A 2D-3D visualization support for human-centered rule-mining

Abstract : On account of the enormous amounts of rules that can be produced by data mining algorithms, knowledge post-processing is a diffcult stage in an association rule discovery process. In order to find relevant knowledge, the user needs to rummage through the rules. To make this task easier, we propose a new interactive mining methodology based on well-adapted dynamic visual representations. It allows the user to drive the discovery process by focusing his/her attention on limited subsets of rules. We have implemented our methodology with two complementary 2D and 3D visualization supports. These implementations exploit the user's focus to guide the generation of the rules by means of a specific constraint-based rule-mining algorithm.
Complete list of metadatas

Cited literature [53 references]  Display  Hide  Download

https://hal.inria.fr/inria-00335928
Contributor : Julien Blanchard <>
Submitted on : Friday, October 31, 2008 - 11:07:14 AM
Last modification on : Monday, July 1, 2019 - 12:02:19 PM
Long-term archiving on : Tuesday, October 9, 2012 - 2:43:48 PM

File

papier_2.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Julien Blanchard, Bruno Pinaud, Pascale Kuntz, Fabrice Guillet. A 2D-3D visualization support for human-centered rule-mining. Computers and Graphics, Elsevier, 2007, 31 (3), pp.350-360. ⟨10.1016/j.cag.2007.01.026⟩. ⟨inria-00335928⟩

Share

Metrics

Record views

268

Files downloads

369