Sign | Register
UDC 519.67.612-087.681.3
Data Processing of Discrete Composite Frequency-Modulated Signals by Means of the Neural Network Analysis
S.N. Darovskikh, South Ural State University, Chelyabinsk, Russian Federation,
A.O. Golovenko, South Ural State University, Chelyabinsk, Russian Federation,
N.S. Nikitin, South Ural State University, Chelyabinsk, Russian Federation,
The algorithm of processing of compound frequency-modulated signals with use of neural networks is described. The task of estimation of neuronet characteristics at which the maximum quality of detection of a signal would be provided was defined as a research task. The algorithm of step-by-step creation of the neural network which is carrying out a task of “compression” of a signal is described. Work has between – disciplinary character, it is written on a joint of such disciplines, as a radar-location and statistical radio engineering. Such algorithm of compression has the similar analog model realized in the form of the coordinated filter. The advantages of this digital algorithm are speed and higher precision. Dynamic neural networks are capable to process multidimensional sets of the sequences of radio pulse signals distributed in time. They allow to distinguish the nonstationary multidimensional images coming to network entrances. The results of the work of the programmatically realized dynamic neural network for processing of discrete compound frequency-modulated broadband signals, illustrations of work of algorithm, the block diagram of a dynamic neural network and the scheme of knot of a neuronet which is carrying out a temporary delay are given. Further this algorithm on field-programmable gate arrays will be realized.
dynamic neural network, radiolocation, wideband signal
1. Dudnik P.I. Aviatsionnye radiolokatsionnye ustroystva [Aviation Radiolocation Devices]. Air Force Academy Named by Zsukovskii Publ., 1986. 533 p.
2. Darovskikh. S.N., Zvonov. B.M., Safin. D.K. [Model of Compression of Sound Information on Neural Networks]. Reports of USSR Science Academy. Series Biology, 1990, no.9, pp. 99–104. (in Russ.)
3. Nichols G.J., Martin A.R., Wallas B., Fuchs A.P. From Neuron to Brain. Moscow, Editorial URSS Publ., 2003. 672 p.
4. Osovskiy S. Neyronnye seti dlya obrabotki informatsii [Neural Networks for Information Processing]. Moscow, Finance and Statistics Publ., 2002. 344 p.
5. Antipov O.I. Analiz i prognozirovanie povedeniya vremennyx ryadov: bifurkacii, katastrofy, prognozirovanie i nejronnye seti [Analysis and Forecasting of Time Series Behavior: Bifurcation, Disaster Prediction and Neural Networks]. Moscow, Radiotehnika Publ., 2011. 350 p.
6. Haykin S. Neural Networks: A Comprehensive Foundation Second Edition. Ontario, Canada, Prentice Hall Press; 2nd revised ed., 1999. 1103 p.
Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control, Radio Electronics, 2015, vol. 15, no. 3, pp. 163-168. (in Russ.) (Brief Reports)