Skip to main content Accessibility help

Discovering Knowledge from AIS Database for Application in VTS

  • Ming-Cheng Tsou (a1)


The widespread use of the Automatic Identification System (AIS) has had a significant impact on maritime technology. AIS enables the Vessel Traffic Service (VTS) not only to offer commonly known functions such as identification, tracking and monitoring of vessels, but also to provide rich real-time information that is useful for marine traffic investigation, statistical analysis and theoretical research. However, due to the rapid accumulation of AIS observation data, the VTS platform is often unable quickly and effectively to absorb and analyze it. Traditional observation and analysis methods are becoming less suitable for the modern AIS generation of VTS. In view of this, we applied the same data mining technique used for business intelligence discovery (in Customer Relation Management (CRM) business marketing) to the analysis of AIS observation data. This recasts the marine traffic problem as a business-marketing problem and integrates technologies such as Geographic Information Systems (GIS), database management systems, data warehousing and data mining to facilitate the discovery of hidden and valuable information in a huge amount of observation data. Consequently, this provides the marine traffic managers with a useful strategic planning resource.


Corresponding author


Hide All
Agrawal, R., Imielinske, T. and Swami, A. (1993). Mining association rules between sets of items in large database, Proceedings Of ACM-SIGMOD 1993 Int. Conference of Management of data, Washington, D.C, 207216.
Agrawal, R. and Srikant, R. (1994). Fast algorithms for mining association rules, Proceedings of the 20th International Conference on very large database (VLDB), Santiago: Chile, 487499.
Barratt, M. J. (1973). Encounter Rates in a Marine Traffic Seperation Scheme. The Journal of Navigation, 26(4), 458465.
Beattie, J. H. (1971). Traffic Flow Measurements in the Dover Strait. The Journal of Navigation, 24(3), 325340.
Berry, M. A. and Linoff, G. S. (2000). Mastering Data Mining: The Art & Science of Customer Relationship Management, New York:Wiley
Bradshaw, M. R. and Jones, K. D. (1980). Information Systems in Ports. The Journal of Navigation, 33(3), 370378.
Draper, J. and Bennett, C. (1972). Modelling Encounter Rates in Marine Traffic Flows with Particular Application to the Dover Strait. The Journal of Navigation, 25(3), 381382.
Carter, A. (2001). Intelligent Transportation Systems. The Journal of Navigation, 54(2), 5764.
Chang, S. J. (2004). Development and Analysis of AIS Applications as an Efficient Tool for Vessel Traffic Service. Proceedings of MTIS/IEEE TECHNO-OCEAN'04, 4, 22492253.
Ciletti, M. D. (1978). Traffic Models for use in Vessel Traffic Systems. The Journal of Navigation, 31(3), 104116.
Colley, B. A., Curtis, R. G. and Stockel, C. T. (1984). A Marine Traffic Flow and Collision Avoidance Computer Simulation. The Journal of Navigation, 37(2), 232250.
Dahlbom, A. and Nuklasson, L. (2007). Trajectory Clustering and Coastal Surveillance. Proceeding of Information Confusion, 2007 International Conference, 18.
Degré, T. (1995). The Management of Marine Traffic, A Survey of Current and Possible Future Measures. The Journal of Navigation, 48(1), 5369.
Ester, M., Kriegel, H.-P. and Sander, J. (1997). Spatial data mining: a database approach, Proceedings of 5th International Symp. On Spatial Database (SSD'97), 4766.
Frawley, W., Piatesky-Shapiro, G. and Matheus, C. (1991). Knowledge discovery in database: an overview, In Fayyad, U. M., Piatestky-Shaprio, G., Smyth, P. and Ulthurusamy, R. (eds.), Knowledge Discovery in Database, Cambridge, Massachusetts: MIT Press.
Fujii, Y. (1977). Development of Marine Traffic Engineering in Japan. The Journal of Navigation, 30(1), 8693.
Fujii, Y. and Tanaka, K. (1971). Traffic Capacity. The Journal of Navigation, 24(4), 543552.
Goodwin, E. M. (1978). Marine Encounter Rates. The Journal of Navigation, 31(3), 357369.
Han, J. and Kamber, M. (2000). Data Mining: Concepts and Techniques, New York: Morgan Kaufmann Publisher.
Hara, K. (1977). A Method for Estimating the Voyage Distribution of Marine Traffic. The Journal of Navigation, 30(3), 386393.
Harre, I. (2000). AIS Adding New Quality to VTS Systems. The Journal of Navigation, 53(3), 527539.
Koperski, K., Adhihary, J. and Han, J. (1996). Spatial data mining: progress and challenges survey paper, Proceeding of SIGMOD'96 Workshop on Ressearch Issues on Data Mining and Knowledge Discovery.
Koperski, K., Adhihary, J. and Han, J. (1998) Mining knowledge in geographical data, Communication of ACM
Li, X., Han, J. and Kim, S. (2006). Motion-Alert: Automatic Anomaly Detection in Massive Moving Objects. Proceedings of IEEE International Conference on Intelligence and Security Informatics, ISI 2006, 3975, 166177.
Miller, H. J. and Han, J. (2001). Geographic data mining and knowledge: an overview, Geographic Data Mining and Knowledge Discover, New York: Taylor & Francis, 333
Naisbitt, J. (1982). Megatrends: Ten New Directions Transforming Our Lives, Warner Books.
Roiger, R. J. and Geatz, M. W. (2002). Data Mining – A Tutorial-Based Primer, New York: Addison Wesley.
Toyoda, S. and Fujii, Y. (1971). Marine Traffic Engineering. The Journal of Navigation, 24(1), 2434.
Wepster, A. (1981). European Cooperation in Science and Technology. The Journal of Navigation, 24(3), 485487.
Yamaguchi, A. and Sakaki, S. (1971). Traffic surveys in Japan. The Journal of Navigation, 24(4), 521534.
Yao, C., Liu, Z. and Wu, Z. (2010). Distribution Diagram of Ship Tracks Based on Radar Observation in Marine Traffic Survey. The Journal of Navigation, 63(1), 129136.
Zheng, B., Chen, J., Xia, S. and Jin, Y. (2009). Analysis of Marine Traffic flow Characteristics Based on Data Mining (In Chinese). Navigation of China, 32(1), 6063.


Related content

Powered by UNSILO

Discovering Knowledge from AIS Database for Application in VTS

  • Ming-Cheng Tsou (a1)


Altmetric attention score

Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed.