Deep Transfer Cooperative Sensing in Cognitive Radio
Lusi Li, He Jiang, Haibo He
Abstract
In this letter, we propose a deep transfer cooperative sensing (DTCS) approach in cognitive radio networks, where multiple secondary users (SUs) cooperate to detect the presence of signals from a primary user (PU) in a shared frequency band. DTCS is a cooperative spectrum sensing (CSS) framework based on unsupervised deep transfer learning. It operates on energy vectors, whose each element is a sensing result by an energy detector from individual SU. It learns the knowledge by combining the sensing results from all SUs in one radio frequency environment and transfers it to another one. This approach is applicable for detecting the presence of arbitrary unknown signals, which enhances the generalization ability and robustness of the framework. Simulation results demonstrate the effectiveness of DTCS.