Title :
Neural Conjuncted Polynomial´s Structure Adaptive Equalizer
Author :
Haiquan Zhao ; Zhang, Jiashu
Author_Institution :
Southwest Jiaotong Univ., Chengdu
Abstract :
Based on the analysis of linear conjuncted polynomial filter and the characteristic of single layer neural network with mild nonlinear and severe nonlinear distortions, novel conjunction´s structure equalizer is proposed in this paper, and adaptive algorithm is deduced by the normalized least mean squares (NLMS). Computer simulations show that not only the novel type structure equalizer is simpler in structure and but also can availably remove nonlinear distortions and intersymbol interference (ISI), improve performance of bit error rates (BER) no matter what linear channel or nonlinear channel in digital communication systems.
Keywords :
adaptive equalisers; error statistics; intersymbol interference; least mean squares methods; neural nets; nonlinear distortion; polynomials; BER; ISI; adaptive algorithm; adaptive equalizer; bit error rates; digital communication systems; intersymbol interference; linear conjuncted polynomial filter; mild nonlinear distortions; neural conjuncted polynomial structure; nonlinear channel; normalized least mean squares; severe nonlinear distortions; single layer neural network; Adaptive algorithm; Adaptive equalizers; Adaptive filters; Algorithm design and analysis; Bit error rate; Intersymbol interference; Neural networks; Nonlinear distortion; Nonlinear filters; Polynomials;
Conference_Titel :
Communications, Circuits and Systems, 2007. ICCCAS 2007. International Conference on
Conference_Location :
Kokura
Print_ISBN :
978-1-4244-1473-4
DOI :
10.1109/ICCCAS.2007.4348182
