基于镜像填充谱与LA-ResNet50的超短波卫星信道分类识别算法

吴尚; 沈雷; 王李军; 张如栩; 胡鑫

doi:10.11959/j.issn.1000-0801.2023185

您当前的位置：

首页 >

文章列表页 >

基于镜像填充谱与LA-ResNet50的超短波卫星信道分类识别算法

研究与开发 | 更新时间：2024-06-05

- 基于镜像填充谱与LA-ResNet50的超短波卫星信道分类识别算法
- Ultrashort wave satellite channel classification and recognition algorithm based on mirror filled spectrum and LA-ResNet50
- 电信科学 2023年39卷第10期页码：74-84
- 作者机构：
  
  1. 杭州电子科技大学通信工程学院，浙江杭州 310018
  2. 中国电子科技集团公司第三十六研究所，浙江嘉兴 314000
  3. 通信信息控制和安全技术重点实验室，浙江嘉兴 314000
- 作者简介：
  
  [ "吴尚（1997- ），男，杭州电子科技大学通信工程学院硕士生，中国电子科技集团公司第三十六研究所联合培养硕士生，主要研究方向为数字信号图像处理" ]
  [ "沈雷（1979- ），男，博士，杭州电子科技大学教授、博士生导师，主要研究方向为数字图像处理、模式识别" ]
  [ "王李军（1978- ），男，博士，杭州电子科技大学硕士生导师，中国电子科技集团公司第三十六研究所博士后工作站研究员，通信信息控制和安全技术重点实验室常务副主任，主要研究方向为卫星导航技术、信号与信息处理" ]
  [ "张如栩（1999- ），男，杭州电子科技大学通信工程学院硕士生，主要研究方向为数字信号处理" ]
  [ "胡鑫（1999- ），男，杭州电子科技大学通信工程学院硕士生，主要研究方向为数字信号处理" ]
- 基金信息：
  
  国家自然科学基金资助项目;The National Natural Science Foundation of China(62072121);浙江省尖兵领雁项目;The “Pioneer” and “Leading Goose” Research and development Program of Zhejiang(2023C01143)
- DOI：10.11959/j.issn.1000-0801.2023185
  中图分类号： TN911.73
- 网络出版日期：2023-10，
  
  纸质出版日期：2023-10-20
- 稿件说明：
移动端阅览
吴尚, 沈雷, 王李军, 等. 基于镜像填充谱与LA-ResNet50的超短波卫星信道分类识别算法[J]. 电信科学, 2023,39(10):74-84.

Shang WU, Lei SHEN, Lijun WANG, et al. Ultrashort wave satellite channel classification and recognition algorithm based on mirror filled spectrum and LA-ResNet50[J]. Telecommunications science, 2023, 39(10): 74-84.
吴尚, 沈雷, 王李军, 等. 基于镜像填充谱与LA-ResNet50的超短波卫星信道分类识别算法[J]. 电信科学, 2023,39(10):74-84. DOI： 10.11959/j.issn.1000-0801.2023185.

Shang WU, Lei SHEN, Lijun WANG, et al. Ultrashort wave satellite channel classification and recognition algorithm based on mirror filled spectrum and LA-ResNet50[J]. Telecommunications science, 2023, 39(10): 74-84. DOI： 10.11959/j.issn.1000-0801.2023185.

摘要

针对超短波频段中存在的5 kHz信道、25 kHz信道、宽带干扰信道、窄带干扰信道和单音干扰信道的分类识别问题，提出了一种基于镜像填充谱与局部二值模式的注意力机制残差网络（LBP attention ResNet50， LA-ResNet50）的超短波信道分类识别方法，有效解决了低信噪比下卫星信道与底噪难以区分，信号信道与特征相近的干扰信道识别困难的问题。首先，所提方法对超短波的频谱进行镜像对称并填充，同时对频谱边缘进行描黑处理，构成镜像填充谱，提高不同类型信道频谱图的区分度；然后，在ResNet50中引入通道注意力机制，使网络模型关注度集中在信道上；最后，提出了基于交叉熵和局部二值模式（local binary pattern，LBP）的损失函数，提高对信号信道和干扰信道图像边缘细微纹理特征的提取效果。所提基于镜像填充谱和LA-ResNet50 的方法，对比利用快速傅里叶变换（fast Fourier transform，FFT）频谱门限阈值分类的传统方法与基于镜像填充谱的YOLOv5s目标检测分类法，以及基于镜像填充谱的注意力机制残差网络（Attention-ResNet50）、Transformer网络方法，在10 dB信噪比下对超短波信道的分类识别率分别提高了19.8%、8.2%、1.8%、0.8%。

Abstract

In response to the classification and identification problems of 5 kHz channels

25 kHz channels

broadband interference channels

narrowband interference channels

and single tone interference channels in the ultrashort wave frequency band

a classification and identification method for ultrashort wave channels based on mirror filled spectrum and LA-ResNet50 (LBP attention ResNet50) was proposed.The problem of difficulty in distinguishing between satellite channels and background noise under low signal-to-noise ratio

as well as the identification of signal channels and interference channels with similar characteristics

has been effectively solved.Firstly

the proposed method performs mirror symmetry on the ultrashort wave spectrum and fills it in

while blackening the edges of the spectrum to construct a mirror-filled spectrum

which improves the discrimination of different types of channel spectra.Then

channel attention was introduced into ResNet50 to focus the attention of the network model on the channel.Finally

a loss function based on cross entropy and local binary pattern (LBP) was proposed to improve the extraction effect of subtle texture features on signal channels and interference channels images.The proposed method based on mirror-filled spectrum and LA-ResNet50 has shown an improvement of 19.8%

8.2%

1.8%

and 0.8% in classification accuracy for ultrashort wave channels compared to the traditional method utilizing fast Fourier transform (FFT) spectrum thresholding

the YOLOv5s target detection and classification method based on mirror-filled spectrum

the Attention-ResNet50 method with attention mechanism based on mirror-filled spectrum

and the Transformer network method under a signal-to-noise ratio (SNR) of 10 dB.

关键词

Keywords

references

张洋 , 毛忠阳 , 刘锡国 , 等 . 海上超短波超视距对流层散射信道模型研究 [J ] . 电波科学学报 , 2022 , 37 ( 2 ): 238 - 243 .

ZHANG Y , MAO Z Y , LIU X G , et al . Study on tropospheric scattering channel model of ultra short wave over the horizon at sea [J ] . Chinese Journal of Radio Science , 2022 , 37 ( 2 ): 238 - 243 .

孔凌劲 , 刘月玲 , 张校晨 , 等 . 超短波频段复杂城区场景的信道测量与建模 [J ] . 电波科学学报 , 2020 , 35 ( 4 ): 542 - 550 .

KONG L J , LIU Y L , ZHANG X C , et al . Channel measurement and modeling for VHF bands in typical urban scenarios [J ] . Chinese Journal of Radio Science , 2020 , 35 ( 4 ): 542 - 550 .

陈柯威 , 刘宏波 , 马俊凯 . 超短波信道模型的仿真与分析 [J ] . 舰船电子工程 , 2022 , 42 ( 2 ): 87 - 90 , 129 .

CHEN K W , LIU H B , MA J K . Simulation and analysis of ultrashort wave channel model [J ] . Ship Electronic Engineering , 2022 , 42 ( 2 ): 87 - 90 , 129 .

张玉波 , 李志达 , 沈延峰 . 虚拟短波/超短波通信系统的关键技术研究 [J ] . 中国新通信 , 2016 , 18 ( 7 ): 92 .

ZHANG Y B , LI Z D , SHEN Y F . Research on key technologies of virtual shortwave/ultrashort wave communication system [J ] . China New Telecommunications , 2016 , 18 ( 7 ): 92 .

黄超 . 无线射频信号的能量检测与特征识别 [D ] . 北京:北京邮电大学 , 2016 .

HUANG C . Energy detection and feature recognition of radio frequency signals [D ] . Beijing:Beijing University of Posts and Telecommunications , 2016 .

SMRITI , CHHAGAN C . Double threshold-based energy detection spectrum sensing scheme by considering the sensing history in confusion region [C ] // Proceedings of 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN) . Piscataway:IEEE Press , 2018 : 518 - 521 .

WANG W Y , WANG J M , LI C Q . A signal detection method based on hybrid energy detection [C ] // Proceedings of 2022 4th International Conference on Intelligent Control,Measurement and Signal Processing (ICMSP) . Piscataway:IEEE Press , 2022 : 695 - 700 .

LI P J , HOU D Y , ZHAO J , et al . Research on adaptive energy detection technology based on correlation window [C ] // Proceedings of 2021 IEEE 5th Information Technology,Networking,Electronic and Automation Control Conference (ITNEC) . Piscataway:IEEE Press , 2021 : 836 - 840 .

姚朋 . 基于频谱特征的深度学习信号检测方法研究 [D ] . 武汉:华中科技大学 , 2019 .

YAO P . Research on deep learning signal detection method based on spectral features [D ] . Wuhan:Huazhong University of Science and Technology , 2019 .

KUMAR Y , SHEORAN M , JAJOO G , et al . Automatic modulation classification based on constellation density using deep learning [J ] . IEEE Communications Letters , 2020 , 24 ( 6 ): 1275 - 1278 .

BHATTI F A , KHAN M J , SELIM A , et al . Shared spectrum monitoring using deep learning [J ] . IEEE Transactions on Cognitive Communications and Networking , 2021 , 7 ( 4 ): 1171 - 1185 .

邵延华 , 张铎 , 楚红雨 , 等 . 基于深度学习的 YOLO 目标检测综述 [J ] . 电子与信息学报 , 2022 , 44 ( 10 ): 3697 - 3708 .

SHAO Y H , ZHANG D , CHU H Y , et al . A review of YOLO object detection based on deep learning [J ] . Journal of Electronics ＆ Information Technology , 2022 , 44 ( 10 ): 3697 - 3708 .

周宇航 , 侯进 , 李嘉新 , 等 . 基于频域叠加和深度学习的频谱信号识别 [J ] . 计算机应用研究 , 2023 , 40 ( 3 ): 874 - 879 .

ZHOU Y H , HOU J , LI J X , et al . Spectrum signal identification based on frequency-domain superposition and deep learning [J ] . Application Research of Computers , 2023 , 40 ( 3 ): 874 - 879 .

郑金志 , 汲如意 , 张立波 , 等 . 基于 Transformer 解码的端到端场景文本检测与识别算法 [J ] . 通信学报 , 2023 , 44 ( 5 ): 64 - 78 .

ZHENG J Z , JI R Y , ZHANG L B , et al . End-to-end scene text detection and recognition algorithm based on Transformer decoders [J ] . Journal on Communications , 2023 , 44 ( 5 ): 64 - 78 .

霍纬纲 , 梁锐 , 李永华 . 基于随机Transformer的多维时间序列异常检测模型 [J ] . 通信学报 , 2023 , 44 ( 2 ): 94 - 103 .

HUO W G , LIANG R , LI Y H . Anomaly detection model for multivariate time series based on stochastic Transformer [J ] . Journal on Communications , 2023 , 44 ( 2 ): 94 - 103 .

李宝奇 . 深度卷积神经网络及其在地面图像目标识别中的应用 [D ] . 西安:西北工业大学 , 2019 .

LI B Q . Depth convolution neural network and its application in ground image target recognition [D ] . Xi’an:Northwestern Polytechnical University , 2019 .

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 (CVPR) . Piscataway:IEEE Press , 2016 : 770 - 778 .

HU J , SHEN L , SUN G . Squeeze-and-excitation networks [C ] // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway:IEEE Press , 2018 : 7132 - 7141 .

徐文贵 . 基于融合全局与局部特征网络的指静脉识别算法及其轻量化研究 [D ] . 杭州:杭州电子科技大学 , 2022 .

XU W G . Finger vein identification algorithm based on global and local feature networks and its lightweight research [D ] . Hangzhou:Hangzhou Dianzi University , 2022 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

GMTBLC：基于深度学习的双模态网络流量分类

基于改进长短期记忆网络的新能源场站网络安全评估方法研究

基于霍克斯过程的动态异质网络表征学习方法

信号增强网络驱动的调制识别

基于特征校正的多对抗域适应方法