Using HPC to visualize cultural patterns

Print Friendly, PDF & Email

The High Performance Computing Program established jointly by the DOE and the National Endowment for the Humanities recently announced the first recipients of grants of supercomputing time meant to explore the applications of advanced computing in the humanities. The awards provide computer time on the supers at NERSC, and fund training time to enable researchers to be able to use the resources.

One of those awards went to UC San Diego to support analysis and visualization of patterns in databases of cultural images and video.

“Digitization of media collections, the development of Web 2.0 and the rapid growth of social media have created unique opportunities to study social and cultural processes in new ways,” said principal investigator Lev Manovich, who directs the Software Studies Initiative. “For the first time in human history, we have access to unprecedented amounts of data about people’s cultural behavior and preferences as well as cultural assets in digital form. This grant guarantees that we’ll be able to process that data and extract real meaning from all of that information.”

We don’t usually think of visual data as being computable, but project researchers intend to process “millions of images, paintings, professional photography, and graphic design” as well as tens of thousands of videos.

For the new project to run on DOE supercomputers, researchers will use a number of algorithms to extract image features and structure from the images and video. The resulting metadata will be analyzed using a variety of statistical techniques, including multivariate statistics methods such as factor analysis, cluster analysis, and multidimensional scaling. That statistical analysis and the original data sets will then be used to produce a number of highly detailed visualizations to reveal new patterns in the data.

All results will be posted at Culturevis.org and made freely available.

Trackbacks

  1. […] Using HPC to visualize cultural patterns (insidehpc.com) […]