Using ANNs to Predict Frequency Spectrum Occupancy in Cognitive-Radio Receivers
Promise I. Okorie, Luis A. Camuñas-Mesa, José M. de la Rosa · 2022
This paper analyzes the use of Artificial Neural Networks (ANNs) to identify vacant portions of the radioelectric spectrum in Cognitive Radio (CR) systems. Several ANN topologies are considered, including Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks or hybrid combinations of them. These ANNs are modeled and compared in terms of their complexity, speed and accuracy of the prediction. As an application, a CR-based receiver is simulated, where Radio-Frequency (RF) signals are digitized by a Band-Pass Sigma-Delta Modulator (BP-ΣΔM) with a tunable notch frequency, which is modified according to the less occupied band predicted by the ANNs.1This work was supported in part by Grant PID2019-103876RB-I00, funded by MCIN/AEI/10.13039/501100011033, by the European Union “ESF Investing in your future”, and by “Junta de Andalucía” under Grant P20-00599.