Communication jamming signal recognition method based on fractal dimension and information entropy
Guan Wang, Yong Kang, Hui Wang, Jing Sun, Jinyu Wang, Zhiwei Zhang · 2022
Aiming at the problem of low recognition accuracy of traditional communication jamming signals, a communication jamming signal recognition method combining fractal dimension and information entropy is proposed. Firstly, Fourier transform, singular value decomposition and wavelet packet decomposition are performed on the jamming signal in turn; Then, the fractal dimension and information entropy are used to extract the spectrum box dimension, time-frequency image singular value entropy and wavelet packet energy entropy of the jamming signal respectively, and the three-dimensional feature vector is constructed; Finally, the feature vector is input into multi classification support vector machine for classification and recognition. The simulation results show that the proposed method can accurately identify five types of typical communication jamming signals under the condition of low jamming noise ratio, and the recognition rate can reach more than 90% when the jamming noise ratio is -10dB. It is a strong anti noise communication jamming recognition method with practical application value.