access icon free NN-based IDF demodulator in band-limited communication system

To meet the spectrum requirement in the future wireless communication system, the m-ary phase position shift keying as a type of the spectrally efficient modulation has been considered in this study. However, the inter-symbol interference (ISI), the waveform distortion and the non-white noise are introduced by the band-pass infinite impulse response filters, which is adopted to limit the signal bandwidth and eliminate the out-band interference. The traditional demodulation methods based on impacting filter or matched filter cannot work well in these scenarios. Therefore, a neural network (NN)-based demodulator is proposed to solve the problem of waveform distortion. Additionally, a novel NN-based iterative decision feedback (IDF) demodulator is also proposed to further reduce the ISI iteratively by using the previous estimated symbol information. Simulation results show that both the NN-based demodulator and the NN-based IDF demodulator can greatly outperform the traditional demodulation methods in the band-limited communication system, and the NN-based IDF demodulator achieves better performance than the normal NN-based demodulator.

Inspec keywords: signal denoising; band-pass filters; interference suppression; telecommunication computing; intersymbol interference; iterative methods; IIR filters; radio networks; matched filters; neural nets; phase shift keying; demodulators

Other keywords: neural network-based demodulator; demodulation methods; wireless communication system; NN-based IDF demodulator; spectrally efficient modulation; intersymbol interference; waveform distortion; bandlimited communication system; M-ary phase position shift keying; symbol information estimation; ISI; impacting filter; out-band interference elimination; spectrum requirement; nonwhite noise; iterative decision feedback demodulator; matched filter; signal bandwidth; band-pass infinite impulse response filters

Subjects: Radio links and equipment; Neural computing techniques; Communications computing; Interpolation and function approximation (numerical analysis); Modulators, demodulators, discriminators and mixers; Filtering methods in signal processing; Signal processing theory; Modulation and coding methods; Interpolation and function approximation (numerical analysis)

References

    1. 1)
      • 16. Lerkvaranyu, S., Dejhan, K., Miyanaga, Y.: ‘M-QAM demodulation in an OFDM system with RBF neural network’, Circuits Syst., 2004, 2, (2), pp. 581584.
    2. 2)
      • 1. Wu, L.: ‘UNB modulation in high speed space communications’, Proc. SPIE, 2007, 6795, (679510), pp. 16.
    3. 3)
      • 14. Zhang, H., Luo, Y., Liu, D.: ‘Neural-network-based near-optimal control for a class of discrete-time affine nonlinear systems with control constraints’, IEEE Trans. Neural Netw., 2009, 20, (9), pp. 14901503.
    4. 4)
      • 9. Chen, Z., Wu, L., Chen, P.: ‘Efficient modulation and demodulation methods for multi-carrier communication’, IET Commun., 2016, 10, (5), pp. 567576.
    5. 5)
      • 18. Hong, X., Chen, S., Harris, C.J., et al: ‘Single-carrier frequency domain equalization for hammerstein communication systems using complex-valued neural networks’, IEEE Trans. Signal Process., 2014, 62, (17), pp. 44674478.
    6. 6)
      • 10. Proakism, J., Salehi, M.: ‘Digital communications’ (McGraw-Hill, New York, 1995).
    7. 7)
      • 3. Feng, M., Wu, L., Gao, P.: ‘From special analogous crystal filters to digital impacting filters’, Academic Press Inc., 2012, 22, (4), pp. 690696.
    8. 8)
      • 24. Yin, P., Zhang, S., Qi, Y., et alQuantization and training of low bit-width convolutional neural networks for object detection’, arXiv preprint arXiv:1612.06052, 2016.
    9. 9)
      • 21. Ying, P., Wu, L.: ‘New scheme of MPPSK modem’, J. Southeast Univ., 2012, 42, (2), pp. 564568.
    10. 10)
      • 12. Keller, P.: ‘Artificial neural networks: an introduction’, vol. TT68 (SPIE Publications, 2005).
    11. 11)
      • 4. Lu, C., Wu, L., Chen, P., et al: ‘M-ary phase position shift keying with orthogonal signalling’, IET Commun., 2015, 9, (13), pp. 16271634.
    12. 12)
      • 2. Feng, M., Wu, L.: ‘Special non-linear filter and extension to Shannon's channel capacity’, Digit. Signal. Process., 2009, 19, (5), pp. 861873.
    13. 13)
      • 25. Zhou, A., Yao, A., Guo, Y., et alIncremental network quantization: towards lossless CNNs with low-precision weights’, arXiv preprint arXiv:1702.03044, 2017.
    14. 14)
      • 19. Zhao, H.Q., Zeng, X.P., He, Z.Y., et al: ‘Complex-valued pipelined decision feedback recurrent neural network for non-linear channel equalisation’, IEt Commun., 2012, 6, (9), pp. 10821096.
    15. 15)
      • 8. Wu, L., Feng, H.: ‘Extended binary phase shift keying modulation and demodulation method for frequency spectrum compression’. Chinese Patent CN101582868B, October 2009.
    16. 16)
      • 20. Oppenheim, A., Schafer, R.: ‘Discrete-time signal processing’ (Prentice-Hall Inc., Upper Saddle River, NJ, USA, 1989).
    17. 17)
      • 5. Wu, L., Feng, M.: ‘On BER performance of EBPSK-MODEM in AWGN channel’, Adam Hilger Ser. Sens., 2010, 10, (4), pp. 38243834.
    18. 18)
      • 11. Salz, J.: ‘Optimum mean-square decision feedback equalization’, Bell Syst. Tech. J., 1973, 52, (8), pp. 13411373.
    19. 19)
      • 15. LeCun, Y., Bengio, Y., Hinton, G.: ‘Deep learning’, Nature, 2015, 521, (7553), pp. 436444.
    20. 20)
      • 6. Vaidyanathan, P., Regalia, P., Mitra, S.: ‘Design of doubly-complementary IIR digital filters, using a single complex allpass filter’. IEEE Int. Conf. ICASSP, 1986, pp. 25472550.
    21. 21)
      • 13. Qiu, J., Gao, H., Ding, S.X.: ‘Recent advances on fuzzy-model-based nonlinear networked control systems: a survey’, IEEE Trans. Ind. Electron., 2016, 63, (2), pp. 12071217.
    22. 22)
      • 17. Onder, M., Akan, A.: ‘Pilot tone investigation for joint channel estimation, equalization, and demodulation based on neural networks’. Int. Conf. Electrical and Electronics Engineering, 2015, pp. 749752.
    23. 23)
      • 22. Glorot, X., Bordes, A., Bengio, Y.: ‘Deep sparse rectifier neural networks’. Proc. Fourteenth Int. Conf. Artificial Intelligence and Statistics, PMLR 15, 2011, pp. 315323.
    24. 24)
      • 23. Abramson, N., Braverman, D., Sebestyen, G.: ‘Pattern recognition and machine learning’, IEEE Trans. Inf. Theory, 2003, 9, (4), pp. 257261.
    25. 25)
      • 7. Qi, C., Wu, L.: ‘Pll demodulation technique for m-ray position phase shift keying’, J. Electron. (China), 2009, 26, (3), pp. 289295.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-com.2017.0643
Loading

Related content

content/journals/10.1049/iet-com.2017.0643
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading