RadViz Deluxe: An Attribute-Aware Display for Multivariate Data

Modern data, such as occurring in chemical engineering, typically entail large collections of samples with numerous dimensional components (or attributes). Visualizing the samples in relation of these components can bring valuable insight. For example, one may be able to see how a certain chemical property is expressed in the samples taken. This could reveal if there are clusters and outliers that have specific distinguishing properties. Current multivariate visualization methods lack the ability to reveal these types of information at a sufficient degree of fidelity since they are not optimized to simultaneously present the relations of the samples as well as the relations of the samples to their attributes. We propose a display that is designed to reveal these multiple relations. Our scheme is based on the concept of RadViz, but enhances the layout with three stages of iterative refinement. These refinements reduce the layout error in terms of three essential relationshipssample to sample, attribute to attribute, and sample to attribute. We demonstrate the effectiveness of our method via various real-world domain examples in the domain of chemical process engineering. In addition, we also formally derive the equivalence of RadViz to a popular multivariate interpolation method called generalized barycentric coordinates.