Neural networks applications for the prediction of propagation path loss in urban environments

This paper presents neural network based models for the prediction of propagation path loss in urban environment. The neural networks are designed separately for line-of-sight (LOS) and non-line-of-sight (NLOS) cases. The performance of the neural models is compared to that of the COST231-Walfisch-Ikegami model, the Walfisch-Bertoni model and the single regression model, based on the absolute mean error, standard deviation and the root mean squared error between predicted and measured values.