Specific emitter identification using fractal features based on box-counting dimension and variance dimension

• Published in: 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) pp. 226 - 231
• Main Authors: Wu, Longwen, Zhao, Yaqin, Wang, Zhao, Abdalla, Fakheraldin Y. O., Ren, Guanghui
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2017
• Subjects: box-counting dimension; Feature extraction; Fingerprint recognition; fractal features; Fractals; Frequency modulation; Phase noise; Signal processing algorithms; specific emitter identification; support vector machine; variance dimension
• DOI: 10.1109/ISSPIT.2017.8388646

Specific emitter identification (SEI) is a technique for distinguishing different emitters of a same type with other weak individual characteristics. Only using some traditional modulation parameters for recognition cannot distinguish different emitters with close modulation parameters. To solve the problem, new complex and high-dimensional features, which can characterize the emitters with more details, urgently need to be developed for recognition. An SEI method using fractal features based on box-counting dimension and variance dimension is presented. This paper mainly focuses on the weak individual characteristics caused by phase noise, applies fractal theory to the feature extraction, and finally establishes the recognition process using support vector machine. Numerical results show that the identification rate is generally more than 95% above 15dB of signal to noise ratio (SNR), and the real data experiment proves the practical performance of the proposed algorithm.