Deep Sensing: Cooperative Spectrum Sensing Based on Convolutional Neural Networks

In this paper, we investigate cooperative spectrum sensing (CSS) in a cognitive radio network (CRN) where multiple secondary users (SUs) cooperate in order to detect a primary user (PU) which possibly occupies multiple bands simultaneously. Deep sensing, which constitutes the first CSS framework based on a convolutional neural network (CNN), is proposed. In deep sensing, instead of the explicit mathematical modeling of CSS, the optimal strategy for combining the individual sensing results of the SUs is obtained with a CNN based on training sensing samples. Accordingly, an environment-specific CSS is found in an adaptive manner regardless of whether the individual sensing results are quantized or not. Through simulation, we show that the performance of CSS can be significantly improved by the proposed deep sensing scheme, especially in the low signal-to-noise ratio (SNR) regime, even when the number of training samples is moderate.