Application of Neural Network Techniques on Nonlinear Channel Equalization for 16-QAM Modulation Systems

The design of a Chebyshev functional link artificial neural networks (CFLANN) based channel equalizer in digital communication systems is discussed in this paper. The design has been successfully applied to digital communication systems in which 16-QAM modulated signals are transmitted. To improve equalizer performance, a decision feedback mechanism is used in the networks (DF-CFLANN). But the computational complexity of DF-CFLANN is about 60% higher than CFLANN. In this paper, we propose a reduced decision feedback Chebyshev functional link artificial neural network (RDF-CFLANN) which not only has simple structure, but also exhibits better performance to DF-CFLANN.