NCSA Welcomes 2020-21 Faculty Fellows June 19, 2020 Announcements Artificial IntelligenceArts and HumanitiesData AnalyticsEarth and EnvironmentEngineeringHealth SciencesResearch and Development Share this page: Twitter Facebook LinkedIn Email By Boswell Hutson NCSA has named six new Faculty Fellows for the 2020-21 academic school year. The NCSA Faculty Fellowship is a competitive program for faculty and researchers at the University of Illinois at Urbana-Champaign which provides seed funding for new collaborations that include NCSA staff as integral contributors to the project. The new fellows and their projects are: SUCCESSFUL FORGERIES: ANALYZING FAKELORE FOR ORAL-FORMULAIC EPIC POETRY CHARACTERISTICS Faculty Fellow: David Cooper (Dept. of Slavic Languages and Literatures, College of Liberal Arts and Sciences)NCSA Collaborator: Michal Ondrejcek Abstract: Two Czech manuscripts were taken as genuine monuments of medieval poetry for at least 60 years following their discovery in the early 1800s before they were found to be an unusually successful case of literary forgery. This project will bring textual analysis techniques from information theory to bear on the characterization of oral-formulaic epic poetry’s use of a highly repetitive phraseology and analysis of the Czech manuscripts’ imitation of that model. The developed stemming or lemmatization for Old Czech and other highly inflected Slavic languages, as well as improved text analysis techniques, could be widely used in digital humanities research. AGNET: WEIGHING BLACK HOLES WITH DEEP LEARNING Faculty Fellow: Xin Liu (Dept. of Astronomy, College of Liberal Arts and Sciences)NCSA Collaborators: Vlad Kindratenko, Matias Carrasco Kind Abstract: Supermassive black holes (SMBHs) are usually found at the centers of most galaxies. Measuring SMBH mass is important for fundamental science such as understanding the origin and evolution of SMBHs and enabling the usage of quasars or active galactic nuclei (AGN), however, traditional methods require spectral data which are highly expensive to gather. A pilot program to develop a new, interdisciplinary approach combining astronomy big data with machine learning tools to build a deep learning algorithm, AGNet, that weighs SMBHs using AGN light curves, circumventing the need for expensive spectra will be developed. By training algorithms that directly learn from the data to map out the nonlinear encoding, the field of SMBHs and cosmology will be transformed. SEEING MUSIC THROUGH DATA VISUALIZATION: A BLACK AESTHETIC GENIUS/HIPHOP EXPRESS PROPOSAL Faculty Fellow: Malaika McKee (Dept. of African American Studies, College of Liberal Arts and Sciences)NCSA Collaborators: Robert Sisneros, Colleen Bushell Abstract: This STEAM project will use data visualization techniques to analyze the internal structures of hip-hop music to show how computing can be used to analyze music. Information will be shared with the public through the HIPHOP XPRESS Double Dutch Boom Bus, a mobile public outreach classroom. By examining the internal data structure of music and applying principles of scientific visualization, the researchers will consider the temporality of sound and how that helps uncover internal insights about data architecture, and my also gain new insights about digital signal processing. The project meets a gap on behalf of educating cultural creatives about the important technical understandings embedded in music and enhances understandings from those in the technical field about ways that music creates unseen architectures and analytics. VIRTUAL REALITY INTERACTIVE EXPERIENCE FOR ACTIVELY CONTROLLED AND DEPLOYABLE TENSEGRITY FOOTBRIDGES Faculty Fellow: Ann Sychterz (Dept. of Civil and Environmental Engineering, Grainger College of Engineering)NCSA Collaborator: Robert Sisneros Abstract: Tensegrity structures are pin-jointed systems of bars and cables held stable in a state of self-stress; they are lightweight and can change shape with minimal activation energy. Simulations of tensegrity structures are challenging to visualize and comprehend, which may prevent engineers from including these structures in their projects. By providing a virtual reality (VR) interactive environment to demonstrate to researchers, practicing engineers, students, and the general public the feasibility of a deployable and controllable tensegrity footbridge the researchers will educate people about these deployable systems. The VR interactive environment will utilize form-finding to determine the stresses and deformations of a deployable tensegrity structure, vibration characterization for damage detection, statistical model-data methods for finding potential broken elements following a damage event, and advanced computing algorithms for mitigating the effect of damage on the structure using actuation. The researchers hope this outreach will lead to advanced future technical capabilities for structural engineering in the construction industry. MACHINE LEARNING APPROACHES FOR QUANTIFYING AND VISUALIZING DIETARY EFFECT IN PERSONALIZED NUTRITION Faculty Fellows: Ruoqing Zhu (Dept. of Statistics, College of Liberal Arts and Sciences) and Hannah Holscher (Dept. of Food Science and Human Nutrition, College of Agricultural, Consumer and Environmental Sciences)NCSA Collaborators: Colleen Bushell, Peter Groves, Charles Blatti Abstract: Personalized nutrition is an emerging field that draws attention from the fields of molecular biology, machine learning and statistics. Scientists believe that diet can be used to modulate the microbiome (a collection of trillions of microorganisms that resides within the human gut) to help reduce the risk of developing diseases like Type 2 diabetes and cancer. Microbiome studies are “big data” studies but integration of these large, heterogeneous and “multi-omic” data has become increasingly important for understanding their association with dietary treatment. By studying the keystone species (the organism that helps hold the system together) and microbial signatures of “responders” versus “non-responders” participating in diet-microbiota-health clinical trials, which will inform the use of diet-microbiota-tailored treatments in precision nutrition efforts, the team will develop and verify a new computationally intensive analytical approach necessary to properly study the multi-omic data for the purpose of personalized nutrition, and identify new advanced visualization requirements for the interactive visualization tool. ABOUT NCSA The National Center for Supercomputing Applications at the University of Illinois Urbana-Champaign provides supercomputing and advanced digital resources for the nation’s science enterprise. At NCSA, University of Illinois faculty, staff, students and collaborators from around the globe use these resources to address research challenges for the benefit of science and society. NCSA has been advancing many of the world’s industry giants for over 35 years by bringing industry, researchers and students together to solve grand challenges at rapid speed and scale.