Zhurnal Radioelektroniki - Journal of Radio Electronics. eISSN 1684-1719. 2023. №2
Contents

Full text in Russian (pdf)

DOI: https://doi.org/10.30898/1684-1719.2023.2.3

NEURAL NETWORK ALGORITHM FOR SIGNAL DETECTION

WITH BINARY PULSE POSITION MODULATION

Yu.E. Korchagin, K.D. Titov, O.N. Zavalishina

Voronezh State University

394018, Russia, Voronezh, Universitetskaya sq., 1

The paper was received January 8, 2023

Abstract. In the work, a neural network method for detecting signals with binary position-pulse modulation was studied. The detection process was reduced to distinguishing signals by a neural network, the architecture of which included convolutional and fully-connected layers. The network was trained on the basis of a set of labeled realizations of a sum of signals with noise, which were represented by discrete samples. The TensorFlow library was used to model and train the network. A bell video pulse and a quasi-radio signal with a bell modulating function were used as possible signal models. The functioning efficiency of the trained neural network was studied by the methods of statistical modeling on a computer. The detection quality of the neural network algorithm is compared with the classical one synthesized in the framework of the statistical decision theory. The possibility of training a neural network detector with an unknown duration of the received signals is investigated. The efficiency of the neural network detector is compared with the quasi-optimal one, which does not take into account the possible unknown of the signal duration. It is shown that the neural network detection algorithm is significantly inferior to the optimal one synthesized by the maximum likelihood method. However, in the presence of a priori uncertainty about the signal duration, the quasi-optimal detector is inferior in efficiency to the neural network one. Recommendations are formulated for a reasonable choice of the detector, depending on the required quality of its work.

Key words: position-pulse modulation, signal distinguishing, neural network, convolutional layer, fully-connected layer, TensorFlow, training, cost function, categorical cross-entropy, unknown duration.

Financing: This work is supported by the Russian Science Foundation under grant 21-19-00323, https://rscf.ru/en/project/21-19-00323/.

Corresponding author: Titov Konstantin Dmitrievich, titovkd@gmail.com

References

1. Teplyakov I.M., Roshchin B.V., Fomin A.I., Weitzel V.A. Radiosistemy peredachi informacii [Radio systems of information transmission]. Moscow, Radio i Svyaz’ Publ. 1982. 264 p. (In Russian)

2. Parfenov V.I, Golovanov D.Y. Noise stability of signal reception algorithms with multipulse pulse-position modulation. Computer Optics. V.42. №1. P.167-174. 2018. https://doi.org/10.18287/2412-6179-2018-42-1-167-174 (In Russian)

3. Wintzell O., Zigangirov D.K., Zigangirov K.S. On the Capacity of a Pulse Position Hopped CDMA System. IEEE Transactions on Information Theory. 2001. V.47. №6. P.2630-2644. https://doi.org/10.1109/18.945282

4. IEEE Standard for Low-Rate Wireless Networks. IEEE Std 802.15.4-2020 (Revision of IEEE Std 802.15.4-2015). 23 July 2020. P.1-800. https://doi.org/10.1109/IEEESTD.2020.9144691

5. Patent US-6687293-B1. Stephen R. Loyer, amuel Alexander Method, system and apparatus for calibrating a Pulse Position Modulation (PPM) decoder to a PPM signal. Application Date: 22.06.2000. Publication Date: 02.02.2004.
URL: https://portal.unifiedpatents.com/patents/patent/US-6687293-B1IEEE Standard for Low-Rate Wireless Networks (Revision of IEEE Std 802.15.4-2015). 2020. 510 p.

6. Tikhonov V.I. Optimal'nyi priem signalov. [Optimal signal reception]. Moscow, Radio i svjaz' Publ. 1983. 320 p. (In Russian)

7. Van Trees H.L. Detection, Estimation, and Modulation Theory, Part I: Detection, Estimation, and Linear Modulation Theory, 2nd edition. John Wiley & Sons, Inc. 2013. 1151 p.

8. Repin V.G., Tartakovsky G.P. Statisticheskii sintez pri apriornoi neopredelennosti i adaptatsiya informatsionnykh system [Statistical synthesis with a priori uncertainty and adaptation of information systems], Moscow, Sovetskoye Radio Publ. 1977. 432 p. (In Russian)

9. Korchagin Yu.E., Titov K.D. Sintez i analiz obrabotki sverkhshirokopolosnykh kvaziradiosignalov [Synthesis and analysis of processing ultra-wideband quasi-radio signals]. Voronezh, State Univ. Press. 2019. 128 p. (In Russian)

For citation:

Korchagin Yu.E., Titov K.D., Zavalishina O.N. Neural network algorithm for signal detection with binary pulse position modulation. Zhurnal radioelektroniki [Journal of Radio Electronics] [online]. 2023. №2. https://doi.org/10.30898/1684-1719.2023.2.3 (In Russian)