Weihua Zhou, assistant professor, Health Informatics, and member of the ICC’s Center for Data Sciences, is the principal investigator on a project that has received a $24,497 federal pass-through research and development grant from Tulane University. The project is titled, “Trans-Omics Integration of Multi-Omics Studies for Male Osteoporosis.” This is a 7-1/2 month project.
The College of Computing (CC) will present a Friday Seminar Talk on November 15, at 3:00 p.m. in Rekhi 214. Featured this week is Weihua Zhou, assistant professor of Health Informatics and member of the ICC’s Center for Data Sciences. He will present his research titled: “Information retrieval and knowledge discovery from cardiovascular images to improve the treatment of heart failure.” Refreshments will be served.
Abstract: More than 5 million Americans live with heart failure, and the annual new incidence is about 670,000. Once diagnosed, around 50% of patients with heart failure will die within 5 years. Cardiac resynchronization therapy (CRT) is a standard treatment for heart failure. However, based on the current guidelines, 30-40% of patients who have CRT do not benefit from CRT. One of Zhou’s research projects is to improve CRT favorable response by information retrieval and knowledge discovery from clinical records and cardiovascular images. By applying statistical analysis, machine learning, and computer vision to his unique CRT patient database, Zhou has made a number of innovations to select appropriate patients and navigate the real-time surgery. His CRT software toolkit is being validated by 17 hospitals in a large prospective clinical trial.
Zhuo Feng (ECE/ICC) is Principal Investigator on a project that has received a $500,000 research and development grant from the National Science Foundation. This potential three-year project is titled, “SHF: Small: Spectral Reduction of Large Graphs and Circuit Networks.”
This research project will investigate a truly-scalable yet unified spectral graph reduction approach that allows reducing large-scale, real-world directed and undirected graphs with guaranteed preservation of the original graph spectra. Unlike prior methods that are only suitable for handling specific types of graphs (e.g. undirected or strongly-connected graphs), this project uses a more universal approach and thus will allow for spectral reduction of a much wider range of real-world graphs that may involve billions of elements:
- spectrally-reduced social (data) networks allow for more efficiently modeling, mining and analysis of large social (data) networks;
- spectrally-reduced neural networks allow for more scalable model training and processing in emerging machine learning tasks;
- spectrally-reduced web-graphs allow for much faster computations of personalized PageRank vectors;
- spectrally-reduced integrated circuit networks will lead to more efficient partitioning, modeling, simulation, optimization and verification of large chip designs, etc.
From Tech Today, June 21, 2019