MOBILE RADIO PROPAGATION PREDICTION FOR A URBAN MICROCELLULAR ENVIRONMENT USING FACTORIZABLE GAUSSIAN NEURAL NETWORKS

In this paper, we present the application of a factorizable Gaussian n eural network to the prediction of field strength in an urban microcel lular environment. The Gaussian neural network is a two-layer localize d receptive field network whose output nodes form a combination of Gau ssian radial activation functions computed by the hidden layer nodes. Appropriate centres, spreads and connection weights in the Gaussian ne twork lead to a network that is capable of forming the best approximat ion to any continuous nonlinear mapping up to an arbitrary resolution. Such an approximation introduces the best nonlinear approximation cap ability into the prediction model in order to predict propagation loss accurately over an arbitrary environment based on adaptive learning f rom measurement data. The adaptive learning employs a gradient-descent algorithm with a combination of both the delta-bar-delta rule and mom entum heuristics to enhance its convergence performance. The applicati ons to Lee's field measurements taken in Irvine, CA, USA, are conducte d to demonstrate the effectiveness of the Gaussian neural network appr oach.