Design of Adaptive FLANN Based Model for Non-Linear Channel Equalization

  • Sidhartha Dash
  • Santanu Kumar Sahoo
  • Mihir Narayan Mohanty
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 150)


Wireless Communication systems require the most efficient techniques for reception of error-less data with high data rate. The channels introduce both linear and non-linear distortions. ISI plays a major role in this field. Also these channels contaminate the received sequence with random fluctuation. In this paper, an adaptive algorithm based on FLANN has been developed for channel equalization with analysis of MSE. The FLANN is developed with LMS technique as well as sign regressor based LMS technique and the results are compared. Also the result is compared with the standard adaptive LMS algorithm. The signed FLANN based model shows better performance as compared to LMS based FLANN model.


Channel equalization Sign regressor based LMS Functional link artificial neural network Signed regressor FLANN 


  1. 1.
    Proakis JG (2001) Digital communications, 4th edn. McGraw-Hill, New YorkGoogle Scholar
  2. 2.
    Qureshi SUH (1985) Adaptive equalization. Proc IEEE 73:1349–1387Google Scholar
  3. 3.
    Erdogmus1 D, Rende D, Principel JC, Wong TF (2012) Nonlinear channel equalization using multilayer perceptrons with information-theoretic criterion. In: IEEE International Conference on Neural networks for Signal Processing XI [ICNNSP], pp 443–451Google Scholar
  4. 4.
    Guha DR, Patra SR (2009) Channel equalization for lSI channels using Wilcoxon generalized RBF. In: Fourth international conference on industrial and information systems, ICIIS, Sri Lanka, 28–31 Dec 20MGoogle Scholar
  5. 5.
    Patra JC, Pal RN (1995) Functional link artificial neural network based adaptive channel equalization. EURASIP Signal Process J 43(2):181–195Google Scholar
  6. 6.
    Haykin S (2004) Neural networks. A comprehensive foundation, 2nd edn. Pearson Education, New DelhiGoogle Scholar
  7. 7.
    Dash S, Mohanty MN (2012) Analysis of outliers in system identification using WLMS algorithm. In: IEEE International conference on computing, electronics and electrical technologies [ICCEET], p 802–806Google Scholar
  8. 8.
    Haykin S (2003) Adaptive filter theory. PHI IndiaGoogle Scholar
  9. 9.
    Jatoth RK, vaddadi MSBS, Kanoop SSVK (2009) An intelligent functinal link artificial neural network for channel equalization. In: Proceedings of the 8th WSEAS international conference on signal processing, robotics and automation [ISPRA], pp 240–245Google Scholar
  10. 10.
    Mckean JW (2004) Robust analysis of linear models. Stat Sci 19(4):562–570Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Sidhartha Dash
    • 1
  • Santanu Kumar Sahoo
    • 1
  • Mihir Narayan Mohanty
    • 1
  1. 1.ITERSiksha ‘O’ Anusandhan UniversityBhubaneswarIndia

Personalised recommendations