Author(s): Matthew O. Ward, Computer Science Department, Worcester Polytechnic Institute, Worcester, MA 01609

Source: Proc. of IEEE Conference on Visualization (Visualization '94), October, 1994.

Abstract: Much of the attention in visualization research has focussed on data rooted in physical phenomena, which is generally limited to three dimensions (with a temporal attribute creating a fourth dimension). However, many sources of data, for example from surveys and simulations, do not share this dimensional restriction. A critical problem in the analysis of such data is providing researchers with tools to gain insights into characteristics of the data, such as extrema, clusters, trends, anomalies, correlations, and patterns. Several visualization methods have been developed to address this problem, and each has its strengths and weaknesses in terms of the structure of the data (dimensionality, distribution) and data characteristics of interest for which it is most suited. This paper describes a system named XmdvTool which integrates several of the most common methods for projecting multivariate data onto a two-dimensional screen. This integration allows users to explore their data in a variety of formats with ease. A view enhancement mechanism called an N-dimensional brush is also described. The brush allows users to gain insights into spatial relationships over N dimensions by highlighting data which falls within a user-specified subspace. The user can control the shape, size, and position of the subspace via easy-to-use widgets.