Artificial Neural Network (ANN) approaches are applied to detect and determine the object class using a special set of the UltraWideBand (UWB) pulse Ground Penetrating Radar (GPR) sounding results. It used the results of GPR sounding with the antenna system, consisting of one radiator and four receiving antennas located around the transmitting antenna. The presence of four receiving antennas and, accordingly, the signals received from four spatially separated positions of the antennas provide a collection of signals received after reflection from an object at different angles and, due to this, to determine the location of the object in a coordinate system, connected to the antenna. We considered the sums and differences of signals received by two of the four antennas in six possible combinations: (1 and 2, 1 and 3, 2 and 3, 1 and 4, etc.). These combinations were then stacked sequentially one by one into one long signal. Synthetic signals constructed in such a way contain many more notable differences and specific information about the class to which the object belongs as well as the location of the searched object compared to the signals obtained by an antenna system with just one radiating and one receiving antenna. It therefore increases the accuracy in determining the object’s coordinates and its classification. The pulse radiation, propagation, and scattering are numerically simulated by the finite difference time domain (FDTD) method. Results from the experiment on mine detection are used to examine ANN too. The set of signals from different objects having different distances from the GPR was used as a training and testing dataset for ANN. The training aims to recognize and classify the detected object as a landmine or other object and to determine its location. The influence of Gaussian noise added to the signals on noise immunity of ANN was investigated. The recognition results obtained by using an ANN ensemble are presented. The ensemble consists of fully connected and recurrent neural networks, gated recurrent units, and a long-short term memory network. The results of the recognition by all ANNs are processed by a meta network to provide a better quality of underground object classification.
The nonsinusoidal waves radiation problem is considered. The Mode Basis Method is accommodated for free space using continuous spectrum parameters. As a result a one-dimensional Klein-Gordon equation is obtained like the evolutionary waveguide equations. The method is examined by a step function radiation problem.
The comparison of approaches to subsurface object recognition based on Artificial Neural Network and Cross-Correlation methods is carried out. The irradiation by ultrashort Gaussian impulse plane electromagnetic wave is used. The information about subsurface objects is received from the reflected wave measured in four points. The time dependence of the amplitude of electrical component of the field is presented in form of time points with constant step. These values are the input data for deep artificial neural network as well as for cross-correlation data processing. The analysis of the stability of an object recognition is made for the presence of additive white noise of different power.
The problem of identification of objects under ground surface is solved by the application of irradiation of the surface by short impulse electromagnetic waves and the use of artificial neural networks (ANN) for the analysis of reflected field characteristics. As input data for ANN the normalized amplitudes of electrical component of the field in determined points of observation in equidistant moments of time are used. As an example of the object for the identification, the metal tube under surface of a ground is considered. The plane electromagnetic wave having Gaussian time dependence is used as an incident field. The influence of a number of hidden layers of ANN on precision of the recognition is investigated.
All components of electromagnetic field radiated from Hertz dipole excited by current with arbitrary time dependence are obtained in time domain by means of vector Hertz technique. The processes of transformation of quasistatic components of field into electromagnetic wave are investigated. The problem of radiation of Hertz dipole with quickly decreasing dipole moment from some constant value to zero is considered. The questions of describing the process of the forming of free electromagnetic field from quasistatic field components in near field zone of dipole are discussed.