Optimum Multiuser Detection for CDMA Systems Using the Mean Field Annealing Neural Network

  • Po-Rong Chang
  • Bor-Chin Wang
  • Tan-Hsu Tan
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 74)


In this chapter, we investigate the application of Mean Field Annealing (MFA) neural networks to the optimum multiuser detection in a direct-sequence code-division multiple-access (DS/CDMA) system over the additive white Gaussian noise (AWGN) channel. Although the optimum receiver for multi-user detection is superior to the conventional matched filter receiver when the relative powers of the interfering signals are large, the optimum receiver obtained by the maximization of a log-likelihood function has a complexity that is exponential in the number of users. This prohibitive complexity has spawned the area of research on employing neural network techniques to develop an optimum detector with moderate complexity. In this chapter, it is shown that the energy function of the neural network can be derived from and is then expressed in terms of the likelihood function of the optimum multi-user detection for both the synchronous and asynchronous CDMA systems. An MFA network, which combines characteristics of the simulated annealing algorithm and the Hopfield neural network is proposed to seek out the global optimum solution of this energy function. Additionally, MFA exhibits the rapid convergence of the neural network while preserving the solution quality afforded by the stochastic simulated annealing algorithm. This would lead to a cost-effective and efficient minimization mechanism for CDMA multiuser detection. Computer simulation carry out performance comparisons among optimum detection, matched filter detection and MFA detection.


Code Division Multiple Access Matched Filter Multiuser Detection Hopfield Neural Network VLSI Implementation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    A. J. Viterbi: “CDMA, Principle of Spread Spectrum Communication”, Addison-Wesley Company, NY, 1995.Google Scholar
  2. [2]
    A. Duel-Hallen, J. Holtzman, Z. Zvonar: “Multiuser detection CDMA systems”, IEEE Personal Communication, vol. 2, no. 2, pp. 46–58, April 1995.CrossRefGoogle Scholar
  3. [3]
    R. Lupas, S. Verdu: “Linear multiuser detectors for synchronous code-division multiple access channels”, IEEE Trans. Inform. Theory, vol. 35, no. 1, pp. 123–136, Jan. 1989.MathSciNetMATHCrossRefGoogle Scholar
  4. [4]
    R. Lupas, S. Verdu: “Near-far resistance of multiuser detectors in asynchronous channels”, IEEE Trans. Commun., vol. 38, no. 4, pp. 496508, April 1990.Google Scholar
  5. [5]
    M. K. Varanasi, B. Aazhang: “Near-optimum detection in synchronous code-division multiple-access systems”, IEEE Trans. Commun., vol. 39, no. 5, pp. 725–736, May 1991.CrossRefGoogle Scholar
  6. [6]
    S. Verdu: “Computational complexity of optimum multiuser detection”, Algorithmica, vol. 4, no. 3, pp. 303–312, 1989.MathSciNetMATHCrossRefGoogle Scholar
  7. [7]
    B. Aazhang et al.: “Neural networks for multiuser detection in code-division multiple-access communications”, IEEE Trans. Commun., vol. 40, no. 7, pp. 1211–1222, July 1992.CrossRefGoogle Scholar
  8. [8]
    U. Mitra, H. V. Poor: “Neural network techniques for adaptive multiuser demodulation”, IEEE J. Select. Areas on Commun., vol. 12, no. 9, pp. 1460–1470, Dec. 1994.CrossRefGoogle Scholar
  9. [9]
    T. Miyajima et al.: “On the multiuser detection using a neural network in code-division multiple-access communications”, IEICE Trans. Commun., vol. E76-B, no. 8, August 1993.Google Scholar
  10. [10]
    G. Kechriotis, E. S. Manolakos: “Implementing the optimum CDMA multiuser detector with Hopfield neural networks”, Proc. of the Intl Workshop on Applications of Neural Networks to Telecommunications, pp. 60–67, Princeton, NJ, Oct. 1993.Google Scholar
  11. [11]
    J. J. Hopfield, D. W. Tank: “Neural computation of decisions in optimization problems”, Biol. Cybernetics, vol. 52, pp. 141–152, 1985.MathSciNetMATHGoogle Scholar
  12. [12]
    P. J. M. Van Laarhoven, E. H. L. Arts: “Simulated Annealing: Theory and Application”, Dordrecht, Holland: Reidel, 1987.Google Scholar
  13. [13]
    D. E. Goldberg: “Genetic Algorithms in Search, Optimization, and Machine Learning”, Reading, MA: Addison-Wesley, 1989.MATHGoogle Scholar
  14. [14]
    D. E. Van den Bout, T. K. Miller III: “Graph partition using annealing networks”, Complex System, vol. 1, no. 2, pp. 192–203, June, 1990.Google Scholar
  15. [15]
    C. Peterson: “A mean field theory learning algorithm for neural networks”, Complex System, vol. 1, pp. 995–1019, 1987.MATHGoogle Scholar
  16. [16]
    C. Peterson: “Neural networks and NP-complete optimization problem: a performance study on the graph bisection problem”, Complex System, vol. 2, pp. 59–89, 1988.MATHGoogle Scholar
  17. [17]
    C. Peterson: “A new method for mapping optimization problem onto neural networks”, Int’l J. Neural System, vol. 1, no. 1, pp. 3–22, 1989.CrossRefGoogle Scholar
  18. [18]
    C. Peterson, E. Hartman: “Explorations of the mean field theory learning algorithm”, Neural Networks, vol. 2, pp. 475–494, 1989.CrossRefGoogle Scholar
  19. [19]
    G. Bilbro, R. Mann et al.: “Optimization by mean field annealing”, Advances in Neural Information Processing System 1.Google Scholar
  20. [20]
    G. H. Golub, C. F. V. Load: “Matrix Computation”, 2nd edition, The Johns Hopkins University Press, Baltimore, 1989.Google Scholar
  21. [21]
    A. Cichocki, R. Unbenauen: “Neural Networks for Optimization and Signal Processing”, John Wiley and Son, NY, 1993.Google Scholar
  22. [22]
    W. C. Y. Lee: “Power control in CDMA”, Proc. Veh. Technol. Conference, 1991, pp. 77–80.Google Scholar
  23. [23]
    M. B. Pursley, H. F. Roefs: “Numerical evaluation of correlation parameters for optimum phases of binary register sequences”, IEEE Trans. Commun., vol. COM-27, pp. 1593–1604, Oct. 1979.Google Scholar
  24. [24]
    J. A. Alspector et al.: “Experimental evaluation of learning in a neural microsystem”, in Advances in Neural Information Processing System 1. (J. E. Moody et al. ed.), pp. 871–878, San Mateo CA, Morgan Kaufmanns, 1992.Google Scholar
  25. [25]
    T. Miyajima, T. Hasegawa: “Multiuser detection using a Hopfield network for asynchronous code-division multiple-access systems”, IEICE Trans. on Fundamentals, vol. E-79 A, no. 12, Dec. 1996.Google Scholar
  26. [26]
    R. J. Glauber: “Time-dependent statistics of the Ising model”, Journal of Mathematical Physics, vol. 4, pp. 481–485, 1963.MathSciNetCrossRefGoogle Scholar
  27. [27]
    M. Mezard, G. Parisi, M. Virasoro: “Spin glass theory and beyond”, Singapore: World Scientific, 1987.MATHGoogle Scholar
  28. [28]
    C. Mead: “Analog VLSI and VLSI system”, New York: Addison-Wesly, 1989.CrossRefGoogle Scholar
  29. [29]
    B. W. Lee, B. J. Sheu: “General-purpose neural chips with electrically programmable synapses and gain-adjust neurons”, IEEE Journal of Solid-State Circuits, vol. 27, no. 9, pp. 1299–1302, Sept. 1992.Google Scholar
  30. [30]
    A. D. Culhane, M. C. Peckerar, C. R. K. Marrian: “A neural net approach to discrete Hartley and Fourier transform”, IEEE Trans. on Circuits and Systems, vol. 36, pp. 695–702, May 1989.MathSciNetCrossRefGoogle Scholar
  31. [31]
    J. F. Wakerly: “Digital Design, Principles and Practices”, 2nd edition, New Jersey: Prentice-Hall Inc., 1994.MATHGoogle Scholar
  32. [32]
    N. H. E. Weste, K. Eshraghian: “Principles of CMOS VLSI Design”, 2nd edition, MA: Addison-Wesley, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Po-Rong Chang
    • 1
  • Bor-Chin Wang
    • 1
  • Tan-Hsu Tan
    • 1
  1. 1.Department of Communication EngineeringNational Chiao-Tung UniversityHsin-ChuTaiwan

Personalised recommendations