Communication radiation source individual identification method based on IQ graph features

• Main Authors: PAN BISHENG, LI XING, ZHANG MENGBO, TENG FEI, CHEN XIANG, CHEN YUE, LEI YINGKE
• Format: Patent
• Language: Chinese; English
• Published: 05.01.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a communication radiation source individual identification method based on IQ graph features. The method comprises the following steps of normalizing all types of radiation source data to obtain I and Q paths of data of which the amplitude maximum values are a; for the normalized I and Q paths of data, taking each b points as a data sample, and intercepting c samples by each type of radiation source to obtain a training set; performing dimension change on all types of I-path and Q-path data, performing dimension change on one-dimensional I-path and Q-path data accordingto the sizes of taking a horizontal axis as time and taking a longitudinal axis as a sample value to obtain a two-dimensional IQ graph matrix, splicing the I-path matrix and the corresponding Q-pathmatrix to obtain a two-dimensional matrix graph, and taking the two-dimensional matrix graph as input of a neural network; and learning the neural network by using the training sample of each type ofradiation source, and stori