An Approach to Propagation Modeling for Indoor WLAN Applications Using Neural Networks

This paper reports results obtained by propagation modeling for WLAN applications. A multi-ray model is proposed and tested through analytical calculations, neural network simulation, and measurements. As the case used a corridor of university building in Dubrovnik, for which calculation, simulation and measurement of signal strength were obtained. Calculation is based on ray-tracing method with neglecting diffraction and scattering. The results of calculation are compared with measurement. Neural network architecture is proposed with back-propagation training algorithm. The simulation data matches with measurement data rather good.