The performance of existing signal detection methods depends heavily on the amount of prior information acquired by the sensor of interest. Therefore, to improve cognitive radio-based detection in lowsignal-to-noise (SNR) environments, we propose a deep learning method-based passive signal detection. A convolution neural network (CNN) and the long short-term memory (LSTM) approach are used to extract the frequency and time domain features of the signal. Our method can detect signal when little

more »

... o none prior information exists. The simulation experiments verify the probability of detection for our method. The results show that our method is about 4.5-5.5 dB better than a traditional blind detection algorithm under different SNR environments. INDEX TERMS Cognitive radio, deep learning, signal detection.