Novel method for SEI based on 3D-Hilbert energy spectrum and multi-scale segmentation features
Jie Han, Tao Zhang · 2017
This paper proposes a novel specific emitter identification (SEI) method for communication emitter individual identification based on the 3D-Hilbert energy spectrum and multi-scales segmentation (3D-HESMS). First, the time-frequency energy spectrum is derived via Hilbert-Huang Transform (HHT), which can be defined as a complicated curved surface in the three dimension space, namely the 3D-HUbert energy spectrum. Then, via the fractal theory, four features are extracted to compose the feature vector under multi-scale segmentation. Finally, the communication emitter individual identification is achieved utilizing the Support Vector Machine (S VM). Moreover, the identification performance of the 3D-HESMS method is compared with two existing methods. The experiment results show that the identification rate of the 3D-HESMS method is higher than that of the other two methods. The features extracted by the 3D-HESMS method have a high stability, sufficiency, and identifiability.