Machine Learning Target Count Prediction in Electromagnetics Using Neural Networks

In this article, we showcase an application of neural networks (NNs) to solve an inverse problem in electromagnetics (EMs). Wires are randomly distributed into an area of known dimensions. The wires are then illuminated with a monochromatic plane wave (PW) at a certain angle of incidence, and the EM field measured at a finite number of uniformly spaced points along the perimeter of the area is then fed into a convolutional neural network (CNN) designed to predict the number of wires. Counting the wires is posed as a supervised classification problem with a known upper limit to the number of wires, and accuracy of 96% has been achieved for the case where the number of the wires is known to be ten or less. A number of approaches have been taken to improve the network performance including frequency variation analysis and illuminating the wire distributions with additional PW angles of incidence. We conclude with an analysis of the network capability to resolve objects based on its performance on known wire distributions, which suggests the existence of a characteristic resolution limit corresponding to the CNN topology.