Comparison of ANN and Cross-Correlation Approaches for Ultra Short Pulse Subsurface Survey

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.