Research on Spectrum Sensing Method by Robust Multiscale Neural Network
In Cognitive Radio(CR),Spectrum Sensing(SS)is a key technology that supports dynamic spectrum allocation and enhances spectrum utilization.However,traditional SS methods are susceptible to the impact of noise uncertainty,resulting in lower detection accuracy and a higher computational parameter load in low Signal to Noise Ratio(SNR)environments.To solve these problems,an SS method by Robust-Multiscale Neural Network(R-MsNN)based on Signal Processing(SP)features is proposed.This method combines the advantages of multiscale neural network and Gated Recurrent Unit(GRU)to effectively address the challenges faced in SS.The multiscale neural network gradually extracts abstract features from the bottom layer to the top layer to enhance the robustness of signal recognition.GRU selectively retains and forgets past temporal information,thereby better capturing long-term dependencies and temporal relationships.To validate the generalization capability of R-MsNN,the SS performance of R-MsNN is compared with that of different Deep Neural Network(DNN)architectures in two different noise models:one generated from a Generalized Gaussian Distribution(GGD)as noise model 1,and experimental data collected from unoccupied frequency modulation broadcasting channels as noise model 2.The experimental results demonstrate that,compared to the optimal model,R-MsNN trained with a combination of SP features achieved an average detection probability increase of 1.74％,2.55％,2.08％,and 1.59％for four different noise models 1,and a 1.72％increase for noise model 2.Additionally,compared to GRU,R-MsNN has half the number of parameters.This indicates that R-MsNN trained with a combination of SP features,exhibits robustness in a variety of complex noise en-vironments and can meet the dual requirements of high detection probability and low parameter number in SS tasks.
国家科技期刊平台
NSTL
万方数据
