Automatic Spectrum Sensing Techniques Using Support Vector Machine In Cognitive Radio Network

Abstract

Cognitive Radio (CR) network is established for spectrum utilization. This technology allows unlicensed users to share the spectrum with licensed users. In order to perform such a process, the spectrum needs to be periodically scanned in order to find the voids in the white (licensed) spectrum. Automatic spectrum sensing approaches are proposed in this paper. Deep learning classifier namely Neural Network a Multilayer Perceptron (MLP) and machine learning approaches such as Gradient Boosting (GB), Support Vector Machine (SVM), Logistic Regression (L_R), K-nearest Neighbor (KNN) and Bagging algorithm. SVM-based spectrum sensing is outperformed with 94.01 % spectrum sensing accuracy was achieved using this technique.