基于Swin-Transformer的短波协议信号识别

朱政宇; 陈鹏飞; 王梓晅; 巩克现; 吴迪; 王忠勇

doi:10.11959/j.issn.1000-436x.2022209

您当前的位置：

首页 >

文章列表页 >

基于Swin-Transformer的短波协议信号识别

学术论文 | 更新时间：2024-06-05

- 基于Swin-Transformer的短波协议信号识别
- Short wave protocol signals recognition based on Swin-Transformer
- 通信学报 2022年43卷第11期页码：127-135
- 作者机构：
  
  1. 郑州大学电气与信息工程学院，河南郑州 450001
  2. 郑州大学河南省智能网络和数据分析国际联合实验室，河南郑州 450001
  3. 郑州大学电子材料与系统国际联合研究中心，河南郑州 450001
  4. 信息工程大学数据与目标工程学院，河南郑州 450001
- 作者简介：
  
  [ "朱政宇（1988− ），男，河南周口人，博士，郑州大学副教授、硕士生导师，主要研究方向为无线通信与信号处理、智能反射表面技术、物理层安全技术等" ]
  [ "陈鹏飞（1998− ），男，河南南阳人，郑州大学硕士生，主要研究方向为短波通信、智能信号处理" ]
  [ "王梓晅（1998− ），男，河南周口人，郑州大学博士生，主要研究方向为通信信号处理、多源信息融合等" ]
  [ "巩克现（1976− ），男，山东泰安人，博士，郑州大学教授、博士生导师，主要研究方向为无线通信信号分析与处理、信道编码、无线接入、目标监测及电子对抗等" ]
  [ "吴迪（1984− ），男，福建建阳人，博士，信息工程大学讲师，主要研究方向为通信信号分析与智能处理、电子对抗等" ]
  [ "王忠勇（1965− ），男，江西遂川人，博士，郑州大学教授、博士生导师，主要研究方向为通信信号处理等" ]
- 基金信息：
  
  国家重点研发计划基金资助项目(2019QY0302);中国博士后科学基金资助项目(2020M682345);河南省高校科技创新人才支持计划资助项目(23HASTIT019);河南省博士后经费资助项目(202001015)
- DOI：10.11959/j.issn.1000-436x.2022209
  中图分类号： TN92
- 网络出版日期：2022-11，
  
  纸质出版日期：2022-11-25
- 稿件说明：
移动端阅览
朱政宇, 陈鹏飞, 王梓晅, 等. 基于Swin-Transformer的短波协议信号识别[J]. 通信学报, 2022,43(11):127-135.

Zhengyu ZHU, Pengfei CHEN, Zixuan WANG, et al. Short wave protocol signals recognition based on Swin-Transformer[J]. Journal on communications, 2022, 43(11): 127-135.
朱政宇, 陈鹏飞, 王梓晅, 等. 基于Swin-Transformer的短波协议信号识别[J]. 通信学报, 2022,43(11):127-135. DOI： 10.11959/j.issn.1000-436x.2022209.

Zhengyu ZHU, Pengfei CHEN, Zixuan WANG, et al. Short wave protocol signals recognition based on Swin-Transformer[J]. Journal on communications, 2022, 43(11): 127-135. DOI： 10.11959/j.issn.1000-436x.2022209.

摘要

针对短波复杂信道环境下信号所属协议识别困难的问题，提出一种基于Swin-Transformer神经网络模型的短波协议信号识别算法。首先使用时频分析方法得到信号的灰度时频图作为神经网络的输入；其次设计一种基于Swin-Transformer的神经网络模型，对信号时频图进行特征提取；最后将特征与协议建立映射关系，从而实现信号协议的识别。仿真实验结果表明，在信噪比大于 -4 dB的高斯信道下，所提算法的识别准确率接近100%，高于现有算法。此外，在强干扰以及多径时延衰落的信道条件下，所提算法仍具有较高的短波协议信号识别率。

Abstract

Aiming at the problem that it is difficult to identify the protocol to which the signal belongs in the complex SW channel environment

a SW protocol signal recognition algorithm based on Swin-Transformer neural network model was proposed.Firstly

the gray-scale time-frequency map of the signal was obtained by using the time-frequency analysis method as the input of the neural network.Secondly

a neural network model based on swing transformer was designed to extract the features of the signal time-frequency map.Finally

the mapping relationship between the features and the protocol was established to realize the recognition of the signal protocol.The simulation results show that the recognition accuracy of the proposed algorithm is close to 100% in the Gaussian channel with SNR greater than -4 dB

which is higher than the existing algorithms.In addition

under the channel conditions of strong interference and multipath delay fading

the proposed algorithm still has a high SW protocol signals recognition rate.

关键词

Keywords

references

张有光 , 江琥 , 熊鹰 . 通用短波数据传输协议发展状况综述 [J ] . 电讯技术 , 2002 , 42 ( 2 ): 140 - 144 .

ZHANG Y G , JIANG H , XIONG Y . Introduction to and comparison of commercial HF digital protocols [J ] . Telecommunication Engineering , 2002 , 42 ( 2 ): 140 - 144 .

GIESBRECHT J E , CLARKE R , ABBOTT D . Modulation recognition for real HF signals [C ] // Proceedings of Microelectronics:Design,Technology,and Packaging II . Bellingham:SPIE Press , 2006 : 458 - 469 .

聂东举 , 叶进 , 闫坤 , 等 . 基于SVM算法的短波通信协议识别技术 [J ] . 系统工程与电子技术 , 2013 , 35 ( 6 ): 1307 - 1311 .

NIE D J , YE J , YAN K , et al . Recognition technology for high frequency communication protocol based on SVM algorithm [J ] . Systems Engineering and Electronics , 2013 , 35 ( 6 ): 1307 - 1311 .

DEARLOVE C M , WRIGHT P G . Rapid HF waveform identification [C ] // Proceedings of Frequency Selection and Management Techniques for HF Communications . London:IET , 1999 : 1 - 5 .

林肖辉 , 张润生 . 基于模板匹配的2G-ALE信号识别技术 [J ] . 无线电通信技术 , 2016 , 42 ( 3 ): 46 - 48 , 69 .

LIN X H , ZHANG R S . Technology of 2G-ALE signal recognition based on spectrum template matching [J ] . Radio Communications Technology , 2016 , 42 ( 3 ): 46 - 48 , 69 .

谷双春 , 施昉 , 张润生 . 短波 110A 信号检测分析方法研究 [J ] . 无线电通信技术 , 2018 , 44 ( 3 ): 277 - 281 .

GU S C , SHI F , ZHANG R S . Study on HF 110A signal detection and analysis method [J ] . Radio Communications Technology , 2018 , 44 ( 3 ): 277 - 281 .

US Department of Defense . Interoperability and performance standards for data modems:MIL-STD-188-110A [S ] . 1991 .

North Atlantic Treaty Organization . Characteristics of 1200/2400/3600 bits per second single tone modulators/ demodulators for HF radio links:STANAG 4285 [S ] . 1989 .

US Department of Defense . Interoperability and performance standards for medium and high frequency radio systems:MIL-STD-188-141A [S ] . 1988 .

安泽亮 , 张天骐 , 马宝泽 , 等 . 基于一维 CNN 的多入多出 OSTBC信号协作调制识别 [J ] . 通信学报 , 2021 , 42 ( 7 ): 84 - 94 .

AN Z L , ZHANG T Q , MA B Z , et al . Cooperative modulation recognition based on one-dimensional convolutional neural network for MIMO-OSTBC signal [J ] . Journal on Communications , 2021 , 42 ( 7 ): 84 - 94 .

LIN S G , ZENG Y , GONG Y . Learning of time-frequency attention mechanism for automatic modulation recognition [J ] . IEEE Wireless Communications Letters , 2022 , 11 ( 4 ): 707 - 711 .

HUANG Z H , LI S , YANG X H , et al . OAE-EEKNN:an accurate and efficient automatic modulation recognition method for underwater acoustic signals [J ] . IEEE Signal Processing Letters , 2022 , 29 : 518 - 522 .

WAN L , WANG Q , PAPIR A , et al . Generalized end-to-end loss for speaker verification [C ] // Proceedings of 2018 IEEE International Conference on Acoustics,Speech and Signal Processing . Piscataway:IEEE Press , 2018 : 4879 - 4883 .

XU Z J , SAVVARIS A , TSOURDOS A , et al . High-frequency band automatic mode recognition using deep learning [C ] // Proceedings of 2018 IEEE/AIAA 37th Digital Avionics Systems Conference (DASC) . Piscataway:IEEE Press , 2018 : 1 - 5 .

杨司韩 , 彭华 , 许漫坤 , 等 . 基于卷积神经网络的超短波特定信号谱图识别 [J ] . 系统工程与电子技术 , 2019 , 41 ( 4 ): 744 - 751 .

YANG S H , PENG H , XU M K , et al . Ultra-short wave specific signal spectrogram recognition based on convolution neural network [J ] . Systems Engineering and Electronics , 2019 , 41 ( 4 ): 744 - 751 .

查雄 , 许漫坤 , 彭华 , 等 . 基于深度残差网络的特定协议信号识别 [J ] . 电子学报 , 2019 , 47 ( 7 ): 1532 - 1537 .

ZHA X , XU M K , PENG H , et al . Specific protocol signal recognition based on deep residual network [J ] . Acta Electronica Sinica , 2019 , 47 ( 7 ): 1532 - 1537 .

查雄 . 基于神经网络的数字调制信号检测、识别与解调算法 [D ] . 郑州:信息工程大学 , 2020 .

ZHA X . Research on digital modulation signal detection,recognition and demodulation based on neural network [D ] . Zhengzhou:Information Engineering University , 2020 .

HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C ] // Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway:IEEE Press , 2016 : 770 - 778 .

LIU Z , LIN Y T , CAO Y , et al . Swin transformer:hierarchical vision transformer using shifted windows [C ] // Proceedings of 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway:IEEE Press , 2021 : 9992 - 10002 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C ] // Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017) . Massachusetts:MIT Press , 2017 : 5998 - 6008 .

HAL Communications Corporation . CLOVER2000 waveform＆protocol [S ] . 1999 .

US Department of Defense . Interoperability and performance standards for tactical digital information link(TADIL)A:MIL-STD-118203-1A [S ] . 2013 .

XIAO Z L , YAN Z Y . Radar emitter identification based on novel time-frequency spectrum and convolutional neural network [J ] . IEEE Communications Letters , 2021 , 25 ( 8 ): 2634 - 2638 .

DOSOVITSKIY A , BEYER L , KOLESNIKOV A , et al . An image is worth 16×16 words:transformers for image recognition at scale [C ] // International Conference on Learning Representations (ICLR) .[S.l.:s.n. ] , 2021 : 1 - 21 .

US Department of Defense . Interoperability and performance standards for data modems:MIL-STD-188-110B [S ] . 2000 .

US Department of Defense . Interoperability and performance standards for medium and high frequency radio systems:MIL-STD-188141B [S ] . 1989 .

XIE S N , GIRSHICK R , DOLLÁR P , et al . Aggregated residual transformations for deep neural networks [C ] // Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway:IEEE Press , 2017 : 5987 - 5995 .

WATTERSON C , JUROSHEK J , BENSEMA W . Experimental confirmation of an HF channel model [J ] . IEEE Transactions on Communication Technology , 1970 , 18 ( 6 ): 792 - 803 .

浏览量

886

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于阵列的神经网络水声通信信号多参数联合估计算法

基于神经网络的恶意DNS流量检测方法

基于可见光和射频融合的通信定位一体化系统

基于特征依赖图的源代码漏洞检测方法

基于改进CFCC特征提取的语种识别算法研究