Eigenvalue and Support Vector Machine Techniques for Spectrum Sensing in Cognitive Radio Networks

Cognitive radio has been described as the panacea to the problem of ever growing demand and scarcity of the radio spectrum. Fundamental to the successful implementation of cognitive radio is spectrum sensing. Here, we propose and investigate the performance of eigenvalue and support vector machine (SVM) based learning approach for spectrum sensing in multi-antenna cognitive radios. The simulation results show that the proposed technique is capable of yielding detection probability of ≥ 90% at the signal-to-noise ratio (SNR) of -20 dB while maintaining the false alarm probability at ≤ 0%.