Decision‐fusion‐based reliable CSS scheme in CR networks

Abstract

Cognitive radio (CR) is a rapidly growing technology that can be employed to effectively utilise the radio spectrum. The detection accuracy of the CR user is compromised when a network is under degrading conditions like fading and shadowing effects. Cooperative spectrum sensing (CSS) has been extensively employed to overcome these issues. In CSS, all secondary users communicate with the fusion centre (FC) to share the PU information. Hard fusion schemes are applied to make a correct decision about PU presence at FC; however, such approaches lack reliable decision-making. Hence, there is a need to construct more accurate and reliable fusion schemes. In this study, a neural network (NN)-based decision fusion scheme at FC is used to construct a reliable decision. In the proposed scheme, NN is used as a machine learning tool that is trained using input data and output data to generate the desired fusion model. It has been evaluated through simulation results that the proposed fusion scheme sensing accuracy is much better as compared to conventional fusion schemes and other state-of-the-art schemes proposed in the literature. Further, the proposed fusion scheme is tested using the clustering approach to make it more reliable and accurate.