Artificial neural networks as approximate procedure in wireless devices designing problems

Abstract

Purpose. Present work is dedicated to the optimal configuration selection and training method of neural network (NN). This NN is architecture's element of modified NN ensemble accepted by authors for implementation of frequency-selective microwave devices design algorithms. Optimal configuration determining of NN. Optimal configuration determining of NN was received by analyzing the results of test NN training with different number of layers and neurons in these layers. The main parameters optimal configuration determining of NN is the approximation quality and total learning time. Choosing of optimal teaching method. NN training methods comparison was carried out for 7 popular training methods: Levenberg-Marquardt backpropagation, BFGS quasi-Newton backpropagation, Bayesian regulation backpropagation, Conjugate gradient backpropagation with Powell-Beale restarts, Gradient descent backpropagation, Gradient descent with momentum backpropagation and Resilient backpropagation. Conclusions. NN using allows to approximate complex features of microwave devices, such as frequency dependencies of S – parameters etc. The approximation accuracy depends on configuration and method of NN training. Increasing the number of NN layers leads to improvement of approximate characteristics. According to our results the most effective is usage of 4 layers and the number of neurons in each layer should be over the range 10 to 20. Optimal training method for complex characteristics is Bayesian regulation backpropagation, for time training reduction can be used Levenberg-Marquardt backpropagation.

Authors and Affiliations

V. Adamenko, G. Mirskikh

Keywords

Related Articles

Radio technical characteristics of loop plasma antennas

Influence of mercury vapors in the frequency range 50-500 MHz on the specific conductivity (SC) of cold plasma of gas discharge by the loopback asymmetrical PA is probed. It is shown that in the injection of mercury vapo...

Essentialities of the contemporary higher technical education paradigm are exposed.

Her distinctive characteristics are analysis. Inherent this paradigm the object contradiction are discussed

Usage of ultra wide-band systems for constructing of radar image

Features of usage ultra wide-band radar systems for constructing of radar image are considered. Constructing of the matched processing section of a signal with the unknown form is considered.

Especially using technology of virtual devices for construct and management of radioelectronic means

Purpose. This paper is dedicated to providing the construct process and control electronic equipment by means of multi-purpose devices developed on the basis of modern information technologies that use virtual space and...

Method of calculation broadband asymmetric vibrator with variable radius along the axis of symmetry

New approach to calculation of the bandwidth of microwave elements for antenna system is offered. It is necessary to develop a method of calculating the basic CWT element, namely broadband pin for optimum performance, co...

Download PDF file
  • EP ID EP309138
  • DOI 10.20535/RADAP.2012.51.41-49
  • Views 71
  • Downloads 0

How To Cite

V. Adamenko, G. Mirskikh (2012). Artificial neural networks as approximate procedure in wireless devices designing problems. Вісник НТУУ КПІ. Серія Радіотехніка, Радіоапаратобудування, 0(51), 41-49. https://europub.co.uk/articles/-A-309138