An enhanced two‐phase SVM algorithm for cooperative spectrum sensing in cognitive radio networks

Abstract

SummaryCognitive radio (CR) networks have emerged recently to address the problem of spectrum scarcity. As reliable spectrum sensing (SS) is vital in low signal‐to‐noise ratio (SNR) for CR networks, we propose a novel method of enhancing support vector machines (SVM) classifier named as 2‐Phase SVM for the task of SS in a cooperative sensing structure. In this study, the vectors containing energy levels of primary users (PU) are considered as feature vectors and are fed into the classifier during training and test phase. First, the classifier is trained; afterward, the test feature vectors are labeled as channel available class or channel unavailable class in an online fashion by using 2‐Phase SVM, which is applied during two phases compared with the conventional SVM algorithm. The performance of suggested cooperative SS method is evaluated by receiver operating characteristic (ROC) curve and the functionality of our proposed algorithm is qualified in terms of misclassification error rate in addition to misclassification risk. The results reveal that 2‐Phase SVM outperforms previous methods since it not only increases the classification accuracy and reduces the misclassification risk but also enhances the detection probability.