Clustering analysis and identification of marine traffic congested zones at Wusongkou, Shanghai

Kyay Mone Soe Oo         Chaojian Shi         Qinyou Hu         Adam Weintrit         


Shanghai, with its natural, cultural and historical wealth, is not only one of China’s most beautiful cities, but it is also one of the most exciting cities in the world. However, there are enormous challenges for navigation in the Shanghai Strait due to its geographical, geopolitical and oceanographic structure. One of the challenges is the marine traffic which crosses from one side to other of the strait. In this study, an attempt is made to identify of vessel traffic zones based on DBSCAN in the Wusongkou. It is located along the north end of Huangpu river which flows from South-West of Shanghai to the North-East and flows into Yangtze river. Ship’s domain is introduced into the DBSCAN algorithm, a particle suitable clustering algorithm is improved for clustering the real-time ship’s dynamic data and detecting potential traffic congested areas at sea, and define three neighborhood models. In addition, fuzzy evaluation model is applied to identify traffic congestion degree. At the end of study, combining the improved DBSCAN algorithm and fuzzy evaluation model for traffic congestion degree, using three neighborhood models with different size to analyses the AIS data from the vessels nearby Wusongkou in Shanghai, and build the corresponding figure of traffic condition visualisation, used to visualise the evaluation result. The result indicate that the neighborhood three model (length is seventeen times of ship’s length, width is six point four times of ship’s length plus ship’s width) can identify the traffic congested zones better.

Download full text in pdf: 

Davis G.B., Carely K.M., Computational Analysis of Merchant Marine GPS Data, CASOS Technical Report, Carnegie Mellon University, 2006(11).

Ester M., Kriegel H.P., Sander J., Xu X., A density-based algorithm for discovering clusters in large spatial databases, Knowledge Discovery and Data Mining (KDD’96), Portland, 1996(8).

Fujii Y., Traffic Engineering at Sea, Haiwen Hall, Tokyo 1981.

Han J., Kamber M., Data Mining: Concepts and Techniques, second edition, Morgan Kaufmann, 2006.

Kaufman L., Rousseeuw P.J., Finding Groups in Data: An Introduction to Cluster Analysis, Wiley, New York 1990.

Ng R.T., Han J., Effcient and Effective Clustering Methods for Spatial Data Mining, Proc. 20th Int. Conf. on Very Large Data Bases, Santiago, Chile 1994.

Qinyou H., Yong J., Shi Ch., Chen G., Evaluation of Main Traffic Congestion Degree for Restricted Waters with AIS Reports, 8th International Symposium on Marine Navigation and Safety of Sea Transportation, TransNav 2009.

Wang Shi-yuan, Xu Kai-yu., Actuality, Prospect and Counterplan of AIS, Marine Technology, 2001(10).

Weintrit A., The Electronic Chart Display and Information System (ECDIS). An Operational Handbook. A Balkema Book. CRC Press, Taylor & Francis Group, Boca Raton–London–New York–Leiden 2009.

Yong Jiajia, First Order Real-time Safety Evaluation of Navigation Safety in Restricted Waters, Shanghai Maritime University [dissertation], Shanghai 2009.

Yuan An-cun, Zhang Shu-fang, International Standard Assembly of Ship Automatic Identification System, Dalian Maritime University Press, Dalian 2005(4).

Citation pattern: Oo Kyay Mone Soe, Shi Chaojian, Hu Qinyou, Weintrit A., Clustering analysis and identification of marine traffic congested zones at Wusongkou, Shanghai, Scientific Journal of Gdynia Maritime University, No. 67, pp. 101-113, 2010

BibTeX     EndNote