The goal of maritime traffic management is to provide a safe and efficient maritime environment for different type of vessels facilitating port logistics and supply chain business. However, current maritime traffic management mainly relies on the massive individual vessel’s data for decision making. Lack of macro-level understanding of vessel crowd movement around port challenges maritime safety and traffic efficiency. In this paper, we describe a spatio-temporal data mining method to discover crowd movement patterns of vessels from their short-term history data. The method first captures vessels’ crowd movement features by building vessels’ tracklets with their speed and location. A movement vector clustering algorithm is developed to find different travel behaviors for different group of vessels. With nonparametric regression on the classified vessel movement vectors which represent the crowd travel behaviors, an overall vessel movement pattern can then be discovered. In this research, we tested real trajectory data of vessels near Singapore ports. Comparing with the actual massive vessel movement data, we found that this method was able to extract vessels’ crowd movement information. The hotspots on risk area in terms of vessel traffic and speed can be identified. The method can be used to provide decision-making support for maritime traffic management.
FLETCHER T., 2010, Geocoding rural addresses in a community contaminated by PFOA: a comparison of methods , Environmental Health, 9:18.
YAO X., 2003, Research issues in spatio-temporaldatamining , In White paper submitted to the University Consortium for Geographic Information Science (UCGIS) workshop on Geospatial Visualization and Knowledge Discovery, Lansdowne, Virginia, Nov (pp. 18-20).
ZANDBERGEN P.A., 2007, Influence of geocoding quality on environmental exposure assessment of children living near high traffic roads , BMC Public
ʻTerrains, Techniques, Theorie: travail interdisciplinaire en Sciences Humaines et Socialesʼ. Rapport de fin de projet, Grenoble, France. 148 pages.
Aubigny (d’) C. & Aubigny (d’) G. (2009), New LISA indices for spatio-temporalDataMining, XVIèmes Rencontres de la Société Francophone de Classification, Grenoble, 2-4 Septembre, France.
Bapat R.B. (2010), Graphs and Matrices, Springer, New York, USA.
Belkin M. & Niyogi P. (2001), Laplacian Eigenmaps and Spectral techniques for Embedding and Clustering. Advances in Neural
 Yang, X.-S. and S. Deb. Cuckoo search via Lévy flights. in Nature & Biologically Inspired Computing, 2009. NaBIC 2009. World Congress on . IEEE,2009, 210-214.
 Žalik, K.R., An efficient k′-means clustering algorithm. Pattern Recognition Letters , 29 , 9, 2008, 1385-1391.
 Zhang, B., M. Hsu, and U. Dayal, K-Harmonic Means -A Spatial Clustering Algorithm with Boosting , in Temporal, Spatial, and Spatio-TemporalDataMining , J. Roddick and K. Hornsby, Editor, Springer Berlin Heidelberg. 2001, 31-45.