Sensoriamento espectral utilizando redes neurais artificiais em redes de rádio cognitivo

Abstract

Nowadays wireless communication networks have a distribution policy of fixed radio chan- nels, in which most of the frequency spectrum is rarely used and can vary geographically. Cognitive radio is a new technology that aims to improve the use of the frequency spec- trum, being an intelligent wireless communication system that uses techniques to evaluate the environment and adapt in an opportunistic way for communication. Spectrum sen- sing is one of the main steps used by cognitive radio in transmission, and this step is responsible for the detection of transmitted signals that occupy different frequencies in the area of cognitive radio performance. In order to improve performance when compared to traditional spectrum sensing techniques, this study proposes to use an artificial neural network for the detection of transmissions in the frequency spectrum.