3 February 2014 Visualizing confusion matrices for multidimensional signal detection correlational methods
Author Affiliations +
Abstract
Advances in modeling and simulation for General Recognition Theory have produced more data than can be easily visualized using traditional techniques. In this area of psychological modeling, domain experts are struggling to find effective ways to compare large-scale simulation results. This paper describes methods that adapt the web-based D3 visualization framework combined with pre-processing tools to enable domain specialists to more easily interpret their data. The D3 framework utilizes Javascript and scalable vector graphics (SVG) to generate visualizations that can run readily within the web browser for domain specialists. Parallel coordinate plots and heat maps were developed for identification-confusion matrix data, and the results were shown to a GRT expert for an informal evaluation of their utility. There is a clear benefit to model interpretation from these visualizations when researchers need to interpret larger amounts of simulated data.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yue Zhou, Thomas Wischgoll, Leslie M. Blaha, Ross Smith, Rhonda J. Vickery, "Visualizing confusion matrices for multidimensional signal detection correlational methods", Proc. SPIE 9017, Visualization and Data Analysis 2014, 901709 (3 February 2014); doi: 10.1117/12.2042610; https://doi.org/10.1117/12.2042610
PROCEEDINGS
13 PAGES


SHARE
Back to Top