Individual radiation source identification based on fractal box dimension

Nowadays, it is difficult to identify the individual radiation source under low SNR environment. To this problem, the paper proposed a new fractal box dimension based algorithm, to calculate the fractal box dimension of different communication individual radio signals as the subtle characteristics. Basing on the traditional fractal box dimension, the proposed algorithm calculated the derivations of different reconstructing phase space points, and getting the fractal box dimension of the communications signals under different reconstructing conditions, which constitute a feature vector, to realize the purpose of extracting the subtle characteristics of individual radiation source more exactly. Finally, neural network was used to process and classify the fractal box dimension vector features, in order to achieve the purpose of classifying and recognizing different communication radiation source under complex environment.