Autocorrelation Convolution Networks Based on Deep Learning for Automatic Modulation Classification

Duona Zhang; Wenrui Ding; Hongyu Wang; Baochang Zhang

doi:10.1109/ICIEA48937.2020.9248386

Autocorrelation Convolution Networks Based on Deep Learning for Automatic Modulation Classification

Duona Zhang
, Wenrui Ding
, Hongyu Wang
, Baochang Zhang

Beihang University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

4 引用（Scopus）

摘要

Automatic modulation classification (AMC) is challenging but significant in the field of cognitive radio. Despite recent deep learning methods have dominated as the best performers for AMC, they are challenged by the practical problem in low signal-to-noise ratios (SNRs). In this paper, we propose novel autocorrelation convolution networks (ACNs) to capture periodic representation for communication signals. In ACNs, modulation modes are classified with the periodic local features under an autocorrelation convolution criterion. The experimental results demonstrate that ACNs achieve a great improvement that outperforms recent deep learning methods in low SNRs.

源语言	英语
主期刊名	Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020
出版商	Institute of Electrical and Electronics Engineers Inc.
页	1561-1565
页数	5
ISBN（电子版）	9781728151694
DOI	https://doi.org/10.1109/ICIEA48937.2020.9248386
出版状态	已出版 - 9 11月 2020
活动	15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020 - Virtual, Kristiansand, 挪威期限: 9 11月 2020 → 13 11月 2020

出版系列

姓名	Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020

会议

会议	15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020
国家/地区	挪威
市	Virtual, Kristiansand
时期	9/11/20 → 13/11/20

联合国可持续发展目标

此成果有助于实现下列可持续发展目标：

可持续发展目标 7 经济适用的清洁能源

访问文件

10.1109/ICIEA48937.2020.9248386

其它文件与链接

链接到 Scopus 的出版物

引用此

Zhang, D., Ding, W., Wang, H., & Zhang, B. (2020). Autocorrelation Convolution Networks Based on Deep Learning for Automatic Modulation Classification. 在 Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020 (页码 1561-1565). 文章 9248386 (Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIEA48937.2020.9248386

Zhang, Duona ; Ding, Wenrui ; Wang, Hongyu 等. / Autocorrelation Convolution Networks Based on Deep Learning for Automatic Modulation Classification. Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 页码 1561-1565 (Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020).

@inproceedings{6bd8bce4b6b14e3a85eb4d74e3415616,

title = "Autocorrelation Convolution Networks Based on Deep Learning for Automatic Modulation Classification",

abstract = "Automatic modulation classification (AMC) is challenging but significant in the field of cognitive radio. Despite recent deep learning methods have dominated as the best performers for AMC, they are challenged by the practical problem in low signal-to-noise ratios (SNRs). In this paper, we propose novel autocorrelation convolution networks (ACNs) to capture periodic representation for communication signals. In ACNs, modulation modes are classified with the periodic local features under an autocorrelation convolution criterion. The experimental results demonstrate that ACNs achieve a great improvement that outperforms recent deep learning methods in low SNRs.",

keywords = "cognitive radio, Deep learning, modulation classification, wireless communication",

author = "Duona Zhang and Wenrui Ding and Hongyu Wang and Baochang Zhang",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020 ; Conference date: 09-11-2020 Through 13-11-2020",

year = "2020",

month = nov,

day = "9",

doi = "10.1109/ICIEA48937.2020.9248386",

language = "英语",

series = "Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1561--1565",

booktitle = "Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020",

address = "美国",

}

Zhang, D, Ding, W, Wang, H & Zhang, B 2020, Autocorrelation Convolution Networks Based on Deep Learning for Automatic Modulation Classification. 在 Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020., 9248386, Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020, Institute of Electrical and Electronics Engineers Inc., 页码 1561-1565, 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020, Virtual, Kristiansand, 挪威, 9/11/20. https://doi.org/10.1109/ICIEA48937.2020.9248386

Autocorrelation Convolution Networks Based on Deep Learning for Automatic Modulation Classification. / Zhang, Duona; Ding, Wenrui; Wang, Hongyu 等.
Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 页码 1561-1565 9248386 (Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - Autocorrelation Convolution Networks Based on Deep Learning for Automatic Modulation Classification

AU - Zhang, Duona

AU - Ding, Wenrui

AU - Wang, Hongyu

AU - Zhang, Baochang

PY - 2020/11/9

Y1 - 2020/11/9

N2 - Automatic modulation classification (AMC) is challenging but significant in the field of cognitive radio. Despite recent deep learning methods have dominated as the best performers for AMC, they are challenged by the practical problem in low signal-to-noise ratios (SNRs). In this paper, we propose novel autocorrelation convolution networks (ACNs) to capture periodic representation for communication signals. In ACNs, modulation modes are classified with the periodic local features under an autocorrelation convolution criterion. The experimental results demonstrate that ACNs achieve a great improvement that outperforms recent deep learning methods in low SNRs.

AB - Automatic modulation classification (AMC) is challenging but significant in the field of cognitive radio. Despite recent deep learning methods have dominated as the best performers for AMC, they are challenged by the practical problem in low signal-to-noise ratios (SNRs). In this paper, we propose novel autocorrelation convolution networks (ACNs) to capture periodic representation for communication signals. In ACNs, modulation modes are classified with the periodic local features under an autocorrelation convolution criterion. The experimental results demonstrate that ACNs achieve a great improvement that outperforms recent deep learning methods in low SNRs.

KW - cognitive radio

KW - Deep learning

KW - modulation classification

KW - wireless communication

UR - https://www.scopus.com/pages/publications/85097537459

U2 - 10.1109/ICIEA48937.2020.9248386

DO - 10.1109/ICIEA48937.2020.9248386

M3 - 会议稿件

AN - SCOPUS:85097537459

T3 - Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020

SP - 1561

EP - 1565

BT - Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020

Y2 - 9 November 2020 through 13 November 2020

ER -

Zhang D, Ding W, Wang H, Zhang B. Autocorrelation Convolution Networks Based on Deep Learning for Automatic Modulation Classification. 在 Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 页码 1561-1565. 9248386. (Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications, ICIEA 2020). doi: 10.1109/ICIEA48937.2020.9248386

Autocorrelation Convolution Networks Based on Deep Learning for Automatic Modulation Classification

摘要

出版系列

会议

联合国可持续发展目标

访问文件

其它文件与链接

指纹

引用此