Correlation based detectors are very popular for spectrum sensing. In these detectors, temporal correlation is often employed to discriminate the signals of primary users from noises. However, large channel delay spread can significantly decrease the correlation of neighbouring samples of received signals, inducing severe performance degradation of temporal correlation based detectors. In this work, we show that the power spectral densities of different delayed versions of a primary signal have high correlation, despite unknown delays. Then, by exploiting the correlation of power spectral densities of received signals, we propose a spectral-correlation detector. To facilitate the practical application of the proposed detector, we also derive a theoretical expression for its decision threshold to achieve a given false alarm probability. Furthermore, in order to handle the case of channels with unknown delay profile, we employ the OR rule to combine the temporal- and spectral-correlation
This work addresses the issue of spectrum sensing with random arrival and departure of primary signals. We first design a convolutional neural network (CNN) with outputs as the posterior probabilities of the arrival and departure of primary signals, leading to a CNN-based detector with the ratio of the posterior probabilities (i.e., the outputs of the CNN) as a test statistic. To further enhance the attention of the network on the switch feature of channel states, we design a switch attention module (SAM) that adaptively weights the received signals. Replacing the convolution plus maximum pooling block in the CNN detector with the SAM block leads to an SAM-CNN detector. Simulations show that the proposed CNN detector significantly outperforms existing detectors, and further improvement of detection probability by 19% is achieved by the SAM-CNN detector.