Home | About Us | Contact Us | Site Map | FAQs

¹Department of Computer Science, California State University, Carson, CA, U.S.A

²College of Information Science and Technology, Drexel University, Philadephia, PA 19104, U.S.A

³Faculty of Computer Science, Dalhouse University, Halifax, Nova Scotia, Canada

Correspondence to: J Han, Department of Computer Science, California State University, Dominguez Hills, 1000 E. Victoria Street, Carson, CA 90747, U.S.A. Tel: +1 310 2432624; E-mail: jhan@csudh.edu

^*This work was done at and partially sponsored by the University of Waterloo, Canada

We briefly introduce an interactive visualization model, RuleViz, for knowledge discovery and data mining, which consists of five components: data preparation and visualization, interactive data reduction, data preprocessing, pattern discovery, and pattern visualization. With this model, the implementation issues are considered and three implementation paradigms, including image-based paradigm, algorithm-embedded paradigm, and interaction-driven paradigm, are discussed. We implement an interactive visualization system, AViz, which discovers 3D numerical association rules from large data sets based on the image-based paradigm. The framework of the AViz system is presented and each component is explored. To discretize numerical attributes, three approaches, including equal-sized, bin-packing-based equal-depth, and interaction-based approaches are proposed, and the algorithm for mining and visualizing numerical association rules is developed. Our experimental result on a census data set is illustrated, which shows that the AViz system is useful and helpful for discovering and visualizing numerical association rules.

Information Visualization (2003) 2, 105-125. doi:10.1057/palgrave.ivs.9500045

Interactive information visualization; data mining; knowledge discovery in databases; association rules