IEEE AP-S/URSI 2023 || Portland, Oregon, USA || 23-28 July 2023

FR-A4.1P.1

Learning From Noise: An Unsupervised GPR Data Denoising Scheme based on Generative Adversarial Networks

Qiqi Dai, Yee Hui Lee, Nanyang Technological University, Singapore, Singapore; Mohamed Lokman Mohd Yusof, Daryl Lee, National Parks Board, Singapore; Abdulkadir C. Yucel, Nanyang Technological University, Singapore

Session:

EM Modeling and Machine learning for Scattering and Propagation

Track:

AP-S: Propagation & Scattering

Location:

C 120-122 (OCC)

Session Time:

Fri, 28 Jul, 15:20 - 17:00 PDT (UTC -7)

Presentation Time:

Fri, 28 Jul, 15:20 - 15:40 PDT (UTC -7)

Session Co-Chairs:

Francesco Andriulli, Politecnico di Torino and Shutong Qi, University of Toronto

Session FR-A4.1P

FR-A4.1P.1: Learning From Noise: An Unsupervised GPR Data Denoising Scheme based on Generative Adversarial Networks

FR-A4.1P.2: Bistatic Scattering Analysis of Vegetation using Fast Hybrid Method of Full Wave Simulations

Jongwoo Jeong, Leung Tsang, University of Michigan, United States; Andreas Colliander, Simon Yueh, California Institute of Technology, United States

FR-A4.1P.3: Embedding General Antenna Patterns in Machine Learning Based Propagation Models

Aristeidis Seretis, Costas Sarris, University of Toronto, Canada

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

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

Learning From Noise: An Unsupervised GPR Data Denoising Scheme based on Generative Adversarial Networks