Analysis of transient fields reflected from model of huma body surface using convolutional neural network

The application of the operation of convolution based on artificial neural network processing for the problem of determination of thickness of layered medium layer by impulse irradiation is considered. The impulse fields reflected from the model of human body surface are analyzed by convolutional neural network in time domain directly. The normal incidence of plane wave with Gaussian time form on the layered medium with losses is considered. The reflected electromagnetic field is obtained by FDTD method. Initial data for the neural network analysis are the values of amplitude of electrical component of reflected field in different time points. As an example, the network is trained to determine the thickness of one of the layers of the medium. The stability of the determination is investigated by numerical simulation in presence of interferences, experimental errors and instabilities of medium parameters. The comparison between the determination by two-layered neural network and convolutional neural network is given.