Individual Identification of Communication Radiation Sources Based on Hilbert-Huang and EfficientNet
NIU Yameng
CUI Liangzhong
SUN Jiajie
Abstract：In view of the problems of low recognition rate,large number of network model parameters and poor model general-ization performance of existing communication radiation source individual recognition methods,this paper proposes a communica-tion radiation source individual recognition method based on Hilbert-Huang and EfficientNet.Firstly,Hilbert-Huang is used to per-form time-frequency transformation on individual signal of communication radiation source,and the collected individual signal of ra-diation source is decomposed empirically.Hilbert transformation is performed on the decomposed signal to convert one-dimensional signal into two-dimensional time-frequency spectrum,and the features of the original signal are enriched through time-frequency analysis.The converted time spectrum is learned using EfficientNet,and the individual identification of communication radiation source is finally completed.The short-wave communication signals of 4 communication radiation sources are collected for experi-ments,and the results show that the proposed method effectively solves the problem of individual identification of communication ra-diation sources.Compared with other time-frequency analysis deep learning communication radiation source individual identifica-tion methods,the proposed method has a higher recognition rate and faster recognition speed,which proves the effectiveness of the proposed method.
Keywords：individual identification of communication radiation sourcesHilbert-Huangtime-frequency analysisEffi-cientNet
Publication Date：2025-04-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 72-76,119 )