A modular spectrum sensing system based on RVM

In cognitive radio system, spectrum sensing to verify whether the primary users are present in a licensed spectrum a fundamental problem. Energy detection is the basic spectrum sensing method to detemine whether the primary user is present. In fact, the nature of spectrum sensing can be taken as a binary classification problem, and energy detection is a linear classifier. If the SNR of the received signal is low, and the number of received signal samples for sensing is small, this binary classification problem is linearly inseparable. In this situation the performance of Energy detection will decrease seriously. In this paper, a novel approach for obtaining a nonlinear threshold based on RVM (relevance vector machine) to take the place of the linear threshold in traditional Energy detection is proposed. Simulations demonstrate that the performance of proposed algorithm is much better than traditional Energy detection.