My research focuses on the numerical modeling and analysis of impedance-based sensing systems, with a particular emphasis on electrical impedance tomography (EIT). I combine forward and inverse modeling, hardware-level simulations, and advanced regularization techniques to better understand and improve imaging and sensing performance. Using self-implemented finite element studies and multiphysical simulation, I study the influence of sensor geometry, electrode configurations, and noise on measurement quality and reconstruction outcomes.
On the hardware side, I explore high-speed data acquisition and signal generation with FPGAs to build high-speed data pipelines.
A further focus is the integration of physics-informed machine learning approaches (e.g., PINNs) into dynamic reconstruction problems, allowing physical laws such as heat diffusion to be incorporated into data-driven methods.
Overall, my research aims to advance the numerics of impedance-based sensor design by combining computational modeling, hardware validation, and machine learning approaches to enable more robust, accurate, and versatile sensing systems.
