Ensemble Classification-Based Spectrum Sensing Using Support Vector Machine for CRN

TL;DR

This paper proposes an ensemble classification approach using various SVM variants to improve spectrum sensing accuracy and efficiency in cognitive radio networks, addressing spectrum scarcity for IoT and D2D applications.

Contribution

It introduces an ensemble SVM-based method for spectrum sensing, enhancing detection performance over individual classifiers in CRNs.

Findings

Ensemble classifier outperforms individual SVM variants.

Gaussian RBF SVM achieves the best detection accuracy.

Method improves spectrum sensing speed and energy efficiency.

Abstract

As the demand for internet of things (IoT) and device-to-device (D2D) applications in next generation communication systems increases, we are confronted with a challenge of spectrum scarcity. One promising solution to this problem is cognitive radio network (CRN), where the key element is the 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. In this research, we employ the supervised machine learning algorithm, support vector machine (SVM), to detect primary users (PU). We investigate different variants of SVM, including linear, polynomial, and Gaussian radial basic function (RBF), and employ an ensemble classification-based approach to improve the classifier's performance and productivity. The simulation results demonstrate that the ensemble classifier achieves the highest performance.