Visualizing the process of knowledge discovery

Most existing visualization systems stress either the original data visuali zation or the discovered knowledge visualization, such as decision tree, ne ural network. rules, etc., but lack the abilities to visualize the entire p rocess of knowledge discovery. We propose an interactive model, RuleViz, fo r visualizing the process of knowledge discovery and data mining. The RuleV iz model consists of five components, each or which can be interacted and v isualized by using different visualization techniques. According to this mo del two interactive systems, AViz and CViz, for visualizing the process of discovering numerical association rules and the process of learning classif ication rules have been implemented, respectively. To preprocess the data, each system provides users with three approaches for discretizing numerical attributes and the corresponding rule discovery algorithms. The discretiza tion approaches and the algorithms for discovering association rules and le arning classification rules are presented, and the approaches to visualizin g discretized data and discovered rules are developed. The discovery of num erical association rules in AViz is based on image-based mining algorithm, while, in CViz, the classification rules are learned in terms of a logical rule induction algorithm. We also demonstrate our experimental results with AViz and CViz on the census data sets. UCI data sets, and artificial data sets. (C) 2000 SPIE and IS&T. [S107-9909(00)01304-0].