Xiaoqiu Wang

Combining RNN equalizer with SOM detector

In this paper, we propose a novel receiver structure by combining adaptive RNN (recurrent neural network) equalizer with a SOM (self-organizing map) detector under serious ISI and nonlinear distortion in QAM system. The performance of the proposed scheme is shown to be quite effective in channel equalization under nonlinear distortion.

A compensating method based on SOM for nonlinear distortion in 16 QAM-OFDM system

This work presents a compensating method based on a self-organizing map (SOM) of nonlinear distortion, which is caused by the high-power amplifier (HPA) in 16 QAM-OFDM systems. OFDM signals are sensitive to nonlinear distortions and different methods are studied to limit them. In the proposed scheme, the correction is done at the receiver by a SOM algorithm. Simulations are carried out considering an additive white Gaussian noise (AWGN) transmission channel. Simulation results show that the SOM algorithm brings perceptible gains in a complete 16 QAM-OFDM system.

Channel equalization using complex-valued recurrent neural network

Recurrent neural network (RNN) is a kind of neural network with one or more feedback loops. In this paper, a complex-valued fully connected RNN with real-time recurrent learning is presented for the equalization of complex-valued systems, such as quadrature amplitude modulation (QAM), in the presence of intersymbol interference and nonlinear distortions. Simulation results show that the proposed scheme is quite effective in channel equalization when facing the nonlinear distortions.

Adaptive detection using self-organizing map in 16 QAM system

A signal suffers from nonlinear, linear, and additive distortion when transmitted through a channel. Linear equalizers are commonly used in receivers to compensate for linear channel distortion. As an alternative, novel equalizer structures utilizing neural computation have been developed for compensating for nonlinear channel distortion. We propose a neural detector based on self-organizing map (SOM) in a 16 QAM system. The proposed scheme uses the SOM algorithm and symbol-by-symbol detector to form a neural detector, and it adapts well to the changing channel conditions because of the topology-preserving property of the SOM algorithm. According to the theoretical analysis and computer simulation results, the proposed scheme is shown to have a better performance than the traditional linear equalizer when faced with nonlinear distortion.

Application of decision feedback recurrent neural network with real-time recurrent algorithm

The recurrent neural network is a kind of neural network with one or more feedback loops. We may have feedback from the output neurons of the multilayer to the input layer. Yet another possible form of feedback is from the hidden neurons of the network to the input layer. In this paper, we propose a channel equalization scheme using a decision feedback recurrent neural network, which has feedback loops from both the hidden layer and the decision part, with real-time recurrent network. Simulation results show that the proposed scheme outperforms the recurrent neural network that only has feedbacks loops from the hidden layer.