Adaptive direct receiving signal cancelling using neural networks

Summary form only given. A layered neural network model trained according to the backpropagation learning algorithm to perform a specific form of adaptive filtering, which will play a role in the DRS (direct receiving signal) cancelling, was used. The first option is in choosing the problem defined specifically so that a selection of inputs and outputs to the artificial neural network (ANN) may be made. Next, the internal design choice must be made, including the topology and size of the network. Finally, the selection of training data presented from the TDSMS (time-domain scattering measurement system) to the ANN influences whether or not the network learns a particular task. The adaptation model architecture and application performance in the DRS cancelling field were described.<>