Data Visualization

Massive amounts of data are created by Internet use, an expanding number of sensors in the environment, and scientific research such as large-scale simulations. In many fields, the challenge has shifted from generating sufficient amounts of data to understanding and using it. Data visualization presents data in ways that best yield insight and support decisions—even as computational science pushes toward exascale capacity and new devices add to the data tsunami via the “Internet of Things.” Amid these advances, managing the scale and complexity of the visualization process can be daunting.

Developing visualizations requires creating a tractable representation of the data, then interactively manipulating and querying it. Often researchers must enable users to traverse data sets ranging from terabytes to petabytes. To design visualizations, researchers combine techniques from several disciplines, including data mining, machine learning, and human-computer interaction.

Effective visualization helps users analyze and reason about data and evidence. It makes complex data more accessible, understandable and usable.

CSE faculty Polo Chau and Jimeng Sun are part of the interdisciplinary GT Visualization (Vis) Group. Research areas of the larger GT Vis Group include information visualization, visual communication and design, data and visual analytics, and visualization in fields of business, journalism, humanities, and education.

Link for GT Vis Group: