Enhancing Interactive Visual Data Analysis by Statistical Functionality
Both information visualization and statistics analyse high dimensional data, but these sciences
apply different systems to explore datasets. While techniques of the former field makes use of the user's pattern
recognition skills, statistical algorithms apply the capabilities of computers. Based on this observation an
interactive combination of techniques of both sciences can help to overcome their drawbacks. For this purpose a
library was compiled that contains statistical routines, which are of high importance for information visualization
techniques and allow a fast modification of their results, to integrate possible adaptations in the interactive
visual data mining process.
Keywords: Data Mining, Information Visualization, Clustering, Dimension Reduction, Outlier Detection
Paper
|