Current Project : Visual Data Mining

Visual Data Mining

About Visual Data Mining

The 3D Group is studying means of exploiting interactive 3D graphics to facilitate and guide the statistical analysis of large data sets. We have developed an interactive application that allows users to directly and interactively manipulate their data set, divide it into clusters, and navigate through the cluster hierarchy. The tool can be used to visualize the results of a traditional statistical analysis. It can also be used as a way to identify local group information that is generally difficult or even impossible to identify with the traditional statistics toolbox. In this mode of operation, interactive visualization effectively guides the analysis.

Most development on this project was the work of undergraduate interns participating in the NSF REU program of the CSC and Art Departments.

Participants
  • Qing Liu (M.S. Computer Science 2005)
  • Ron A. Fackler (REU Intern 2006)
  • Jean-Yves Hervé
Funding

Partial support of this research by the National Center for Research Resources, NIH, through grant number RR16457 (RI BRIN) and of the National Science Foundation (REU) is gratefully acknowledged.

Publications

Jean-Yves Hervé, Q. Liu, M. Nicholson, L. González, and T. Mather, "Combining interactive visualization and statistics to detect patterns in environmental data," in Proceedings of 7th International Conference on Teaching Statistics, Salvador, Bahia, Brazil, July 2006.