Specific Emitter Identification Based on Ensemble Neural Network and Signal Graph

Specific emitter identification (SEI) is a technology for extracting fingerprint features from signal and identifying the emitter. In this paper, author proposes an SEI method based on ensemble neural networks (ENN) graphs, with following innovations: First, graph used to show data in non-Euclidean space. Namely, sequence constructed into transform Euclidian space Hence, feature (the of space) can be extracted graph. Second, network integrated extractor extractor, making it available extract both simultaneously. This also fuses features, obtaining that has Euclidean Therefore, contains more effective information The study results demonstrate higher accuracy robustness than traditional machine learning methods common deep methods.