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

被引：23

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 22 条

[1]

Alnajjar K. A., 2022, P IEEE 5 INT C COMM, P1

[2] Adversarial Transfer Learning for Deep Learning Based Automatic Modulation Classification [J].

Bu, Ke ;

He, Yuan ;

Jing, Xiaojun ;

Han, Jindong .

IEEE SIGNAL PROCESSING LETTERS, 2020, 27 :880-884

[3] A Faster Maximum-Likelihood Modulation Classification in Flat Fading Non-Gaussian Channels [J].

Chen, Wenhao ;

Xie, Zhuochen ;

Ma, Lu ;

Liu, Jie ;

Liang, Xuwen .

IEEE COMMUNICATIONS LETTERS, 2019, 23 (03) :454-457

[4] Abandon Locality: Frame-Wise Embedding Aided Transformer for Automatic Modulation Recognition [J].

Chen, Yantao ;

Dong, Binhong ;

Liu, Cuiting ;

Xiong, Wenhui ;

Li, Shaoqian .

IEEE COMMUNICATIONS LETTERS, 2023, 27 (01) :327-331

[5]

DARPA, 2018, Radio frequency machine learning systems (RFMLS)

[6]

DeepSig, 2022, RF datasets for machine learning

[7] Data-and-Knowledge Dual-Driven Automatic Modulation Recognition for Wireless Communication Networks [J].

Ding, Rui ;

Zhang, Hao ;

Zhou, Fuhui ;

Wu, Qihui ;

Han, Zhu .

IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, :1962-1967

[8] Evaluating Adversarial Evasion Attacks in the Context of Wireless Communications [J].

Flowers, Bryse ;

Buehrer, R. Michael ;

Headley, William C. .

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2020, 15 :1102-1113

[9] On classifiers for blind feature-based automatic modulation classification over multiple-input-multiple-output channels [J].

Kharbech, Sofiane ;

Dayoub, Iyad ;

Zwingelstein-Colin, Marie ;

Simon, Eric Pierre .

IET COMMUNICATIONS, 2016, 10 (07) :790-795

[10] Automatic Modulation Recognition: A Few-Shot Learning Method Based on the Capsule Network [J].

Li, Lixin ;

Huang, Junsheng ;

Cheng, Qianqian ;

Meng, Hongying ;

Han, Zhu .

IEEE WIRELESS COMMUNICATIONS LETTERS, 2021, 10 (03) :474-477

← 1 2 3 →