In a cognitive radio network (CRN), spectrum sensing is an important prerequisite for improving the utilization of spectrum resources. In this paper, we propose a novel spectrum sensing method based on deep learning and cycle spectrum, which applies the advantage of the convolutional neural network (CNN) in an image to the spectrum sensing of an orthogonal frequency division multiplex (OFDM) signal. Firstly, we analyze the cyclic autocorrelation of an OFDM signal and the cyclic spectrum obtained by the time domain smoothing fast Fourier transformation (FFT) accumulation algorithm (FAM), and the cyclic spectrum is normalized to gray scale processing to form a cyclic autocorrelation gray scale image. Then, we learn the deep features of layer-by-layer extraction by the improved CNN classic LeNet-5 model. Finally, we input the test set to verify the trained CNN model. Simulation experiments show that this method can complete the spectrum sensing task by taking advantage of the cycle spectrum, which has better spectrum sensing performance for OFDM signals under a low signal-noise ratio (SNR) than traditional methods.

Deep learning (DL) shows great vitality in all areas, but it rarely involves wireless communication. This paper proposes an automatic signal modulation recognition method based on deep convolutional neural network to solve common problems in wireless communication. The algorithm automatically extracts various feature details of the image through the deep convolutional neural network of deep learning, instead of the huge engineering of manual design features to achieve accurate recognition of signal and noise under various signal-to-noise ratio conditions. The method uses the image processing GPU to build VGGNet to automatically recognize 10 kinds of modulated signals in MPSK and MQAM under the deep learning architecture TensorFlow. The simulation results show that the minimum recognition accuracy of various signals is 96.7% when the signal-to-noise ratio is 5dB. Compared with other methods, the proposed method is better.

No abstract

No abstract