Skip to main content
Log in

Performance of fuzzy logic-based slope tuning of neural equaliser for digital communication channel

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Adaptive equalisation in digital communication systems is a process of compensating the disruptive effects caused mainly by intersymbol interference in a band-limited channel and plays a vital role for enabling higher data rate in modern digital communication system. Designing efficient equalisers having low structural complexity and faster learning algorithms is also an area of much research interest in the present scenario. This paper presents a novel technique of improving the performance of conventional multilayer perceptron (MLP)-based decision feedback equaliser (DFE) of reduced structural complexity by adapting the slope of the sigmoidal activation function using fuzzy logic control technique. The adaptation of the slope parameter increases the degrees of freedom in the weight space of the conventional feedforward neural network (CFNN) configuration. Application of this technique provides faster learning with less training samples and significant performance gain. This research work also proposes adaptive channel equalisation techniques on recurrent neural network framework. Exhaustive simulation studies carried out prove that by replacing the conventional sigmoid activation functions in each of the processing nodes of recurrent neural network with multilevel sigmoid activation functions, the bit error rate performance has significantly improved. Further slopes of different levels of the multilevel sigmoid have been adapted using fuzzy logic control concept. Simulation results considering standard channel models show faster learning with less number of training samples and performance level comparable to the their conventional counterparts. Also, there is scope for parallel implementation of slope adaptation technique in real-time implementation, which saves the computational time.

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

Access this article

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
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Gibson GJ, Siu S, Cowan CFN (1989) Multilayer perceptron structures applied to adaptive equalisers for data communications. In: International Conference on ASSP, ICASSP 89, vol 2, pp 1183–1186

  2. Power P, Sweeney F, Cowan CFN (1999) Non-linear MLP channel equalisation. In: IEE Colloquium on Statistical Signal Processing, pp 3/1–3/6

  3. Kirkland WR, Taylor DP (1992) On the application of feedforward neural networks to channel equalisation. In: Proceedings of international joint conference on neural networks, New York

  4. Peng M, Nikias CL, Proakis JG (1992) Adaptive equalisation with neural networks: new multilayer perceptron structures and their evaluation. In: Proceedings of the ICASSP’92 IEEE international conference acoustics, speech, signal processing, New York

  5. Kechriotis G, Zervas E, Manolakos ES (1994) Using recurrent neural networks for adaptive communication channel equalisation. IEEE Trans Neural Netw 5(2):267–278

    Article  Google Scholar 

  6. Williums RJ, Zipser RA (1989) A learning algorithm for continually training neural networks. Neural Comput 1:270–280

    Article  Google Scholar 

  7. Chang PR, Yeh BF, Chang CC (1994) Adaptive packet equalisation for indoor radio channel using multilayer neural networks. In: IEEE Transactions on Vehicular Technology, vol 43, no 3

  8. Al-Mashouq KA, Reed IS (1994) The use of neural nets to combine equalisation with decoding for severe inter symbol interference channels. IEEE Trans Neural Netw 5(6):982–988

    Article  Google Scholar 

  9. Chen S, Mulgrew B, Hanzo L (2003) Least bit error rate adaptive nonlinear equalisers for binary signalling. In: IEE Proceeding Communication, vol 150, no 1, pp 29–36

  10. Haykin S (1994) Neural networks–a comprehensive foundation. Macmillan, New York

    MATH  Google Scholar 

  11. Bradley MJ, Mars P (1995) Application of recurrent neural networks to communication channel equalisation. In: International Conference on Acoustics, Speech and Signal Processing, ICASSP-95, vol 5, pp 3399–3402

  12. Ortiz-Fuentes JD, Forcada ML (1997) A comparison between recurrent neural network architectures for digital equalisation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP-97, vol 4, pp 3281–3284

  13. Parishi R, Claudio EDD, Orlandi G, Rao BD (1997) Fast adaptive digital equalisation by recurrent neural networks. IEEE Trans Neural Netw 45(1):2731–2739

    Google Scholar 

  14. Stronach AF, Vas P, Neuroth M (1997) Implementation of intelligent self-organising controllers in DSP controlled electromechanical drives. In: IEE proceedings, control theory application, vol 144, No 4, pp 324–330

  15. Miao Z, Xu H, Wang X (2007) The modified self-organizing fuzzy neural network model for adaptability evaluation. Lecture Notes in Computer Science, ISBN: 978-3-540-74770-3, pp 344–353

  16. Driankov D, Hellendoorn H, Reinfrank M (1993) An introduction to fuzzy control. Springer, Berlin

    MATH  Google Scholar 

  17. Brown M, Harris CJ (1994) Neurofuzzy adaptive modelling and control. Prentice Hall, Englewood Cliffs

    Google Scholar 

  18. Kientitz KL (1993) Controller design using fuzzy logic-a case study. Automatica 29:549–554

    Article  Google Scholar 

  19. Satapathy JK, Harris CJ (1999) Application of fuzzy-tuned adaptive feedforward neural networks for accelerating convergence in identification. In: 3rd international conference on industrial automation, p 6.1

  20. Satapathy JK, Das S (2004) BER performance improvement of an FNN based equaliser using fuzzy tuned sigmoidal activation function. In: Proceedings of IEEE international conference on signal processing and communications (SPCOM 2004), Indian Institute of Science, Bangalore. pp 472–475

  21. Das S (2008) Design of adaptive channel equaliser on neural framework using fuzzy logic based multilevel sigmoid slope adaptation. In: Proceedings of IEEE international conference on signal processing, communications and networking (ICSCN 2008), Madras Institute of Technology Chennai, India, ISBN: 978-1-4244-1924-1, pp 274–278

  22. Jang JSR (2001) Neuro-fuzzy and soft computing. Prentice-Hall

  23. Wang L, Mendel JM (1992) Generating fuzzy rules by learning from examples. IEEE Trans Syst Man Cybern 22:1414–1427

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Susmita Das.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Das, S. Performance of fuzzy logic-based slope tuning of neural equaliser for digital communication channel. Neural Comput & Applic 21, 423–432 (2012). https://doi.org/10.1007/s00521-010-0462-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-010-0462-9

Keywords

Navigation