DOI
10.34229/KCA2522-9664.26.4.13
UDC 004.93+621.396
V.Yu. Semenov
Kyiv Academuc University, Kyiv, Ukraine,
vasyl.delta@gmail.com
Ye.V. Semenova
Institute of Mathematics, National Academy of Sciences of Ukraine,
Kyiv, Ukraine; Kyiv Academuc University, Kyiv, Ukraine,
semenovaevgen@gmail.com
METHOD FOR THE BLIND SEPARATION OF PSK SIGNALS
BASED ON NEURAL NETWORK
Abstract. The task of single-channel blind separation of two PSK (Phase Shift Keying) signals with unknown parameters is considered. This problem is particularly important for the case of communications when two signals occupy the same frequency bandwidth. It is shown that blind separation problem can be reduced to multiclass classification task which can be solved by existing machine learning methods. In particular, in this paper four-layered neural network is employed for this task. The effectiveness of method is verified on BPSK and QPSK signals with different amplitude ratios and for different noise levels. It is also shown that at the absence of the second signal proposed separation method effectively performs the demodulation of the remaining signal.
Keywords: blind separation, BPSK, QPSK, neural network.
full text
REFERENCES
- Agne C., Cornell B., Dale M., Keams R., Lee F. Shared-spectrum bandwidth efficient satellite communications. 2010 IEEE Military Communications Conference (MILCOM 2010). 2010. P. 341–346. https://doi.org/10.1109/MILCOM.2010.5674844.
- Hyvrinen A., Oja E. Independent component analysis: algorithms and applications. Neural Networks. 2000. Vol. 13, N 4–5. P. 411–430. https://doi.org/10.1016/S0893-6080(00)00026-5.
- Gouldieff V., Palicot J. MISO estimation of asynchronously mixed BPSK sources. 2015 23rd European Signal Processing Conference (EUSIPCO). 2015. P. 369–373. https://doi.org/10.1109/EUSIPCO.2015.7362407.
- Semenov V., Semenova Ye. Method for the single-channel blind separation based on particle filtering. Physico-Mathematical Modelling and Informational Technologies. 2021. Vol. 32. P. 22–26.
- Chi W., Hua P., Zeyu Q. Blind separation of PCMA signals based on neural network. MATEC Web of Conferences. 2018. Vol. 173. Article number 03045. https://doi.org/10.1051/matecconf/201817303045.
- Tu S. L., Zheng H., Gu N. Single-channel blind separation of two QPSK signals using per-survivor processing. 2008 IEEE Asia Pacific Conference on Circuits and Systems. 2008. P. 473–476. https://doi.org/10.1109/APCCAS.2008.4746059.
- O’Shea T., Hoydis J. An introduction to deep learning for the physical layer. IEEE Transactions on Cognitive Communications and Networking. 2017. Vol. 3, N 4. P. 563–575. https://doi.org/10.1109/TCCN.2017.2758370.
- Semenov V., Semenova Ye. Applying machine learning methods to certain problems of digital signal processing in telecommunication problems. Cybernetics and Systems Analysis. 2025. Vol. 61, N 4. P. 697–704. https://doi.org/10.1007/s10559-025-00803-w.
- Semenov V., Semenova Ye. Method for the automatic modulation classification for the sums of phase-shift-keying signals based on polynomial features. Proc. 2024 IEEE 42nd International Conference on Electronics and Nanotechnology (ELNANO) (13–16 May 2024, Kyiv, Ukraine). 2024. P. 587–590. https://doi.org/10.1109/ELNANO63394.2024.10756909.
- Masters D., Luschi C. Revisiting small batch training for deep neural networks. arXiv:1804.07612 [cs.LG]. 20 Apr 2018. https://doi.org/10.48550/arXiv.1804.07612.
