No abstract

No abstract

Introduction.The general principles of the technique of synthesis of reflective characteristics of complex surfaces for small wavelengths are considered in the article. The problem is set in the conditions of using sound waves and sonar. The calculated scattering characteristics are obtained using a facet model.

An algorithm for determining the distance to the sound source based on amplitude and frequency characteristics was developed. The algorithm is implemented in the Matlab software environment.

Characteristics of the existing neural networks of GMDH with active neurons are given and their main advantages and disadvantages are analyzed. Two approaches of increasing the efficiency of inductive construction of complex system models from statistical data based on a new hybrid GMDH neural networks with active neurons using methods of computational intelligence are proposed. The effectiveness of these networks is compared with classical approaches to artificial inductive modelling tasks (noisy linear and nonlinear models).