Share Email Print

Proceedings Paper

Extending the dimensionality of flatland with attribute view probabilistic models
Author(s): Eric Neufeld; Mikelis Bickis; Kevin Grant
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In much of Bertin's Semiology of Graphics, marks representing individuals are arranged on paper according to their various attributes (components). Paper and computer monitors can conveniently map two attributes to width and height, and can map other attributes into nonspatial dimensions such as texture, or colour. Good visualizations exploit the human perceptual apparatus so that key relationships are quickly detected as interesting patterns. Graphical models take a somewhat dual approach with respect to the original information. Components, rather than individuals, are represented as marks. Links between marks represent conceptually simple, easily computable, and typically probabilistic relationships of possibly varying strength, and the viewer studies the diagram to discover deeper relationships. Although visually annotated graphical models have been around for almost a century, they have not been widely used. We argue that they have the potential to represent multivariate data as generically as pie charts represent univariate data. The present work suggests a semiology for graphical models, and discusses the consequences for information visualization.

Paper Details

Date Published: 28 January 2008
PDF: 8 pages
Proc. SPIE 6809, Visualization and Data Analysis 2008, 680905 (28 January 2008); doi: 10.1117/12.767279
Show Author Affiliations
Eric Neufeld, Univ. of Saskatchewan (Canada)
Mikelis Bickis, Univ. of Saskatchewan (Canada)
Kevin Grant, Univ. of Lethbridge (Canada)

Published in SPIE Proceedings Vol. 6809:
Visualization and Data Analysis 2008
Katy Börner; Matti T. Gröhn; Jinah Park; Jonathan C. Roberts, Editor(s)

© SPIE. Terms of Use
Back to Top