Cognitive Radio (CR) networks have attracted more and more attention in recent years for the ability of dynamic spectrum management and intellectual learning. To meet the challenge of big data and ultra wide band signal processing, Compressed Sensing (CS) theory is introduced to break the bound of Nyquist-Sampling rate. In this paper, we proposed an algorithm of indirect feature reconstruction with good performance and low complexity of both time and space. Considering that most communication signals own cyclostationar-ity, single recognition and detection can be achieved by the use of the Cyclic Autocorrelation Function (CAF). In our study, we evaluated the algorithm in comparison of methods which directly recover CAF. By theoretical analyses and simulations, we demonstrated that the method proposed in the paper performed well and attracted future usage.
展开▼
