Architecture for Trajectory-Based Fishing Ship Classification with AIS Data

This paper proposes a data preparation process for managing real-world kinematic data and detecting fishing vessels. The solution is a binary classification that classifies ship trajectories into either fishing or non-fishing ships. The data used are characterized by the typical problems found in classic data mining applications using real-world data, such as noise and inconsistencies. The two classes are also clearly unbalanced in the data, a problem which is addressed using algorithms that resample the instances. For classification, a series of features are extracted from spatiotemporal data that represent the trajectories of the ships, available from sequences of Automatic Identification System (AIS) reports. These features are proposed for the modelling of ship behavior but, because they do not contain context-related information, the classification can be applied in other scenarios. Experimentation shows that the proposed data preparation process is useful for the presented classification problem. In addition, positive results are obtained using minimal information.

[1]  Xianfei Yang,et al.  Recognizing Deceptive Reviews Based on Weighted Multi-Instance Unbalanced Support Vector Machine , 2019, Proceedings of the 2019 International Conference on Artificial Intelligence and Computer Science.

[2]  A. Harati-Mokhtari,et al.  Automatic Identification System (AIS): Data Reliability and Human Error Implications , 2007, Journal of Navigation.

[3]  Xuegang Ban,et al.  Vehicle classification using GPS data , 2013 .

[4]  Colin P. Schwegmann,et al.  The best of a BAD situation: Optimising an algorithm to match course resolution SAR vessel detections to sparse AIS data , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[5]  Bruce A. McElhoe,et al.  An Assessment of the Navigation and Course Corrections for a Manned Flyby of Mars or Venus , 1966, IEEE Transactions on Aerospace and Electronic Systems.

[6]  Gustavo E. A. P. A. Batista,et al.  A study of the behavior of several methods for balancing machine learning training data , 2004, SKDD.

[7]  Anjana Gosain,et al.  Handling class imbalance problem using oversampling techniques: A review , 2017, 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[8]  Jesús García Herrero,et al.  AIS trajectory classification based on IMM data , 2019, 2019 22th International Conference on Information Fusion (FUSION).

[9]  Xiang Chen,et al.  An application of convolutional neural network to derive vessel movement patterns , 2019, 2019 5th International Conference on Transportation Information and Safety (ICTIS).

[10]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[11]  Federico Castanedo,et al.  A Review of Data Fusion Techniques , 2013, TheScientificWorldJournal.

[12]  Zhong Liu,et al.  Research on Ship Classification Based on Trajectory Features , 2017, Journal of Navigation.

[13]  Paul A. Zandbergen,et al.  Positional accuracy of the Wide Area Augmentation System in consumer-grade GPS units , 2009, Comput. Geosci..

[14]  Jean-Yves Schneider,et al.  Target Classification Based On Kinematic Data From AIS/ADS-B, Using Statistical Features Extraction and Boosting , 2019, 2019 20th International Radar Symposium (IRS).

[15]  Ayushi Jain,et al.  Review of Bagging and Boosting Classification Performance on Unbalanced Binary Classification , 2018, 2018 IEEE 8th International Advance Computing Conference (IACC).

[16]  Y. Bar-Shalom,et al.  The interacting multiple model algorithm for systems with Markovian switching coefficients , 1988 .

[17]  Ivan Martinovic,et al.  Classi-Fly: Inferring Aircraft Categories from Open Data , 2019, ACM Trans. Intell. Syst. Technol..

[18]  Wioleta Błaszczak-Bąk,et al.  Methodology for Processing of 3D Multibeam Sonar Big Data for Comparative Navigation , 2019, Remote. Sens..

[19]  Francisco Herrera,et al.  Learning from Imbalanced Data Sets , 2018, Springer International Publishing.

[20]  Jakob Juul Larsen,et al.  Target Classification Using Kinematic Data and a Recurrent Neural Network , 2018, 2018 19th International Radar Symposium (IRS).

[21]  B.J. Tetreault,et al.  Use of the Automatic Identification System (AIS) for maritime domain awareness (MDA) , 2005, Proceedings of OCEANS 2005 MTS/IEEE.

[22]  Serge P. Hoogendoorn,et al.  Ship classification based on ship behavior clustering from AIS data , 2019, Ocean Engineering.

[23]  Xuegang Ban,et al.  Identifying multiclass vehicles using global positioning system data , 2018, J. Intell. Transp. Syst..

[24]  Sotiris B. Kotsiantis,et al.  Machine learning: a review of classification and combining techniques , 2006, Artificial Intelligence Review.

[25]  Junliang Chen,et al.  Research on Ship Classification Based on Trajectory Association , 2019, KSEM.

[26]  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.

[27]  Carmine Clemente,et al.  A recursive kinematic random forest and alpha beta filter classifier for 2D radar tracks , 2016, EURASIP J. Adv. Signal Process..

[28]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[29]  Jürgen Dickmann,et al.  Semantic Segmentation on Radar Point Clouds , 2018, 2018 21st International Conference on Information Fusion (FUSION).

[30]  Friedhelm Schwenker,et al.  Ship classification based on trajectory data with machine-learning methods , 2018, 2018 19th International Radar Symposium (IRS).

[31]  V. Jilkov,et al.  Survey of maneuvering target tracking. Part V. Multiple-model methods , 2005, IEEE Transactions on Aerospace and Electronic Systems.