Deep-learning path loss prediction model using side-view images

This paper proposes a path loss prediction model based on convolutional neural network utilizing side-view images to consider over-rooftop propagation, in addition the top-view around receiving station of conventional urban macrocell environment. The building profile between transmitting and stations was used for images. In addition, scalar parameter frequency added fully connected part as proposed method characteristics. learned validated using measured data, estimation error compared with evaluate its validity. Our findings showed that RMS 12.1 dB improved 4.4 by model.