Transiently Chaotic Neural Network with Variable Thresholds for the Frequency Assignment Problem in Satellite Communications
We proposed a transiently chaotic neural network with variable thresholds (TCNN-VT) by mapping the optimization problem onto the thresholds in the self-feedback terms of the neural network. This TCNN-VT model consists of N×M noisy chaotic neurons for an N-carrier-M-segment frequency assignment problem (FAP). The application of this new model on the FAP in satellite communications shows better performance compared with existing techniques, especially in large-scale problem.
Unable to display preview. Download preview PDF.