Transfer Learning for Automatic Modulation Recognition Using a Few Modulated Signal Samples

被引：14

作者：

Lin, Wensheng ^{[1
]}

Hou, Dongbin ^{[1
]}

Huang, Junsheng ^{[1
]}

Li, Lixin ^{[1
]}

Han, Zhu ^{[2
,3
]}

机构：

[1] Northwestern Polytech Univ, Sch Elect & Informat, Xian 710129, Peoples R China

[2] Univ Houston, Dept Elect & Comp Engn, Houston, TX 77004 USA

[3] Kyung Hee Univ, Dept Comp Sci & Engn, Seoul 446701, South Korea

来源：

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY | 2023年 / 72卷 / 09期

基金：

中国国家自然科学基金;

关键词：

Transfer learning; few-shot learning; automatic modulation recognition; convolutional neural network; deep learning; CLASSIFICATION;

D O I：

10.1109/TVT.2023.3267270

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：

This letter proposes a transfer learning model for automatic modulation recognition (AMR) with only a few modulated signal samples. The transfer model is trained with the audio signal UrbanSound8K as the source domain, and then fine-tuned with a few modulated signal samples as the target domain. For improving the classification performance, the signal-to-noise ratio (SNR) is utilized as a feature to facilitate the classification of signals. Simulation results indicate that the transfer model has a significant superiority in terms of classification accuracy.

引用

页码：12391 / 12395

页数：5

共 50 条

[31] Automatic Recognition of Communication Signal Modulation based on Neural Network
Zhu, Xiaolei
Lin, Yun
Dou, Zheng
2016 IEEE INTERNATIONAL CONFERENCE ON ELECTRONIC INFORMATION AND COMMUNICATION TECHNOLOGY ICEICT 2016 PROCEEDINGS, 2016, : 223 - 226
[32] Transfer Learning for Automatic Speech Recognition Systems
Asefisaray, Behnam
Haznedaroglu, Ali
Erden, Mustafa
Arslan, Levent M.
2018 26TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2018,
[33] Deep Learning based Automatic Signal Modulation Classification
Lu, Jingyang
Li, Yi
Chen, Genshe
Shen, Dan
Tian, Xin
Khanh Pham
SENSORS AND SYSTEMS FOR SPACE APPLICATIONS XII, 2019, 11017
[34] Transfer Learning in Automatic Speech Recognition for Serbian
Popovic, Branislav
Pakoci, Edvin
Pekar, Darko
2019 27TH TELECOMMUNICATIONS FORUM (TELFOR 2019), 2019, : 309 - 312
[35] MODULATION SIGNAL RECOGNITION BASED ON SELECTIVE KNOWLEDGE TRANSFER
Zhou, Huaji
Wang, Xu
Bai, Jing
Xiao, Zhu
2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 1875 - 1880
[36] Automatic Modulation Recognition Models Based on Transfer Learning and Simulated Radio Signals in AWGN Channels
Olasina, Jamiu R.
Adetiba, Emmanuel
Abayomi, Abdultaofeek
Obiyemi, Obiseye O.
Thakur, Surendra
Moyo, Sibusiso
INNOVATIONS IN BIO-INSPIRED COMPUTING AND APPLICATIONS, IBICA 2021, 2022, 419 : 700 - 712
[37] Deep Learning Aided Method for Automatic Modulation Recognition
Yang, Cheng
He, Zhimin
Peng, Yang
Wang, Yu
Yang, Jie
IEEE ACCESS, 2019, 7 : 109063 - 109068
[38] Universal and complementary representation learning for automatic modulation recognition
Liu, Bohan
Ge, Ruixing
Zhu, Yuxuan
Zhang, Bolin
Bao, Yanfei
ELECTRONICS LETTERS, 2023, 59 (21)
[39] Evaluation of Machine Learning Algorithms for Automatic Modulation Recognition
Hazar, Muhammed Abdurrahman
Odabasioglu, Niyazi
Ensari, Tolga
Kavurucu, Yusuf
NEURAL INFORMATION PROCESSING, PT I, 2015, 9489 : 208 - 215
[40] Contrastive Semi-Supervised Learning With Pseudo-Label for Radar Signal Automatic Modulation Recognition
Wu, Dongming
Shi, Junpeng
Li, Zhihui
Du, Mingyang
Liu, Fangzheng
Zeng, Fangling
IEEE SENSORS JOURNAL, 2024, 24 (19) : 30399 - 30411

← 1 2 3 4 5 →