- This event has passed.
David Uminsky, USF: Classifying Atrial Fibrillation via Persistent Homology
February 14 @ 12:30 pm - 2:00 pm
**Coffee is served at the in-person seminar at 101 Howard St. Talks are recorded and posted to our YouTube channel at https://www.youtube.com/channel/UCN0kf0sI01-FXPZdWAA-uMA . **
Topological Data Analysis for Time Series Data: Classifying Atrial Fibrillation via Persistent Homology
Atrial Fibrillation is a heart condition characterized by erratic heart rhythms caused by chaotic propagation of electrical impulses in the atria, leading to numerous health complications. State-of-the-art models employ complex algorithms that extract expert-informed features to improve diagnosis. In this talk we give a gentle introduction to Topological Data Analysis and how to extract algebro-topological features that can be used to help accurately classify single lead electrocardiograms. Via delay embeddings, we map electrocardiograms onto high dimensional point-clouds that convert periodic signals to algebraically computable topological signatures. We derive features from persistent signatures, input them to a simple machine learning algorithm, and benchmark its performance against
winning entries in the 2017 Physionet Computing in Cardiology
David Uminsky joined USF in 2012 and currently is an Associate Professor of Mathematics and Statistics and serves as the Executive Director of USF’s Data Institute which he co-founded in 2016. David was the founding director of USF’s undergraduate Data Science program, the third such undergraduate Data Science degree in the country. From 2014 to 2019, David served as the Program Director of the Master’s in Data Science growing the program from 30 to 80+ students a year. As Executive Director of the Data Institute, David has launched three data science research initiatives in environment and human rights, Wicklow AI in Medicine Research Initiative, and the new Center for Applied Data Ethics.
David was selected in 2015 by the National Academy of Sciences (NAS) as a Kavli Frontiers of Science Fellow. Each year, 100 researchers under the age of 45 are selected by the academy, and 20% of the current NAS were previous Kavli Fellows. David was selected to join the Harvard Data Science Review as an inaugural Associate Editor in 2019.
Before joining USF, he was a combined National Science Foundation and UC President’s Fellow at UCLA, where he was awarded the Chancellor’s Award for postdoctoral research. This award is given to approximately the top 20 postdocs out of more than a thousand who qualify for consideration. David’s core research interests are in applied mathematics. He is interested in unsupervised machine learning, data clustering, algebraic signal processing, as well as pattern formation, dynamical systems and fluids. He has published more than 30 peer review publications in these areas and his work has an H-index of 15. He holds a PhD in Mathematics from Boston University and a BS in Mathematics from Harvey Mudd College.