Spectrum sensing based on adaptive sampling of received signal

Abstract Spectrum sensing (SS) has been heatedly discussed due to its capacity discover the idle registered spectrum bands, which effectively alleviates shortage of by reuse. Energy detector (ED) is widely accepted for SS as complexity very low. In this paper, an adaptive sampling scheme proposed improve performance ED, where point received signal adaptively adjusted with environment signal-to-noise ratio (SNR). When SNR decreases, can be maintained and even improved rise point. increases, ED considered detection. The evaluated based on joint convolutional neural network (CNN) long short-term memory (LSTM) network. Both theoretical derivations simulation experiments validate effectiveness scheme.