Robust Marine Buoy Placement for Ship Detection Using Dropout K-Means

Marine buoys aid in the battle against Illegal, Unreported and Unregulated (IUU) fishing by detecting fishing vessels in their vicinity. Marine buoys, however, may be disrupted by natural causes and buoy vandalism. In this paper, we formulate marine buoy placement as a clustering problem, and propose dropout k-means and dropout k-median to improve placement robustness to buoy disruption.We simulated the passage of ships in the Gabonese waters near West Africa using historical Automatic Identification System (AIS) data, then compared the ship detection probability of dropout k-means to classic k-means and dropout k-median to classic k-median. With 5 buoys, the buoy arrangement computed by classic k-means, dropout k-means, classic k-median and dropout k-median have ship detection probabilities of 38%, 45%, 48% and 52%.

[1]  T. Pitcher,et al.  Estimating the Worldwide Extent of Illegal Fishing , 2009, PloS one.

[2]  Barbara A. Block,et al.  Tracking the global footprint of fisheries , 2018, Science.

[3]  Satish Rao,et al.  Approximation schemes for Euclidean k-medians and related problems , 1998, STOC '98.

[4]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[5]  Deepu Rajan,et al.  Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey , 2016, IEEE Transactions on Intelligent Transportation Systems.

[6]  Konstantinos Chatzikokolakis,et al.  Knowledge extraction from maritime spatiotemporal data: An evaluation of clustering algorithms on Big Data , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[7]  Fan Zhang,et al.  Hierarchical feature learning with dropout k-means for hyperspectral image classification , 2016, Neurocomputing.

[8]  A. Chatraei,et al.  Aerial node placement in wireless sensor networks using Fuzzy K-means clustering , 2014, 8th International Conference on e-Commerce in Developing Countries: With Focus on e-Trust.

[9]  Shuang Li,et al.  Online Prediction of Ship Behavior with Automatic Identification System Sensor Data Using Bidirectional Long Short-Term Memory Recurrent Neural Network , 2018, Sensors.

[10]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[11]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[12]  Dmitry B. Goldgof,et al.  Detection and tracking of ships in open sea with rapidly moving buoy-mounted camera system , 2012 .

[13]  M. Shirosaki.  Another proof of the defect relation for moving targets , 1991 .

[14]  Sudipto Guha,et al.  A constant-factor approximation algorithm for the k-median problem (extended abstract) , 1999, STOC '99.

[15]  Kil Woo Chung,et al.  Concurrent use of satellite imaging and passive acoustics for maritime domain awareness , 2010, 2010 International WaterSide Security Conference.

[16]  Jakub Montewka,et al.  A method for detecting possible near miss ship collisions from AIS data , 2015 .

[17]  Moe Z. Win,et al.  Hybrid Clustering Scheme for Relaying in Multi-Cell LTE High User Density Networks , 2017, IEEE Access.

[18]  Chung-Chu Teng,et al.  Buoy vandalism experienced by NOAA National Data Buoy Center , 2009, OCEANS 2009.

[19]  Seda Ogrenci Memik,et al.  Systematic temperature sensor allocation and placement for microprocessors , 2006, 2006 43rd ACM/IEEE Design Automation Conference.

[20]  Rikard Laxhammar,et al.  Anomaly detection for sea surveillance , 2008, 2008 11th International Conference on Information Fusion.

[21]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2008, Pattern Recognit. Lett..