Visual analytics of multidimensional data using immersive high performance computing center data

Abstract

In the era of big data, visualizing data techniques have had to modernize in order to cover the increase in data volume and dimension. The recent explosion in popularity of virtual reality technology has provided an immersive platform for users with a vast number of opportunities for data not only to be visualized but also to be interacted with. This project introduces HiperVR, a virtual reality environment that simulates the High Performance Computing Center at Texas Tech University with a new data analysis visualization tool. This system simulates the server room on campus and provides data insight on each node. The data analysis visualization tool is a 3D scatter plot matrix able to represent relationships of up to 4 attributes. This visualization implements Scagnostics, a data analysis tool, in order to find data features in each scatter plot. Using data features, such as outlying and monotonic scores, users are able to filter the matrix and focus on the scatter plots that they are interested in. Thus, HiperVR serves as an application of the integration of data analysis visualizations into a virtual reality simulation.