In order to improve the accuracy of channel estimation in communication systems and adapt to larger data for more complex data calculation,a neural network method was introduced for channel estimation.Experiment comparsion is conducted be-tween the radial basis function(RBF)neural network and back propagation(BP)neural network,compared with traditional channel estimation methods,the experimental results show significant improvement.On this basis,an RBF neural channel estimation method based on improved genetic algorithm was also proposed.The purpose is to determine the hidden layer parameters of RBF network,making the network parameters to the universally optimal solution,and then improving the efficacy of the channel estimator.The en-hanced RBF neural network effectively resolve the channel estimation by MATLAB simulation,thereby verifying the feasibility of this approach.
关键词
OFDM系统/遗传算法/RBF神经网络/信道估计器/Matlab
Key words
orthogonal frequency division multiplexing(OFDM)system/genetic algorithm/RBF neural network/channel esti-mator/Matlab
维普
万方数据