Resource-Constrained Specific Emitter Identification Using End-to-End Sparse Feature Selection

被引:2
作者
Tao, Mengyuan [1 ,2 ]
Fu, Xue [2 ]
Lin, Yun [1 ,2 ]
Wang, Yu [2 ]
Yao, Zhisheng [2 ]
Shi, Shengnan [2 ]
Gui, Guan [1 ,2 ]
机构
[1] NJUPT, Coll Telecommun & Informat Engn, Nanjing, Peoples R China
[2] Harbin Engn Univ, Coll Informat & Commun Engn, Harbin, Peoples R China
来源
IEEE CONFERENCE ON GLOBAL COMMUNICATIONS, GLOBECOM | 2023年
关键词
Specific emitter identification (SEI); deep learning (DL); sparse feature selection (SFS); sparse regularization; FREQUENCY FINGERPRINT IDENTIFICATION; NEURAL-NETWORKS;
D O I
10.1109/GLOBECOM54140.2023.10436740
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Specific emitter identification (SEI) refers to a process to determine the category of emitters by extracting, analyzing and matching the characteristics of received emitter signals. With the increasingly complex environment, traditional SEI methods, such as parameter matching, become difficult to meet the needs of robust and effective signal identification. Deep learning (DL) possesses powerful feature extraction ability and has been widely used in SEI. The superior performance of DL-based SEI methods also brings problems of redundant model parameters and high feature dimensionality, which further causes slow convergence rate, high storage requirements, and ever-increasing computational complexity. In this paper, we propose an SEI method based on end-to-end sparse feature selection (SFS) to make model pay more attention to features with good identification performance. Specifically, we add sparse parameters to features and design loss function composed of cross-entropy loss and sparse regularization. Several experiments are conducted on ADS-B, WiFi and LoRa datasets. From the simulation results, our proposed SFS-SEI method improves feature sparsity, speeds up loss convergence, reduces model parameters on the premise of ensuring accuracy. Code is available at: https://github.com/sleepeach/SFS-SEI.
引用
收藏
页码:6067 / 6072
页数:6
相关论文
共 27 条
  • [1] Semi-Supervised Specific Emitter Identification Method Using Metric-Adversarial Training
    Fu, Xue
    Peng, Yang
    Liu, Yuchao
    Lin, Yun
    Gui, Guan
    Gacanin, Haris
    Adachi, Fumiyuki
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2023, 10 (12) : 10778 - 10789
  • [2] A New Method for Specific Emitter Identification With Results on Real Radar Measurements
    Gok, Gokhan
    Alp, Yasar Kemal
    Arikan, Orhan
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2020, 15 : 3335 - 3346
  • [3] 6G: Opening New Horizons for Integration of Comfort, Security, and Intelligence
    Gui, Guan
    Liu, Miao
    Tang, Fengxiao
    Kato, Nei
    Adachi, Fumiyuki
    [J]. IEEE WIRELESS COMMUNICATIONS, 2020, 27 (05) : 126 - 132
  • [4] COMPRESSION AND ACCELERATION OF NEURAL NETWORKS FOR COMMUNICATIONS
    Guo, Jiajia
    Wang, Jinghe
    Wen, Chao-Kai
    Jin, Shi
    Li, Geoffrey Ye
    [J]. IEEE WIRELESS COMMUNICATIONS, 2020, 27 (04) : 110 - 117
  • [5] GUO Y, 2016, P 30 INT C NEURAL IN, P1387, DOI DOI 10.48550/ARXIV.1608.04493
  • [6] Han Song., 2015, NEURIPS, DOI DOI 10.5555/2969239.2969366
  • [7] Radar Emitter Signal Identification Based on Multi-scale Information Entropy
    Huang Yingkun
    Jin Weidong
    Ge Peng
    Li Bing
    [J]. JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2019, 41 (05) : 1084 - 1091
  • [8] HUANG Z, 2018, 15 EUR C COMP VIS EC, P318, DOI DOI 10.1109/NANA2018.2018.00064
  • [9] Jianzhao Zhang, 2019, 2019 IEEE 5th International Conference on Computer and Communications (ICCC), P1177, DOI 10.1109/ICCC47050.2019.9064314
  • [10] Toward Location-Enabled IoT (LE-IoT): IoT Positioning Techniques, Error Sources, and Error Mitigation
    Li, You
    Zhuang, Yuan
    Hu, Xin
    Gao, Zhouzheng
    Hu, Jia
    Chen, Long
    He, Zhe
    Pei, Ling
    Chen, Kejie
    Wang, Maosong
    Niu, Xiaoji
    Chen, Ruizhi
    Thompson, John
    Ghannouchi, Fadhel M.
    El-Sheimy, Naser
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (06) : 4035 - 4062