2023 APS Logo

IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting

July 23–28, 2023 • Portland, Oregon, USA

23-28 July 2023 • Portland, Oregon, USA

IEEE AP-S/URSI 2023

23-28 July 2023 • Portland, Oregon, USA

WE-A3.1P.5

A Hybrid Electromagnetic Optimization Method Based on Physics-Informed Machine Learning

Yanan Liu, University of Illinois at Urbana Champaign, United States; Hongliang Li, Jian-Ming Jin, University of Illinois at Urbana-Champaign, United States
Session:
Machine Learning in Computational Electromagnetics
Track:
AP-S: Computational & Numerical Techniques
Location:
B 113-114 (OCC)
Session Time:
Wed, 26 Jul, 13:20 - 17:00 PDT (UTC -8)
Presentation Time:
Wed, 26 Jul, 14:40 - 15:00 PDT (UTC -8)
Session Co-Chairs:
Amir Boag, Tel Aviv University and Jian-Ming Jin, University of Illinois at Urbana-Champaign
Presentation
Not logged in.
Discussion
Not logged in.
Session WE-A3.1P
WE-A3.1P.1: Terahertz Antenna Design Using Machine Learning Assisted Global Optimization Techniques
Muhammad Zubair, University of Glasgow, United Kingdom; Mobayode O. Akinsolu, Wrexham Glyndŵr University, United Kingdom; Abdoalbaset Abohmra, Muhammad Imran, Bo Liu, Qammer Hussain Abbasi, University of Glasgow, United Kingdom
WE-A3.1P.2: Analysis of electromagnetic decoupling of an isolation barrier using machine learning
Jaeyoon Park, Jaeyul Choo, Andong National University, Korea (South)
WE-A3.1P.3: 2X Faster Solution of Computational 2D Electrostatic Problems using Artificial Neural Network and Transfer Learning
Pawan Gaire, Shubhendu Bhardwaj, University of Nebraska-Lincoln, United States
WE-A3.1P.4: Hybrid Fourier Neural Network in Solving 2D Electrodynamic Equations in Multilayer Media
Botian Zhang, Yahya Rahmat-Samii, UCLA, United States
WE-A3.1P.5: A Hybrid Electromagnetic Optimization Method Based on Physics-Informed Machine Learning
Yanan Liu, University of Illinois at Urbana Champaign, United States; Hongliang Li, Jian-Ming Jin, University of Illinois at Urbana-Champaign, United States
WE-A3.1P.6: Physics-Informed Machine Learning for Efficient Modeling of High-Frequency Devices
Yanan Liu, Hongliang Li, Jian-Ming Jin, University of Illinois at Urbana-Champaign, United States
WE-A3.1P.7: 2D Eigenmode Analysis Based on Physics Informed Neural Networks
Md Rayhan Khan, Constantinos L. Zekios, Florida International University, United States; Shubhendu Bhardwaj, University of Nebraska-Lincoln, United States; Stavros V. Georgakopoulos, Florida International University, United States
WE-A3.1P.8: Deep Learning Based Metasurface Synthesis from Far-Field Masks
Chen Niu, Hans Paul Schreckenbach, Puyan Mojabi, University of Manitoba, Canada
WE-A3.1P.9: Intelligent Phase Mapping Approach via Neural Networks on Metasurfaces
Lamei Zhang, Wuxia Miao, Bin Zou, Harbin Institute of Technology, China
WE-A3.1P.10: Machine Learning-Assisted Optimization Method with Self-adaptive Hyperparameter Optimization Strategy
Yajie Gong, Qi Wu, Chen Yu, Haiming Wang, Wei Hong, Southeast University, China; Weishuang Yin, ZTE Corporation, China
Resources
No resources available.