ADAPTIVE PACKET EQUALIZATION FOR INDOOR RADIO CHANNEL USING MULTILAYER NEURAL NETWORKS

This paper investigates the application of the multilayer perceptron s tructure to the packet-wise adaptive decision feedback equalization of a M-ary QAM signal through a TDMA indoor radio channel in the presenc e of intersymbol interference (ISI) and additive Gaussian noise. Since the multilayer neural networks are capable of producing complex decis ion regions with arbitrarily nonlinear boundaries, this would greatly improve the performance of conventional decision feedback equalizer (D FE) where the decision boundaries of conventional DFE are linear. Howe ver, the applications of the traditional multilayer neural networks ha ve been limited to real-valued signals. To tackle this difficulty, a n eural-based DFE is proposed to deal with the complex QAM signal over t he complex-valued fading multipath radio channel without performing ti me-consuming complex-valued back-propagation training algorithms, whil e maintaining almost the same computational complexity as the original real-valued training algorithm. Moreover, this neural-based DFE train ed by packet-wise backpropagation algorithm would approach an ideal eq ualizer after receiving a sufficient number of packets. In this paper, another fast packet-wise training algorithm with better convergence p roperties is derived on the basis of a recursive least-squares (RLS) r outine. Results show that the neural-based DFE trained by both algorit hms provides a superior bit-error-rate performance relative to the con ventional least mean square (LMS) DFE, especially in poor signal to no ise ratio conditions.