Received Path Power Prediction for Millimeter-wave Using Machine Learning

This paper discusses the received power prediction of millimeter-wave by machine learning when a user moves simply like walking straight. In general, a large amount of data is required for the neural network to predict the received power. In this paper, the transfer function of the channel is divided into narrower bandwidths, and the received power obtained from the narrower channel is used for the learning data. The RMSE is evaluated to show the effectiveness of the proposed prediction scheme.