Cooperative Spectrum Sensing Based on Artificial Neural Network for Cognitive Radio Systems

To improve the performance of spectrum sensing in cognitive radio (CR) network consisting of primary user (PU), secondary user (SU) and fusion center, a cooperative spectrum sensing scheme based on artificial neural network (ANN) is designed. ANN is introduced at every SU to forecast the probability which represents the effect of local sensing. Fusion center uses weighting fusion which regards the probability forecasted as weights to make full use of information of SUs in diverse environment. Simulations prove that the proposed scheme can achieve satisfying probability of false-alarm and detection.