NeuroVis: exploring interaction techniques by combining dimensional stacking and pixelization to visualize multidimensional multivariate data

Applying a dimensional stacking layout to multidimensional pixelization images yields a highly informative visualization with new possibilities for interactive techniques such as dimension reordering and ad hoc database queries. Pixelization is the mapping of each data point in some set to a pixel in an image. Dimensional stacking is a layout method where N dimensions are projected into 2. In this paper we present NeuroVis, an application that combines both methods to support interactive visual data mining of multidimensional multivariate data. An informal evaluation of how it has been used in neuroscience investigations and classrooms is included. We also provide a generalization of the technique for use in other domains and discuss its utility and limitations. CR Categories: I.3.6 [Computing Methodologies]: Methodology and Techniques—Interaction Techniques; I.6.6 [Computing Methodologies]: Simulation and Modeling—Simulation Output Analysis J.3 [Computer Applications]: Life and Medical Sciences