TITLE:

What is special about mining spatial datasets?

PRESENTER:

Shashi Shekhar : Biography , Homepage

AFFILIATION:

Computer Science Department, University of Minnesota.

URL:

http://www.cs.umn.edu/~shekhar

SLIDES:

ABSTRACT:

The importance of spatial data mining is growing with the increasing incidence and importance of large geo-spatial datasets such as maps, repositories of remote-sensing images, and the decennial census. Applications include M(obile)-commerce industry (location-based services), NASA (studying the climatological effects of El Nino, land-use classification and global change using satellite imagery), National Institute of Health (predicting the spread of disease), National Geo-spatial Intelligence Agency (creating high resolution three-dimensional maps from satellite imagery), National Institute of Justice (finding crime hot spots), and transportation agencies (detecting local instability in traffic).

Classical data mining techniques often perform poorly when applied to spatial data sets because of the following reasons. First, spatial data is embedded in a continuous space, whereas classical datasets are often discrete. Second, spatial patterns are often local where as classical data mining techniques often focus on global patterns. Finally, one of the common assumptions in classical statistical analysis is that data samples are independently generated. When it comes to the analysis of spatial data, however, the assumption about the independence of samples is generally false because spatial data tends to be highly self correlated. For example, people with similar characteristics, occupation and background tend to cluster together in the same neighborhoods. In spatial statistics this tendency is called spatial autocorrelation. Ignoring spatial autocorrelation when analyzing data with spatial characteristics may produce hypotheses or models that are inaccurate or inconsistent with the data set.

Thus new methods are needed to analyze spatial data to detect spatial patterns. This talk surveys some of the new methods including those for discovering spatial co-locations, detecting spatial outliers and location prediction.

KEYWORDS: Spatial Datasets, Auto-correlation, Spatial data mining.

ACKNOWLEDGEMENTS: This work was supported in part by the National Science Foundation, the National Geo-spatial Intelligence Agency, the U.S. Army (Topological Engineering Center and Army Research Lab.), the Federal Highway Autority, and the University of Minnesota (e.g. Center for Transportation Studies).

NOTE: Some of the results discussed in this talk appeared in the following publications:

  1. S. Shekhar and S. Chawla, Spatial Databases: A Tour (Chapter 7), Prentice Hall 2003, ISBN 0-13-017480-7.
  2. S. Shekhar, P. Zhang, V. R. Raju and Y. Huang, Trends in Spatial Data Mining ( pdf ) , Proc. NSF Workshop on Future Directions in Data Mining (Ed. H. Kargupta et al.), MIT Press, 2004 (isbn 0-262-61203-8). (A revised draft is taking shape for a new edition of this book. Comments are welcome.)