кандидат технических наук (2010), доцент
Автор 130 научных работ. Сфера научных интересов - нейронные сети; нечеткие логические выводы; алгоритмы ЦОС.
Ph.D. in Engineering (2010), Associate Professor
The author of more than 130 scientific publications. Area of expertise: neural networks; fuzzy logical conclusions; DSP algorithms.
инженер, адъюнкт
Окончил Ставропольский военный институт связи РВ (2005) по специальности "Многоканальные теле коммуникационные сети".
Автор 36 научных работ. Сфера научных интересов - нейронные алгоритмы ЦОС.
engineer, post-graduate
graduate of Stavropol Military Institute of Telecommunications RV (2005) with a degree in Multichannel Telecommunication Networks. The author of 36 scientific publications. Area of expertise: neural DSP algorithms
кандидат технических наук (1999), доцент (2007)
Автор более 150 научных работ. Сфера научных интересов - адаптивная обработка сигналов в радиотехнических системах.
Ph.D. in Engineering (1999), Associate Professor (2007)
The author of more than 150 scientific publications. Area of expertise: adaptive signal processing in radio engineering systems.
кандидат технических наук (2012), преподаватель
Автор 19 научных работ. Сфера научных интересов - помехоустойчивое кодирование в системах радиосвязи.
Ph.D. in Engineering (2012), Professor
The author of 19 scientific publications. Area of expertise: noise-immune coding in radio communication systems.
доцент (2013)
Автор 86 научных работ. Сфера научных интересов - радиотехника; радиосвязь.
Associate Professor (2013)
The author of more than 86 scientific publications. Area of expertise: radio engineering; radio communication.
Рассмотрено использование алгоритмов нейросетевой классификации для решения задачи приема телеграфно-кодовых конструкций, оценена эффективность их применения. Обоснована структура предлагаемой нейросети-классификатора и получены ее параметры. В одинаковых условиях проведено экспериментальное сравнение эффективности применения разработанного метода и классических методов оптимального приема детерминированных сигналов, основанных на корреляционном подходе.
The use of neural network classification algorithms for solving the problem of receiving telegram-code structures is considered. The article provides comparison of the neural network classifiers analyzing the normalized input signal as well as the signal after the binary conversion. Various measures of the code distance in the space of informative features are considered. Recognition comparative results for the selected pair of symbols are given. On the basis of these results the code distance is determined, which ensures the minimum recognition error probability. The results obtained in the developed neural network classifier are compared with those obtained in correlation receivers operating in the signal time and frequency domains. The advantage of neural network algorithm is shown. The structure implementing the developed neural network classifier is provided. It is shown that the procedure for the classifier developing, k \ including selection of information signs and their amount, as well as code distance, is not of general nature and is to be performed for each set of recognizable symbols. It is stated that to generalize the received alphanumeric blocks it is necessary to use the second decision contour where current information on the reception and information on the duration of the observed symbol is supplied, which is the subject of further research.
The authors declare that there are no conflicts of interest present.