Ensemble Classification-Based Spectrum Sensing Using Support Vector Machine for Cognitive Radio Networks

Abstract

As next-generation communication systems require more spectrum-intensive applications, the challenge of spectrum scarcity becomes increasingly significant. A promising solution is cognitive radio networks (CRNs), which optimize the use of spectrum, a valuable and sharable natural resource that should not be wasted. To design efficient and sustainable networks for the future, it is crucial to ensure that spectrum sensing is not only accurate and rapid, but also energy-efficient. Spectrum sensing is a critical aspect of CRNs, and this study is mainly focused on it. This research employs a supervised Support Vector Machines (SVM) algorithm to detect primary users (PU). We analyze linear, polynomial, and Gaussian RBF SVM variants and enhance performance using an ensemble classification approach. Simulations show the ensemble classifier achieves the best results.