Deep Multimodal Subspace Interactive Mutual Network for Specific Emitter Identification

Zhigang Zhu, Hongbing Ji, Lin Li

Abstract: This article investigates the problem of specific emitter identification (SEI), i.e., radar emitter fingerprint or individual emitter identification, which first measures the emitter-specific differences caused by radar's nonlinearities, e.g., mixer, power amplifiers, transmitter, and then makes a decision. In this article, the SEI problem is considered in the single-modal, dual-modal, and multimodal scenarios, respectively. First, a multimodal subspace interactive mutual unit is proposed to perform information interaction between radar signal and its multiple transformations. Based on this, a data-driven multimodal subspace interactive mutual network is then built to solve the SEI problem. Extensive experiment results demonstrate that the proposed algorithm achieves superior identification performance on the airplane measured data.