Radiation source individual identification method and device based on deep residual shrinkage network

• Main Authors: ZHANG TAO, FANG HAO, YANG XIAOMENG, TANG ZHEN, QIAO XIAOQIANG
• Format: Patent
• Language: Chinese; English
• Published: 25.02.2022
• 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 radiation source individual identification method and device based on a deep residual shrinkage network, and belongs to the technical field of information security. The method comprises the following steps: acquiring one-dimensional point data of an ADS-B signal of a radiation source; converting the one-dimensional point data into an IQ oscillogram, and splicing the I-path image and the corresponding Q-path image together by adopting a splicing mode to form an I/Q spliced image; constructing a deep residual shrinkage network in combination with an attention mechanism and a soft threshold function on the basis of the deep residual network; performing data enhancement on the I/Q spliced graph sample data, and training a deep residual shrinkage network by using the enhanced I/Q spliced graph sample data; inputting the I/Q spliced graph of the radiation source to be identified into the trained deep residual shrinkage network, and identifying the individual radiation source. The device ca