Specific Radar Emitter Identification Using 1D-CBAM-ResNet
Jifei Pan, Linqing Guo, Qiuju Chen, Shengli Zhang, Jingwei Xiong
Abstract
With the development of the multifunction radar, the traditional specific emitter identification (SEI) can no longer meet the needs of the observe-orient-decide-act (OODA) closed loop, and most identification networks are in the process of converting one-dimensional (1D) radar emitter signals into two-dimensional (2D) signals to adapt the network input, which easily misses information. To address the above problems, this paper adopts a 1D convolutional residual neural network with the convolutional block attention module (1D-CBAM-ResNet) for automatic learning and single-step identification of 1D inter-mediate frequency (IF) signals to improve SEI accuracy. The model combines the 1D residual building unit (1D-RBV) with the 1D convolutional block attention module (1D-CBAM) to effectively aggregate channel and spatial information to accurately capture fingerprint features within the pulse. The simulation results demonstrate that the overall identification accuracy of the algorithm for 10 emitters of the same type reaches 93.03%, which proves the effectiveness and feasibility of the module.