Estimation of Propagation Graph Model Based on BP Neural Network

This paper introduces a novel approach to estimate parameters in the propagation graph model using machine learning. The estimation process is framed as a regression problem, which involves mapping from the channel transfer function or channel impulse response to the model parameters. In this method, data obtained from processing the channel impulse responses generated by the propagation graph are used to train the neural network, which outputs the parameters of the propagation graph model. Finally, measured data are applied to the trained neural network to estimate corresponding model parameters. The results indicate that this method provides relatively accurate estimation of the model parameters.