Spectrum sensing by higher-order SVM-based detection
Angelo Coluccia, Alessio Fascista, Giuseppe Ricci · 2019
A novel spectrum sensing algorithm based on support vector machine is proposed. The idea is to map the received signals into a multi-dimensional feature space obtained from well-known spectrum sensing statistics and their higher-order combinations. The approach has been implemented and validated on a software-defined radio testbed. Experimental results have shown the receiver operating characteristic (ROC) curve of the proposed detector can outperform classical spectrum sensing approaches without requiring knowledge of the noise variance.