Artificial Neural Network Based Spectrum Sensing Method for Cognitive Radio

Abstract

Spectrum sensing is a key technology of cognitive radio (CR). In CR systems, the main requirement of spectrum sensing is the ability of rapid and accurate detection of the presence of the primary user. In this paper, we propose a spectrum sensing method using artificial neural network (ANN). Detailed analysis shows that the proposed scheme is appropriate to detect the signals under considerably low signal-to-noise ratio (SNR) environment and has reliable performance. Simulations also illustrate that the discussed method outperforms over previous approaches in noisy environment when sensing the spectrum for CR systems.