Application of neural networks to field strength prediction for indoor environments

The following paper presents an application software for field strength prediction for mobile communication networks inside buildings. The considered technique is based on a proposal that tried to benefit from the advantages of using "dominant paths" (an alternative to ray tracing), and neural networks, trained with measurements. Some graphic and numeric results are presented, but the paper is mainly focused on studying the influences that the variation of some parameters (and consideration of new ones) have on processing time of the training phase for the neural network, and the accuracy of the results.