Skip to main content
SpringerLink
Log in

Multilayer Radial Basis Function Neural Network for Symbol Timing Recovery

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

In digital communication, synchronization between transmitter and receiver is essential for ensuring proper system performance. Error in the receiver symbol time sampling can significantly increase the bit error rate to unacceptable levels. In this paper, we propose a multilayer radial basis function neural network symbol-timing recovery (MRBFNN-STR). The proposed solution has been implemented for a 64-QAM (quadrature and amplitude modulation) system. Results show that the MRBFNN-STR improves the modulation error ratio up to 3.4 dB and reduces the bit error rate by almost one order of magnitude for 100 ppm (part per million) clock offset and signal to noise ratios above 25 dB compared to the classic widely used Gardner-Farrow’s approach. The MRBFNN is able to follow the system dynamics and to generalize, presenting good performance even when under operational situations not presented during the training phase (different clock offset, signal to noise ratio, etc.) and with lower-order modulation schemes, such as 32-QAM, 16-QAM, and QPSK (quadrature phase shift keying), without retraining. Due to the parallel nature of the MRBFNN architecture and the reduced complexity required for inference, it can be efficiently implemented in hardware and easily integrated into communication receivers, representing a feasible solution for receiver time synchronization.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Gardner FM (1993) Interpolation in digital modems - Part I: fundamentals. IEEE Trans Commun 41(3):501–507. https://doi.org/10.1109/26.221081

    Article  MATH  Google Scholar 

  2. Gardner FM (1986) A BPSK/QPSK timing-error detector for sampled receivers. IEEE Trans Commun 34(5):423–429. https://doi.org/10.1109/TCOM.1986.1096561

    Article  Google Scholar 

  3. Harris FJ, Dick C, Jhu US (2018) Comparing statistics of maximum likelihood, Gardner, and Band edge filter timing recovery. In: 21st International Symposium on Wireless Personal Multimedia Communications (WPMC). (IEEE)594–599. Available from: https://doi.org/10.1109/WPMC.2018.8713000

  4. Awan M, Koch P (2010) Combined matched filter and arbitrary interpolator for symbol timing synchronization in SDR receivers. In: 13th IEEE Symposium on Design and Diagnostics of Electronic Circuits and Systems. (IEEE). 153–156. Available from: https://doi.org/10.1109/DDECS.2010.5491797

  5. Bazdresch M, Al-Hamiri M (2017) Symbol synchronization of the Alamouti space-time block code with the Gardner algorithm. In: 8th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON). (IEEE) 635–639. Available from: https://doi.org/10.1109/IEMCON.2017.8117181

  6. Flohberger M, Gappmair W, Koudelka O (2008) Open-loop analysis of an error detector for blind symbol timing recovery using baud-rate samples. In: 2008 IEEE International Workshop on Satellite and Space Communications. (IEEE)176–180 https://doi.org/10.1109/IWSSC.2008.4656779

  7. Tabares JA, Ghasemi S, Velásquez JC, Prat J (2020) Coherent ultra-dense WDM-PON enabled by complexity-reduced digital transceivers. J Lightw Technol 38(6):1305–1313. https://doi.org/10.1109/JLT.2019.2957882

    Article  Google Scholar 

  8. Pan Y, Yan L, Yi A, Jiang L, Pan W, Luo B (2019) Simultaneous demultiplexing of 2xPDM-PAM4 signals using simplified receiver. Opt Exp 27(3):1869–1876. https://doi.org/10.1364/OE.27.001869

    Article  Google Scholar 

  9. Zhou H, Li Y, Lu D, Yue L, Gao C, Liu Y et al (2019) Joint clock recovery and feed-forward equalization for PAM4 transmission. Opt Exp 27(8):11385–11395. https://doi.org/10.1364/OE.27.011385

    Article  Google Scholar 

  10. Barbosa FA, Rossi SM, Mello DAA (2020) Clock recovery limitations in probabilistically shaped transmission. In: 2020 Optical Fiber Communications Conference and Exhibition (OFC). (IEEE) 1–3. Available from: https://doi.org/10.1364/OFC.2020.M4J.4

  11. Xu J, Li Y, Hong X, Qiu J, Zuo Y, Li W et al (2021) Multiplier-free parallel fixed-point adaptive equalizer for real-time digital coherent communication. IEEE Commun Lett 25(7):2380–2384. https://doi.org/10.1109/LCOMM.2021.3074323

    Article  Google Scholar 

  12. Bertolucci M, Cassettari R, Fanucci L (2021) On the frequency carrier offset and symbol timing estimation for CCSDS 131.2-B-1 high data-rate telemetry receivers. Sensors. https://doi.org/10.3390/s21092915

    Article  Google Scholar 

  13. Erup L, Gardner FM, Harris RA (1993) Interpolation in digital modems - Part II: implementation and performance. IEEE Trans Commun 41(6):998–1008. https://doi.org/10.1109/26.231921

    Article  Google Scholar 

  14. Zhang W, Wang X, You W, Chen J, Dai P, Zhang P (2020) RESLS: region and edge synergetic level set framework for image segmentation. IEEE Trans Image Process 29:57–71. https://doi.org/10.1109/TIP.2019.2928134

    Article  MathSciNet  MATH  Google Scholar 

  15. Yu X, Ye X, Zhang S (2022) Floating pollutant image target extraction algorithm based on immune extremum region. Digital Signal Process 123:103442. https://doi.org/10.1016/j.dsp.2022.103442

    Article  Google Scholar 

  16. Mayer KS, Soares JA, Pinto RP, Rothenberg CE, Arantes DS, Mello DAA (2020) Soft failure localization using machine learning with SDN-based network-wide telemetry. In: 46th European Conference on Optical Communication. (IEEE) 1–4. Available from: https://doi.org/10.1109/ECOC48923.2020.9333313

  17. Mayer KS, Soares JA, Pinto RP, Rothenberg CE, Arantes DS, Mello DAA (2021) Machine-learning-based soft-failure localization with partial software-defined networking telemetry. J Opt Commun Netw 13(10):E122–E131. https://doi.org/10.1364/JOCN.424654

    Article  Google Scholar 

  18. Mayer KS, Pinto RP, Soares JA, Arantes DS, Rothenberg C, Cavalcante V et al (2022) Demonstration of ML-assisted soft-failure localization based on network digital twins. J Lightw Technol. https://doi.org/10.1109/JLT.2022.3170278

    Article  Google Scholar 

  19. Swain RR, Khilar PM, Dash T (2020) Multifault diagnosis in WSN using a hybrid metaheuristic trained neural network. Digit Commun Netw 6(1):86–100. https://doi.org/10.1016/j.dcan.2018.02.001

    Article  Google Scholar 

  20. Lun H, Fu M, Liu X, Wu Y, Yi L, Hu W et al (2020) Soft failure identification for long-haul optical communication systems based on one-dimensional convolutional neural network. J Lightw Technol 38(11):2992–2999. https://doi.org/10.1109/JLT.2020.2989153

    Article  Google Scholar 

  21. Cheng D, Yang F, Xiang S, Liu J (2022) Financial time series forecasting with multi-modality graph neural network. Pattern Recognit 121:108218. https://doi.org/10.1016/j.patcog.2021.108218

    Article  Google Scholar 

  22. Abbasimehr H, Paki R, Bahrini A (2022) A novel approach based on combining deep learning models with statistical methods for COVID-19 time series forecasting. Neural Comput Appl 34:3135–3149. https://doi.org/10.1007/s00521-021-06548-9

    Article  Google Scholar 

  23. De Sousa TFB, Fernandes MAC (2018) Butterfly neural equalizer applied to optical communication systems with two-dimensional digital modulation. Opt Express 26(23):30837–30850. https://doi.org/10.1364/OE.26.030837

    Article  Google Scholar 

  24. Enriconi MP, De Castro FCC, Müller C, De Castro MCF (2020) Phase transmittance RBF neural network beamforming for static and dynamic channels. IEEE Antennas Wirel Propag Lett 19(2):243–247. https://doi.org/10.1109/LAWP.2019.2958682

    Article  Google Scholar 

  25. Mayer KS, De Oliveira MS, Müller C, De Castro FCC, De Castro MCF (2019) Blind fuzzy adaptation step control for a concurrent neural network equalizer. Wirel Commun Mob Comput 2019:1–11. https://doi.org/10.1155/2019/9082362

    Article  Google Scholar 

  26. De Sousa TFB, Fernandes MAC (2019) Butterfly neural filter applied to beamforming. IEEE Access 7:96455–96469. https://doi.org/10.1109/ACCESS.2019.2929590

    Article  Google Scholar 

  27. Mayer KS, Soares JA, Arantes DS (2020) Complex MIMO RBF neural networks for transmitter beamforming over nonlinear channels. Sensors 20(2):1–15. https://doi.org/10.3390/s20020378

    Article  Google Scholar 

  28. Mayer KS, Müller C, Soares JA, De Castro FCC, Arantes DS (2022) Deep phase-transmittance RBF neural network for beamforming with multiple users. IEEE Wirel Commun Lett. 11(7):1498–1502. https://doi.org/10.1109/LWC.2022.3177162

    Article  Google Scholar 

  29. Soares JA, Mayer KS, de Castro FCC, Arantes DS (2021) Complex-valued phase transmittance RBF neural networks for massive MIMO-OFDM receivers. Sensors 21(24):1–31. https://doi.org/10.3390/s21248200

    Article  Google Scholar 

  30. Zhang H, Gu M, Jiang XD, Thompson J, Cai H, Paesani S et al (2021) An optical neural chip for implementing complex-valued neural network. Nat Commun 12(457):1–11. https://doi.org/10.1038/s41467-020-20719-7

    Article  Google Scholar 

  31. Herrera LJ, Pomares H, Rojas I, Guillén A, Rubio G, Urquiza J (2011) Global and local modelling in RBF networks. Neurocomputing 74(16):2594–2602. https://doi.org/10.1016/j.neucom.2011.03.027

    Article  Google Scholar 

  32. Park J, Sandberg IW (1991) Universal approximation using radial-basis-function networks. Neural Comput 3(2):246–257. https://doi.org/10.1162/neco.1991.3.2.246

    Article  Google Scholar 

  33. Zamanlooy B, Mirhassani M (2014) Efficient VLSI implementation of neural networks with hyperbolic tangent activation function. IEEE Trans Very Large Scale Integr VLSI Syst 22(1):39–48. https://doi.org/10.1109/TVLSI.2012.2232321

    Article  Google Scholar 

Download references

Funding

Kayol S. Mayer is supported in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brasil (CAPES)—Finance Code 001.

Author information

Authors and Affiliations

  1. Department of Electronics and Computing, Federal University of Santa Maria, 1000, Roraima Avenue, Santa Maria, RS, 97105-900, Brazil

    Candice Müller, Fernando Cesar Comparsi de Castro, Samuel Tumelero Valduga & Natanael Rodrigues Gomes

  2. Department of Communications, University of Campinas, 400, Albert Einstein Avenue, Campinas, SP, 13083-852, Brazil

    Kayol Soares Mayer

  3. School of Technology, Pontifical Catholic University of Rio Grande do Sul, 6681, Ipiranga Avenue, Porto Alegre, RS, 90619-900, Brazil

    Maria Cristina Felippetto de Castro

Authors
  1. Candice Müller
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kayol Soares Mayer
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fernando Cesar Comparsi de Castro
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Maria Cristina Felippetto de Castro
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Samuel Tumelero Valduga
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Natanael Rodrigues Gomes
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kayol Soares Mayer.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Müller, C., Mayer, K.S., de Castro, F.C.C. et al. Multilayer Radial Basis Function Neural Network for Symbol Timing Recovery. Neural Process Lett 55, 3135–3148 (2023). https://doi.org/10.1007/s11063-022-11001-6

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-022-11001-6

Keywords

Search

Navigation