Visual data mining with simultaneous rescaling

Visualization is used in data mining for the visual presentation of already discovered patterns and for discovering new patterns visually. Success in both tasks depends on the ability of presenting abstract patterns as simple visual patterns. Getting simple visualizations for complex abstract patterns is an especially challenging problem. A new approach called inverse visualization (IV) is suggested for addressing the problem of visualizing complex patterns. The approach is based on specially designed data preprocessing. Preprocessing based on a transformation theorem is proved in this chapter. A mathematical formalism is derived from the Representative Measurement Theory. The possibility of solving inverse visualization tasks is illustrated on functional nonlinear additive dependencies. The approach is called inverse visualization because it does not use data “as is” and does not follow the traditional sequence: discover pattern → visualize pattern. The new sequence is: convert data to a visualizable form → discover patterns with predefined visualization.

Key words: Visual data mining, simultaneous scaling, non-linear dependency, data pre processing, reverse visualization.