Total views : 108

Experiments with LMS Algorithm

Affiliations

  • Department of Applied Science and Humanities, G H Patel College of Engineering and Technology, Vallabh Vidyanagar – 388120, Gujarat, India
  • Department of Electronics and Communication, G H Patel College of Engineering and Technology, Vallabh Vidyanagar – 388120, Gujarat, India

Abstract


Objectives: This article focuses on improving the convergence rate and reducing the number of operations used to train the Least Mean Square (LMS) algorithm. Methods/Statistical Analysis: In this paper, two modifications are suggested to train an adaptive filter using the LMS algorithm; one is based on initialization of weights and another on early termination of the training of a sequence. Findings: The optimum weights of an adaptive filter are found by initializing the weights by zeros, providing several random sequences as input and updating the weights according to the error. Moreover, the weights are continuously updated for the entire sequence even if the weights have been converged. In the proposed algorithm, the weights are initialized with zeros only once for the first sequence. The optimum weights obtained for a sequence are used as initial weights for the subsequent sequence to improve the convergence rate. Further, to reduce the number of operations, the weight update process for a sequence is terminated when the error is below some prescribed threshold. Applications/Improvements: Results shows that by making these modifications, the rate of convergence increases and number of multiplications decrease.

Keywords

Convergence Rate, Initialization of Weights, LMS Algorithm, Multiplications, Mean Square Error, Threshold.

Full Text:

 |  (PDF views: 135)

References


  • Haykin S. Adaptive filter theory. Fourth Edition, Pearson; 2016.
  • Nagumo J, Noda A. A learning method for system identification.Institute of Electrical and Electronics Engineers (IEEE) Transactions on Automatic Control. 1967 Jun; 12(3):282–7.
  • Albert A, Gardner L. Stochastic approximation and nonlinear regression. MIT Press, Cambridge, MA; 1967.
  • Chang R. A new equalizer structure for fast start-up digital communications. The Bell System Technical Journal. 1971 Jul–Aug; 50(6):1969–2014.
  • Cowan C. Performance comparisons of finite linear adaptive filters. In IEE Proceedings Part F, Communications, Radar and Signal Processing, London. 1987 Jun; 134(3):211–6.
  • Clark G, Mitra S, Parker S. Block implementation of adaptive digital filters. Institute of Electrical and Electronics Engineers (IEEE) Transactions on Circuits and Systems. 1981 Jun; 28(6):584–92.
  • Shynk J. Frequency-domain and multirate adaptive filtering.Institute of Electrical and Electronics Engineers (IEEE) Signal Processing Magazine. 1992 Jan; 9(1):14–37.
  • Mahmood L, Shirazi SF, Naz S, Shirazi SH, Razzak M, Umar A, Ashraf S. Adaptive filtering algorithms for channel equalization in wireless communication. Indian Journal of Science and Technology. 2015 Aug; 8(17):1577–81.
  • Salman Md N, Rao PT, Rahman Md Z. Efficient and low complexity noise cancellers for cardiac signal enhancement using proportionate adaptive algorithms. Indian Journal of Science and Technology. 2016 Oct; 9(37):1–11.
  • Clark G, Parker S, Mitra S. A unified approach to time and frequency-domain realization of FIR adaptive digital filters.Institute of Electrical and Electronics Engineers (IEEE) Transactions on Acoustics, Speech, and Signal Processing.1983 Oct; 31(3):1073–83.
  • Ferrara E. Fast implementation of LMS adaptive filters.Institute of Electrical and Electronics Engineers (IEEE) Transactions on Acoustics, Speech, and Signal Processing.1980 Sep; 28(4):474–5.
  • Yasukawa H, Shimada S. Acoustic echo canceler with high speed quality. In the Proceedings of Institute of Electrical and Electronics Engineers (IEEE) International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Dallas, TX; 1987. p. 2125–8.
  • Chen J, Bes H, Vandewalle J, Janssens P. A new structure for sub-band acoustic echo canceler. In the Proceedings of Institute of Electrical and Electronics Engineers (IEEE) International Conference on Acoustics, Speech, and Signal Processing, New York; 1988 Apr. p. 2574–7.
  • Gilloire A, Vetterli M. Adaptive filtering in sub-bands with critical sampling: analysis, experiments and applications to acoustic echo cancellation. Institute of Electrical and Electronics Engineers (IEEE) Transactions on Circuits and Systems.1992; 40:1862–75.
  • Petraglia M, Mitra S. Performance analysis of adaptive filter structures based on sub-band decomposition. In the Proceedings of International Symposium on Circuits and Systems.Chicago. 1993 May; 1:60–3.
  • Gu Y, Tang H, Cui H. LMS algorithm with gradient descent filter length. Institute of Electrical and Electronics Engineers (IEEE) Signal Process. Letters. 2004 Mar; 11(3):305–7.
  • Cho H, Kim S. Variable step size normalized LMS algorithm by approximating correlation matrix of estimation error. Signal Processing. 2010 Sep; 90(9):2792–9
  • Kwong R, Johnston E. A variable step size LMS algorithm.Institute of Electrical and Electronics Engineers (IEEE) Transactions on Signal Processing. 1992; 40(7):1633–42.
  • Costa M, Bermudez J. A robust variable step size algorithm for LMS adaptive filters. Institute of Electrical and Electronics Engineers (IEEE) International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2006 May; 3:93–6.
  • Sinha R, Choubey A, Mahto S. An efficient adaptive system identification technique based on wind driven optimization method. Indian Journal of Science and Technology. 2016 Oct; 9(38):1–12.
  • Sinha R, Choubey A. Design of a discrete adaptive equalizer for noisy channel using quantum behaved particle swarm optimization technique. Indian Journal of Science and Technology. 2016 Nov; 9(41):1–8.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.