Communication Modulation Signal Recognition Algorithm Based on Entropy Cloud Characteristics

Abstract

Communication modulation signal recognition, as an emerging technology, has been widely used in the field of communication reconnaissance. It is generally known that the characteristics of communication modulation signals under low SNR environment is difficult to extract. To solve this problem, a novel modulation signal feature extraction algorithm based on entropy cloud characteristics is put forward in three steps by this paper. Firstly, it extracts entropy characteristics of the modification signal, which introduce the exponential entropy to construct two-dimensional feature entropy with shannon and exponential entropy for a better signal recognition performance. Then, it extracts cloud digital characteristics of information entropy to build three-dimensional feature, which can depict the modulation type characteristics of the signal. Finally, it uses grey correlation classifier for signal identification. By means of simulation, it can be seen that the new algorithm has overcome the defection that signal characteristics are unstable and difficult to extract under low SNR environment in the traditional method. So the new algorithm is available and effective for the signal identification under low SNR environment, thus achieves the goal of the signal classification.