Visual Analytics of Human Brain Connectome
Abstract: Visualization plays a vital role in the analysis of multi-modal neuroimaging data. A major challenge in neuroimaging visual analytics is how to integrate structural, functional and connectivity data to form a comprehensive visual context for data exploration, quality control, and hypothesis discovery. In this talk I will present some of our recent work on integrated visualization and analysis solutions for brain imaging data using a combination of scientific visualization, information visualization, machine learning and network analysis techniques. Our emphasis is on generating visual representations that can help detecting salient features for analytics and diagnosis applications.
Bio: Dr. Shiaofen Fang is a Professor of Computer Science and the Chairman of the Department of Computer and Information Science at Indiana University Purdue University Indianapolis (IUPUI). Prof. Fang received his Ph.D in Computer Science from the University of Utah and his BS and MS in Mathematics from Zhejiang University. Prof. Fang’s research interest is in Scientific and Information Visualization, Medical Imaging, Volume Graphics, and Geometric Modeling. He has published extensively in these fields. His research has been funded by the National Science Foundation (NSF), Nation Institutes of Health (NIH), National Institute of Justice (NIJ) and US Department of Defense (DoD).
Visual Analysis in China AI 2.0
Abstract: In this talk, I will briefly introduce the role of visual analysis in China AI 2.0, a new strategy recently released by China Academy of Engineering. I will explain how visual analysis may benefit AI in an interactive way, and the way it may influence the future of AI. Many examples from my team will be demonstrated.
Bio: Wei Chen is a professor in State Key Lab of CAD&CG at Zhejiang University, P.R.China. He has performed research in visualization and visual analysis and published more than 30 IEEE/ACM Transactions and IEEE VIS papers. His current research interests include visualization, visual analytics and bio-medical image computing. For more information, please refer to http://www.cad.zju.edu.cn/home/chenwei.
Deconstructing Graphs by Learning their Grammars
Abstract: In this talk we present current and ongoing work about how to learn the Lego-like building blocks of real world networks in order to gain insights into the mechanisms that underlie network growth and evolution. We recently discovered a relationship between graph theory and formal language theory that thinks like a context free grammar (CFG), but for graphs. The extracted hyperedge replacement grammar (HRG) contains the precise building blocks of the network as well as the instructions by which these building blocks ought to be pieced together to make predictions about the data.
Bio: Tim Weninger is an Assistant Professor at the University of Notre Dame where he directs the Data Science Group and is a member of the Interdisciplinary Center for Networks Science and Applications (ICENSA). His research interests are in data mining, machine learning and network science. The key application of his research is to identify how humans generate, curate and search for information in the pursuit of knowledge. He uses properties of these emergent networks to reason about the nature of relatedness, membership and other abstract and physical phenomena.