Radar Emitter Identification Based on Weighted Local and Global Consistency

摘要

In order to realize radar emitter identification with only a small number of training samples, this paper introduces the Local and Global Consistency (LGC) algorithm into the field of radar emitter identification. Aiming at the problem that the method is greatly affected by the signal measurement error, a radar emitter identification method based on weighted local and global consistency is proposed. The improved method adds the importance weight of the sample in the regularization framework of the original algorithm and reduces the influence of the samples located in the overlapping region, thereby improving the recognition accuracy of the algorithm when the measurement error is large. The simulation results show that the proposed algorithm can effectively identify the operating modes of the radar under the condition of less training samples and reduce the influence of measurement error on the recognition effect.