), PP. 259-275.
Saeys, Y., Inza, I. & Larrañaga, P., 2007, A Review of Feature Selection Techniques in Bioinformatics, Bioinformatics, 23(19), PP. 2507-2517.
van Essen, S., Scharnke, J., Bunnik, T., Düz, B., Bandringa, H., Hallmann, R. & Helder, J., 2020, Linking Experimental and Numerical Wave Modelling, Journal of Marine Science and Engineering, 8(3).
Vemula, A., Muelling, K. & Oh, J., 2017, Social Attention: Modeling Attention in Human Crowds,  arXiv preprint, arXiv:1710.04689.
Vlachos, M., 2017, Dimensionality Reduction, In: Encyclopedia of Machine Learning and Data Mining, Edited By: C. Sammut and G. I. Webb. Boston, MA, Springer, US, PP. 354-361.
Wang, S., Tang, J. & Liu, H., 2017, Feature Selection, Encyclopedia of Machine Learning and Data Mining, Edited By: C. Sammut and G. I. Webb. Boston, MA, Springer, US, PP. 503-511.
Xiao, F., Ligteringen, H., van Gulijk, C. & Ale, B., 2015, Comparison Study on AIS Data of Ship Traffic Behavior, Ocean Engineering, 95, PP. 84-93.