Multi-scale feature extraction and feature selection network for radiation source identification

被引：0

作者：

Zhang, Shunsheng ^{[1
]}

Ding, Huancheng ^{[1
]}

Wang, Wenqin ^{[2
]}

机构：

[1] Research Institute of Electronic Science and Technology, University of Electronic Science and Technology of China, Chengdu

[2] School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu

来源：

Guofang Keji Daxue Xuebao/Journal of National University of Defense Technology | 2024年 / 46卷 / 06期

关键词：

feature selection; IQ signal; multi-scale feature extraction; radiation source identification;

D O I：

10.11887/j.cn.202406015

中图分类号：

学科分类号：

摘要：

Convolutional neural nelworks currently applied to radiation source identification process the time-series IQ(in-phase and quadralure-phase) signals in two ways; one way transforms them inlo images, and the other way extracts shallow features of the IQ time-series data. The former way leads to a large computalional efforl of the algorithm, while the latter way leads to a low accuracy of the recognition rate. To address the above problems, a multi-scale feature extraction and feature selection network was proposed. After inputling the IQ signal, the shallow and multi-scale features of the IQ signal were extracted by the multi-scale feature extraction network. Then the data dimension of multi-scale features was reduced by the feature selection network. Feature enhancement was achieved by the adaptive linear rectilicalion unit, and a single fully connected layer was used to classify the radiation source. Comparison experimenls with ORACLE, CNN-DLRF and IQCNet on the FIT/CorleXlab radio frequency fingerprint recognition datasel show lhat the proposed network improves the recognition accuracy and reduces the computational effort to some extent. © 2024 National University of Defense Technology. All rights reserved.

引用

页码：141 / 148

页数：7

共 22 条

[1]

XU T, LIU Z M, GUO F C., A radar radiation source identification method based on high-dimensional re-frequency features[J], Modern Radar, 46, 4, pp. 1-7, (2022)

[2]

LECUN Y, BENGIO Y, HINTON G., Deep learning [J], Nature, 521, pp. 436-444, (2015)

[3]

HUANG J S., Research on image retrieval algorithm in Computer vision based on deep learning [J], Information Technology and Informatization, 2022, 9, pp. 181-184

[4]

DU Y N, LIU Q W., Application of deep learning framework in Computer vision, China Security & Protection, 5, pp. 34-40, (2022)

[5]

LU H T, LUO M K., Survey on new progresses of deep learning based Computer vision [J], Journal of Data Acquisilion and Processing, 37, 2, pp. 247-278, (2022)

[6]

KONG M X, ZHANG J, LIU W F, Radar emitter identification based on deep convolulional neural network [C], Proceedings of ihe 2018 International Conference on Conlrol, Automation and Information Sciences (ICCAIS), pp. 309-314, (2018)

[7]

YIN X F, WU B., Radar emitter identification algorithm based on deep learning, Aerospace Electronic Warfare, 37, 1, pp. 7-11, (2021)

[8]

ZHAO N., Intelligent recognition of radar emitter based on deep learning [D], (2022)

[9]

XIAO Z L, YAN Z Y., Radar emitter identification based on ieedforward neural networks [C], Proceedings of the 2020 IEEE 4tli Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), pp. 555-558, (2020)

[10]

WANG X B, HUANC CM, MA C S, Et al., Convolulional neural network applied to specific emitter identification based on pulse wavefomi images [J], IET Radar, Sonar & Navigation, 14, 5, pp. 728-735, (2020)

← 1 2 3 →