Knowledge Discovery on Trajectory Data Warehouses: Possible usage of the Data Mining Techniques
Resumo
In this paper we are interested in discussing the possibility of theusage of Data Mining tasks in order to reveal knowledge resident in Trajectory Data Warehouses (TDW). We consider a data stream environment where a set of mobile objects send the data about its location in a irregular and unbounded way. The data volume is stored in a centralized and traditional DW with precomputed aggregations values (preserving the trajectories privacy). Through of analysis of the TDW measures (pre-computed aggregation values) we can reveal some characteristics about trajectories in a given spatio-temporal area. The revealed knowledge can be useful in order to describe or show the occurrence of a real phenomenon. We present a review of a proposed structure of a TDW and discuss the use of Data Mining tasks to improve the analysis of the trajectory data warehouse environment.
Referências
Braz, F., Orlando, S., Orsini, R., Raffaetà, A., Roncato, A., and Silvestri, C. (2007). Approximate aggregations in trajectory data warehouse. In Proc. of ICDE Workshop STDM, pages 536–545.
Dunham, M. H. (2003). Data mining introductory and advanced topics. Prentice Hall.
Gray, J., Chaudhuri, S., Bosworth, A., Layman, A., Reichart, D., Venkatrao, M., Pellow, F., and Pirahesh, H. (1997). Data cube: A relational aggregation operator generalizing group-by, cross-tab and sub-totals. Data Mining and Knowledge Discovery, 1:29–54.
Han, J., Stefanovic, N., and Kopersky, K. (1998). Selective materialization: An efcient method for spatial data cube construction. PAKDD’98, pages 144–158.
Kimball, R. (1996). Data Warehouse Toolkit. John Wiley.
Simpósio Brasileiro de Sistemas de Informação 197 Marchant, P., Briseboi, A., Bedard, Y., and Edwards, G. (2004).
Implementation and evaluation of a hypercube-based method for spatiotemporal exploration and analysis. ISPRS Journal of Photogrammetry and Remote Sensing, 59:6–20.
Rakesh Agrawal, T. I. and Swami, A. N. (1993). Mining association rules between sets of items in large databases. Proceedings of the ACM International Conference on Management of Data, pages 207–216.
Rivest, S., Bedard, Y., and Marchand., P. (2001). Towards better support for spatial decision making: Dening the characteristics of spatial on-line analytical processing(solap). Geomatica, 55(4):539–555.
Shekhar, S., Lu, C., Tan, X., Chawla, S., and Vatsavai, R. (2001). Map Cube: Avisualization Tool for Spatial Data Warehouse, chapter Geographic Data Mining and Knowledge Discovery. Taylor and Francis.
T. Uno, Y. Uchida, T. A. and Arimura, H. (2003). Lcm: An efcient algorithm for enumerating frequent closed item sets. In FIMI’03: Workshop on Frequent Item set Mining Implementations, Florida, USA. IEEE Computer Society.
