A 2D Near-Field Microwave Imaging Database for Machine Learning Training

Citation Author(s):
Seth
Cathers
University of Manitoba
Ben
Martin
University of Manitoba
Noah
Stieler
University of Manitoba
Ian
Jeffrey
University of Manitoba
Colin
Gilmore
University of Manitoba
Submitted by:
Colin Gilmore
Last updated:
Mon, 03/18/2024 - 14:42
DOI:
10.21227/rh89-dv06
Data Format:
License:
5
1 rating - Please login to submit your rating.

Abstract 

With the goal of improving machine learning approaches in inverse scattering, we provide an experimental data set collected with a 2D near-field microwave imaging system. Machine learning approaches often train solely on synthetic data, and one of the reasons for this is that no experimentally-derived public data set exists. The imaging system consists of 24 antennas surrounding the imaging region, connected via a switch to a vector network analyzer. The data set contains over 1000 full Scattering parameter scans of five targets at numerous positions from 3-5 GHz.

Funding Agency: 
Natural Sciences and Engineering Research Council of Canada