Modeling · Intelligence · Design · Optimization Laboratory
Dept. of Electronic Engineering · Soonchunhyang University
EM SOLVERS FDTD + 0 − Ez field (TE mode) FEM Unstructured mesh MoM ∫∫ J·G dS Surface integral eq. train / replace AI / ML ENGINE PINN / SURROGATE MODEL x,y,z,t x y z t h₁ h₂ h₃ out E Physics-Informed Loss ℒ = ℒdata + λℒPDE + μℒbc KEY PROPERTIES Fast Inference Physics Consistency Generalization deploy APPLICATIONS EM Prediction Antenna / RCS Radiation pattern Field prediction PINN result Antenna Design RCS / Scattering WPT Safety (EMF) FPGA Edge Vision FPGA Inference pipeline Sensor CNN FPGA Out Black Ice Detection Semiconductor Defect Real-time Inspection GPU-free Low Latency Low Power
Research overview — AI-accelerated numerical electromagnetics & FPGA edge vision
About the Lab

We build smarter, faster numerical solvers — where physics meets machine intelligence.

Our work spans physics-informed deep learning, fast numerical solvers, and intelligent embedded systems — driven by real engineering problems.

Research Interests
FDTD / FEM / MoM PINN Surrogate Modeling WPT FPGA Vision Reverberation Chamber EMC / EMF