Pattern Knowledge Discovery of Ship Collision Avoidance based on AIS Data Analysis

doi:10.23940/ijpe.18.10.p22.24492457

Abstract

Abstract:

Maritime traffic pattern is very important for intelligent ship collision avoidance applications, as it can help provide decision support to avoid ship collision accidents and reduce casualties. There has been a large amount of Automatic Identification System (AIS) data saved by ports or management departments. If these data can be processed and analyzed scientifically to provide an early warning with appropriate collision avoidance measures, injuries or more serious results from maritime traffic may be reduced or eliminated. Our focus is to synthesize ship behaviors of interest in a clear and effective way based on automatic preprocessing and analyzing original static AIS data. One improved DBSCAN algorithm is first called to reduce the data scale and discover important data points. Then, from the perspective of Own ship, seven patterns including course change and speed change are defined to be discovered. For each special pattern, the space collision risk DCPA (distance to closest point of approach) and time collision risk TCPA (time to closest point of approach) at the beginning time and ending time are computed to confirm its situation as heading on, crossing, or overtaking with other ships in sight of one another. This unsupervised learning approach will help discover traffic pattern knowledge in current trajectories and provide decision support for future route design or anomaly analysis.

Submitted on July 20, 2018; Revised on August 15, 2018; Accepted on September 18, 2018
References: 10

Peng Chen, Guoyou Shi, Shuang Liu, and Miao Gao. Pattern Knowledge Discovery of Ship Collision Avoidance based on AIS Data Analysis [J]. Int J Performability Eng, 2018, 14(10): 2449-2457.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References 0

	G. Pallotta, M. Vespe, and K. Bryan, “Vessel Pattern Knowledge Discovery from AIS Data: A Framework for Anomaly Detection and Route Prediction,” Entropy, Vol. 15, No. 6, pp. 2218-2245, 2013
	L. P. Perera, J. P. Carvalho, and C. G. Soares, “Autonomous Guidance and Navigation based on the COLREGs Rules and Regulations of Collision Avoidance,” Advanced Ship Design for Pollution Prevention, Publisher: Taylor & Francis Group, pp. 205-216, London, UK, 2009
	B. T. Morris and M. M. Trivedi, “Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach,” IEEE Transactions on Pattern Analysis & Machine Intelligence, Vol. 33, No. 11, pp. 2287-2301, 2011
	R. O. Lane, D.A. Nevell, S. D. Hayward, and T. W. Beaney, “Maritime Anomaly Detection and Threat Assessment,” Information Fusion, pp. 1-8, 2011
	K. Kowalska and L. Peel, “Maritime Anomaly Detection Using Gaussian Process Active Learning,” in Proceedings of International Conference on Information Fusion, pp. 1164-1171, 2012
	M. Vespe, I. Visentini, K. Bryan, and P. P Braca, “Unsupervised Learning of Maritime Traffic Patterns for Anomaly Detection,” in Proceedings of 9th IET Data Fusion & Target Tracking Conference, pp. 1-5, London, UK, 2012
	R. Walker, A. Stevens, O. Anjum, M. Suriarachchi, and K. Mcnamara, “Fast Maritime Anomaly Detection Using Kd-Tree Gaussian Processes,” Post, Vol. 31, No. 10, pp. 1-6, 2011
	S. Kazemi, S. Abghari, N. Lavesson, H. Johnson, and P. Ryman, “Open Data for Anomaly Detection in Maritime Surveillance,” Expert Systems with Application, Vol. 40, No. 14, pp. 5719-5729, 2013
	R. Zhen, Y. Jin, Q. Hu, Z. Shao, and N. Nikitas, “Maritime Anomaly Detection within Coastal Waters based on Vessel Trajectory Clustering and Naive Bayes Classifier,” Journal of Navigation, Vol. 70, No. 3, pp. 648-670, 2017
	P. R. Lei, “A Framework for Anomaly Detection in Maritime Trajectory Behavior,” Knowledge and Information Systems, Vol. 47, No. 1, pp. 189-214, 2016