Automatic ship route design between two ports: A data-driven method

Abstract With the forced installation of the ship's automatic identification system (AIS), a large amount of ship trajectory data in the world is generated. These data provide information on latitude, longitude, speed and course, and plenty of materials for maritime pattern extraction and vessel behavior prediction. And how to dig into these AIS data deeply to discover the ship behavior pattern is an important job. There are two key points on the automatic ship route design research: the turning area generation and the turning area linkage. In this paper, we integrate DBSCAN and Artificial Neural Network capable of automatic ship route design based on massive AIS data between certain ports. The main purpose of this study is to recognize the key regions by applying DBSCAN algorithm and then connect these regions automatically by cluster similarity measuring. Then artificial neural network has been used to learn the relationship of turning regions and generate a reasonable route with different ship dimensions. The main achievement of this study have twofold. First, a research framework for automatic generation of ship route is proposed. We can process big AIS data and use them to generate ship route. Second, generation of different routes according to ships of different dimension under the research framework. The method is capable of generating ship route automatically according to different ship dimensions, which has been evaluated on two real routes around the world.

[1]  Chen Guo,et al.  Automatic collision avoidance of multiple ships based on deep Q-learning , 2019, Applied Ocean Research.

[2]  Eamonn J. Keogh,et al.  Exact indexing of dynamic time warping , 2002, Knowledge and Information Systems.

[3]  Bradley J. Rhodes,et al.  Probabilistic associative learning of vessel motion patterns at multiple spatial scales for maritime situation awareness , 2007, 2007 10th International Conference on Information Fusion.

[4]  Yuanqiao Wen,et al.  Modelling of marine traffic flow complexity , 2015 .

[5]  Andrew T. Irish,et al.  Trajectory Learning for Robot Programming by Demonstration Using Hidden Markov Model and Dynamic Time Warping , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[6]  Andrea Copping,et al.  Maritime Route Delineation using AIS Data from the Atlantic Coast of the US , 2016, Journal of Navigation.

[7]  Jos van Hillegersberg,et al.  Maritime Pattern Extraction from AIS Data Using a Genetic Algorithm , 2016, 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[8]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[9]  Xuesong Zhou,et al.  Method for investigating intradriver heterogeneity using vehicle trajectory data: A Dynamic Time Warping approach , 2015 .

[10]  Chen Chen,et al.  Study on a Numerical Navigation System in the East China Sea , 2015 .

[11]  Wen-Chih Peng,et al.  Discovering Maritime Traffic Route from AIS network , 2016, 2016 18th Asia-Pacific Network Operations and Management Symposium (APNOMS).

[12]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[13]  Dimitrios Zissis,et al.  A cloud based architecture capable of perceiving and predicting multiple vessel behaviour , 2015, Appl. Soft Comput..

[14]  Jing Deng,et al.  Ship trajectory prediction for intelligent traffic management using clustering and ANN , 2016, 2016 UKACC 11th International Conference on Control (CONTROL).

[15]  Milton S. Boyd,et al.  Designing a neural network for forecasting financial and economic time series , 1996, Neurocomputing.

[16]  Stan Matwin,et al.  Knowledge-based clustering of ship trajectories using density-based approach , 2014, 2014 IEEE International Conference on Big Data (Big Data).

[17]  P. Silveira,et al.  Use of AIS Data to Characterise Marine Traffic Patterns and Ship Collision Risk off the Coast of Portugal , 2013, Journal of Navigation.

[18]  Zhiwei Zhao,et al.  Data-driven based automatic maritime routing from massive AIS trajectories in the face of disparity , 2018 .

[19]  Naixue Xiong,et al.  A Dimensionality Reduction-Based Multi-Step Clustering Method for Robust Vessel Trajectory Analysis , 2017, Sensors.

[20]  Michele Vespe,et al.  Vessel Pattern Knowledge Discovery from AIS Data: A Framework for Anomaly Detection and Route Prediction , 2013, Entropy.

[21]  Lily Rachmawati,et al.  Exploiting AIS Data for Intelligent Maritime Navigation: A Comprehensive Survey From Data to Methodology , 2016, IEEE Transactions on Intelligent Transportation Systems.

[22]  Zhe Xiao,et al.  Maritime Traffic Probabilistic Forecasting Based on Vessels’ Waterway Patterns and Motion Behaviors , 2017, IEEE Transactions on Intelligent Transportation Systems.

[23]  Seniz Ertugrul,et al.  Prediction of manually controlled vessels' position and course navigating in narrow waterways using Artificial Neural Networks , 2009, Appl. Soft Comput..

[24]  Xinping Yan,et al.  A novel method for restoring the trajectory of the inland waterway ship by using AIS data , 2015 .

[25]  Jos van Hillegersberg,et al.  Using machine learning for unsupervised maritime waypoint discovery from streaming AIS data , 2015, I-KNOW.

[26]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[27]  M. C. Jones,et al.  A reliable data-based bandwidth selection method for kernel density estimation , 1991 .

[28]  Xia Lu.  SA-DBSCAN:A self-adaptive density-based clustering algorithm , 2009 .

[29]  Yong Deng,et al.  Unsupervised maritime traffic pattern extraction from spatio-temporal data , 2015, 2015 11th International Conference on Natural Computation (ICNC).