Specific Emitter Identification Based on Square Integral Bispectrum Features

Specific Emitter Identification is an important technology employed to identify the unique radio transmitter at the physical level regardless of specific information carried. RF fingerprint contains rich nonlinear characteristics and reflects the differences of internal components in radio transmitters. Radio frequency fingerprint extraction and identification has been extensively adopted to enhance the security of radio frequency communication in both military and civilian use. On the basis of time-frequency analysis of emitter signals, this paper proposes an individual emitter recognition algorithm based on square integral bispectrum features, and uses softmax classifier to classify and recognize five types of emitter individuals, and studies the influence of square integral bispectrum features dimensions and Gaussian noise on recognition results. The algorithm can effectively reduce the feature dimensions and greatly improve the correct recognition rate of emitter. The experiment results demonstrate the practicality of our proposal.