Physics-Assisted Machine Learning for Solving Electrical Impedance Tomography

Abstract

The talk addresses Electrical Impedance Tomography (EIT) using physics-assisted machine learning (ML). EIT is a tomographic imaging method that numerically reconstructs the conductivity of an object using the boundary voltage-current data collected from the surface. EIT has wide and important applications, such as in medical imaging, material engineering, and geoscience. Solving EIT using ML has attracted researchers’ interests in recent years. However, most existing works in this area directly adopt ML as a black box. In fact, researchers have gained, over several decades, much insightful domain knowledge on EIT physics and in addition some of these physical laws present well-known mathematical properties (even analytical formulas), which do not need to be learnt by training with a lot of data. The talk demonstrates that it is of paramount importance to profitably combine ML with the available knowledge on underlying EIT physics. The talk discusses the technical details on how domain knowledge of EIT, including the mathematical and physical principles of the forward problem, as well as traditional non-learning inversion skills, are deployed in machine learning. Finally, some experiences gained by solving various inverse problems are summarized.

About the Speaker

Prof. CHEN Xudong received his BS and MS in Electrical Engineering from Zhejiang University in 1999 and 2001 respectively, and his PhD in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology in 2005. Since 2005, he has been with the National University of Singapore where he is currently a Professor in the Department of Electrical and Computer Engineering.

Prof. Chen’s research interests include mainly electromagnetic wave theories and applications, with a focus on inverse problems and computational imaging. He has published 170 journal papers on inverse scattering problems, material parameter retrieval, microscopy, and optical encryption. He was an Associate Editor of the IEEE Transactions on Microwave Theory and Techniques in 2015-2019 and is currently an Associate Editor of IEEE Transactions on Geoscience and Remote Sensing and IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology. He has also authored the book, Computational Methods for Electromagnetic Inverse Scattering which has been adopted as a textbook by more than 10 undergraduate- and graduate-level courses worldwide.

Prof. Chen is a Fellow of IEEE and a Fellow of the Electromagnetics Academy. He is a recipient of the Young Scientist Award by the International Union of Radio Science in 2010 and the Ulrich L. Rohde Innovative Conference Paper Award at the IEEE International Conference on Computational Electromagnetics in 2019.

For Attendees' Attention

This talk will be held online via Zoom. To attend, please join the Zoom meeting at https://hkust.zoom.us/j/98193288065 (Meeting ID: 981 9328 8065 / Passcode: iasip2022).

About the Program

For more information, please refer to the program website at https://iasprogram.hkust.edu.hk/inverseproblems/.