A Proposed Cognitive Radio to Minimize the Sensing Time for High Frequency Receivers Based on Neural Network

Abstract

Cognitive radio (CR) is the exciting emerging technology that has the ability to deal with the requirements of the frequency spectrum. This new technology illustrates new developments in communications systems, because CR allows usage of the frequency spectrum more efficiently. As an example of the challenges related to CR system is the detection of the founded authorized users (PU) over a large range of frequency band at a precise time called sensing time (Ts). To increase the detection reliability of the primary users at minimum sensing time, an adaptive CR system have been built in this work based on neural network to identify if signal or noise. The system consists of feature extraction and decision stages was designed with help of Numeral Virtual Generalizing RAM (NVG-RAM) weightless neural network (WNN). Obtained simulation results of the proposed system are tested at different noisy channels: as AWGN and fading channels (Rayleigh and Rician). The results shows that probability of detection (Pd)=100% at -38 dB. at very low sensing time equal to 0.4 msec. A novel technique is also presented to estimate SNR for CR by statistical features by calculation the moment and cumulants for different modulated noisy signals. This is an indirect method for SNR measurements based on statistical features.