NSS-ML: a Novel spectrum sensing framework using machine learning for cognitive radio IoT networks

Abstract

A key component of cognitive radio systems is spectrum sensing, which reduces coexistence problems and maximises spectrum efficiency. However, the introduction of multiple situations with distinct characteristics brought about by 5G communication presents problems for spectrum sensing to support a wide range of applications with high performance and flexible implementation. Inspired by these difficulties, a new method with a multi-layer extreme learning machine optimised for bats is presented in this study. This technique makes use of a variety of input vectors, such as channel ID, energy, distance, and received signal intensity, to enhance user categorization and sensing capabilities. Moreover, we compare the proposed method with the state-of-the-art spectrum sensing approaches in order to evaluate its effectiveness in 5G situations, especially in healthcare applications. Evaluation metrics including channel detection probability, sensitivity, and selectivity are carefully examined. The findings unequivocally prove the suggested spectrum sensing approach’s superiority over current methods and highlight its potential for smooth incorporation into a variety of 5G applications.