Threat Evaluation of Radiation Resource with RBF Neural Networks
Huang Wen · Modern Radar · 2003
A new method for evaluation radiation resource with a robust radial basis function(RBF) is presented. The proposed RBF uses Log Sigmoid function as a basis function to eliminate any risk of instabilities, and it has much better learning properties and function approximation capabilities. A new normalization function is also presented to convert various data with different scales into the interval of 〔 1,1〕 .The function embodies the principle for reward the better and punish the worse, also benefits the training of neural networks. Simulation results demonstrate the superiority of this approach.