Unsupervised specific emitter identification of bispectrum features based on contrastive learning

Abstract

Aiming at the problem that features of communication emitter data without label information are different to extract and the classification acquisition is not high, this paper cites the contrastive learning theory, constructs a residual network with two parameters sharing as the backbone network, conducts contrastive learning on the rectangular integral bispectral features of signal augmented samples, and further extracts the feature presentation with more differentiation. To this end, the feature separability between samples from different emitters is enhanced. Then, the new features extracted are used for contrastive learning at the cluster level to complete the tasks of classification and identification. Compared with other unsupervised learning algorithms, the proposed method achieves a better identification accuracy of about 78% through experiences on the data set of measured ultra-short wave communication stations.