Joint source/channel coding modulation based on BP neural networks
暂无分享,去创建一个
A new JSCCM scheme based on multi-layer feed-forward network is proposed. The coding and modulation of traditional system is replaced by a neural network. At the receive end, a network maps the deteriorated modulation signals to reconstructed signals, the demodulation and decoding of the traditional system is replaced. Simulation results show that the performance of the neural networks is superior to the traditional system. The result is a useful basis for applying neural networks to transmitter and receiver of communication system.
[1] Kurt Hornik,et al. Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.
[2] Johan A. K. Suykens,et al. Robust local stability of multilayer recurrent neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..
[3] Héctor J. Sussmann,et al. Uniqueness of the weights for minimal feedforward nets with a given input-output map , 1992, Neural Networks.