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

[1] Deep Transfer Learning method for Automatic Modulation Recognition
Zeng, Wenlong
Sheng, Hanmin
Xu, Xintao
Wang, Xi
2024 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE, I2MTC 2024, 2024,
[2] Signal Automatic Modulation Classification and Recognition in View of Deep Learning
Xu, Tianpei
Ma, Ying
IEEE ACCESS, 2023, 11 : 114623 - 114637
[3] AUTOMATIC MODULATION RECOGNITION OF DIGITALLY MODULATED SIGNALS
HSUE, SZ
SOLIMAN, SS
1989 IEEE MILITARY COMMUNICATIONS CONFERENCE, VOLS 1-3: BRIDGING THE GAP : INTEROPERABILITY, SURVIVABILITY, SECURITY, 1989, : 645 - 649
[4] Automatic Modulation Recognition using Deep Learning Architectures
Zhang, Meng
Zeng, Yuan
Han, Zidong
Gong, Yi
2018 IEEE 19TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (SPAWC), 2018, : 281 - 285
[5] Automatic Modulation Recognition for Secondary Modulated Signals
Chu, Peng
Xie, Lijin
Dai, Chuanjin
Chen, Yarong
IEEE WIRELESS COMMUNICATIONS LETTERS, 2021, 10 (05) : 962 - 965
[6] Automatic Modulation Recognition: A Few-Shot Learning Method Based on the Capsule Network
Li, Lixin
Huang, Junsheng
Cheng, Qianqian
Meng, Hongying
Han, Zhu
IEEE WIRELESS COMMUNICATIONS LETTERS, 2021, 10 (03) : 474 - 477
[7] Automatic Modulation Recognition for Spectrum Sensing using Nonuniform Compressive Samples
Lim, Chia Wei
Wakin, Michael B.
2012 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC), 2012,
[8] Few-Shot Learning of Signal Modulation Recognition based on Attention Relation Network
Zhang, Zilin
Li, Yan
Gao, Meiguo
28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020), 2021, : 1372 - 1376
[9] Large-Scale Printed Chinese Character Recognition for ID Cards Using Deep Learning and Few Samples Transfer Learning
Li, Yi-Quan
Chang, Hao-Sen
Lin, Daw-Tung
APPLIED SCIENCES-BASEL, 2022, 12 (02):
[10] Automatic modulation recognition algorithm for MQAM signal
Zhang, Huadi
Lou, Huaxun
Tongxin Xuebao/Journal on Communications, 2019, 40 (08): : 200 - 211

← 1 2 3 4 5 →