Multi-task neural network for solving the problem of recognizing the type of QAM and PSK modulation under parametric a priori uncertainty

Objectives. Automatic modulation recognition of unknown signals is an important task for various fields oftechnology such as radio control, radio monitoring, and identification of interference and sources of radio emission. The paper aims to develop a method for recognizing the types of signal modulation under conditions of parametric a priori uncertainty, including the uncertainty of carrier frequency- and initial signal phase values. An additional task consists in estimating the offset values of the carrier frequency or signal phase at the initial stage of the recognition process.

Methods. A multi-task learning with artificial neural network and the theory of cumulants of random variables are used.

Results. For signals with a carrier frequency and initial phase shift, cumulant approaches for QAM-8, APSK-16, QAM-64, and PSK-8 modulations are calculated. A multi-task learning with artificial neural network using cumulant features and a data standardization algorithm is presented. The results of the experiment show that using multi-task learning with an artificial neural network provides high accuracy of recognizing QAM-8 and APSK-16, QAM-64 and PSK-8 modulations with small mismatches of the carrier frequency or initial phase. The accuracy of determining the offset values from the carrier frequency or the initial phase for QAM-8, APSK-16, QAM-64, and PSK-8 modulation is high.

Conclusions. The multi-task learning with neural network using high-order signal cumulants makes it possible not only to recognize modulation types with high accuracy under conditions of a priori uncertainty of signal parameters, but also to determine the offset values of carrier frequency or initial signal phase from expected values.

1. Paramonov A.A., Nguyen M.V. Recognition of types of digital modulation of radio signals with multi-task neural network. Vestnik vozdushno-kosmicheskoi oborony = Aerospace Defense Herald. 2022;4(36):91–97 (in Russ.). Available from URL: https://www.elibrary.ru/item.asp?id=49815162

2. Paramonov A.A., Tikhonova O.V., Nguyen V.M. Recognition of digital modulation of radio signals using a multilayer neural network based on cumulative features. In: Systems of computer mathematics and their applications: Proceedings of the 23rd International Scientific Conference. Smolensk: SmolGU; 2022. Issue 23. P. 23–28 (in Russ.).

3. Nabilkov V.D., Priorov A.L., Dubov M.A. Using of the convolutional neural network CLDNN for classification of modulation types. In: Digital Signal Processing and its Application (DSPA 2021): Reports 23rd International Conference. Moscow: A.S. Popov Russian Scientific and Technical Society of Radio Engineering, Electronics and Communications; 2021. P. 228–231 (in Russ.). Available from URL: https://www.elibrary.ru/item.asp?id=45841831

4. Nguyen M.V., Miloradov G.A., Paramonov A.A. Convolutional neural network in the problem of recognizing digital modulation of radio signals. In: Actual Problems and Prospects for the Development of Radio Engineering and Infocommunication Systems (Radioinfocom 2022): Collection of Scientific Articles based on the Materials of the 6th International Scientific and Practical Conference. Moscow: MIREA – Russian Technological University; 2022. P. 181–185 (in Russ.). Available from URL: https://www.elibrary.ru/item.asp?id=49447332&pff=1

5. Avedyan E.D., Nhich D.V. To the selection of the best cumulants features in the recognition task of the digital modulation kind of the radio signals. Informatizatsiya i svyaz’ = Informatization and Communication. 2015;4:11–15 (in Russ.). Available from URL: https://www.elibrary.ru/item.asp?id=24853422

6. Adjemov S.S., Klenov N.V., Tereshonok M.V., Chirov D.S. Methods for the automatic recognition of digital modulation of signals in cognitive radio systems. Moscow Univ. Phys. Bull.2015;70(6):448–456. https://doi.org/10.3103/S0027134915060028 [Original Russian Text: Adjemov S.S., Klenov N.V., Tereshonok M.V., Chirov D.S. Methods for the automatic recognition of digital modulation of signals in cognitive radio systems. Vestnik Moskovskogo Universiteta. Ser. 3. Fizika. Astronomiya. 2015;6:19–27 (in Russ.). Available from URL: https://www.elibrary.ru/item.asp?id=25580690]

7. Grishin P.S., Shabanov A.V., Shcheglov A.V. Recognition of digital radio signal modulations using a multitasking convolutional neural network. In: Intelligent Information Systems: Theory and Practice: A collection of scientific articles based on the materials of the First All-Russian Conference. Part 1. Kursk: Kursk State University; 2020. P. 22–31 (in Russ.). Available from URL: https://elibrary.ru/KADKBX

8. Arkhipenkov D.V. Analysis of radio signal parameters for emission source identification. Doklady Belorusskogo Gosudarstvennogo Universiteta Informatiki i Radioelektroniki (Doklady BGUIR). 2020;18(1):52–58 (in Russ.). https://doi.org/10.35596/1729-7648-2020-18-1-52-58

9. Kendall M., Stuart A. Teoriya raspredelenii (Distribution Theory): transl. from Engl. Moscow: Nauka; 1966. 588 p. (in Russ.). [Kendall M.G., Stuart A. The Advanced Theory of Statistics. V. 1. Distribution Theory. London; 1963. 433 p.]

10. Haykin S. Neironnye seti: polnyi kurs (Neural networks: a complete course): transl. from Engl. Moscow: Vil’yams; 2006. 1104 p. (in Russ.). [Haykin S. Neural Networks. Upper Saddle River, NJ: Prentice Hall; 1999. 842 p.]

11. Elgendy M. Deep Learning for Vision Systems. Manning Publications Co; 2020. 480 p. ISBN 978-1-6172-9619-2

12. Geron A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. O’Reilly Media, Inc.; 2019. 856 p. ISBN 978-1-4920-3264-9

13. Finlay S. Artificial Intelligence and Machine Learning for Business: A No-Nonsense Guide to Data Driven Technologies. ‎Relativistic; 2017. 150 p.

14. Raschka S., Mirjalili V. Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2. Packt Publishing; 2019. 770 р. ISBN 978-1-7899-5575-0

15. Voronina V.V., Mikheev A.V., Yarushkina N.G., Svyatov K.V. Teoriya i praktika mashinnogo obucheniya (Theory and Practice of Machine Learning). Ul’yanovsk: UISTU; 2017. 290 p. (in Russ.). ISBN 978-5-9795-1712-4