Channel Estimation for UAV Communication Systems Using Deep Neural Networks

Channel modeling of unmanned aerial vehicles (UAVs) from wireless communications has gained great interest for rapid deployment in communication. The UAV channel its own distinctive characteristics compared to satellite and cellular networks. Many proposed techniques consider formulate the UAVs as a classification problem, where key is extract discriminative features signal. For this issue, we propose framework multiple Gaussian–Bernoulli restricted Boltzmann machines (GBRBM) dimension reduction pre-training utilization incorporated with an autoencoder-based deep neural network. developed system used measurements town’s already existing commercial network training validation. To evaluate approach, run ray-tracing simulations program Remcom Wireless InSite at distinct frequency 28 GHz them results demonstrate that method accurate acquisition various flying scenarios outperforms conventional DNNs.