WANG Jiamin,LI Tianjia,GU Taofeng,et al.A Method of Electromagnetic Interference Identification and Suppression based on Deep Convolutional Neural Network[J].Journal of Chengdu University of Information Technology,2024,39(01):43-49.[doi:10.16836/j.cnki.jcuit.2024.01.008]
一种基于深度卷积神经网络的电磁干扰识别与抑制方法
- Title:
- A Method of Electromagnetic Interference Identification and Suppression based on Deep Convolutional Neural Network
- 文章编号:
- 2096-1618(2024)01-0043-07
- 分类号:
- TN959.4
- 文献标志码:
- A
- 摘要:
- 随着无线电通信技术的发展,人工无线电对气象雷达的电磁干扰(EMI)明显增加,对雷达数据的质量产生严重影响。目前,关于检测和抑制电磁干扰的研究大多是基于雷达的初级产品。从雷达接收机前端的I/Q数据出发,提出使用深度卷积神经网络来识别和抑制电磁干扰的方法。设计一种残差结构的全卷积网络,并且选择UNet和DeepLab V3+共同进行识别效果的对比,在识别之后使用线性插值方法对电磁干扰进行抑制。结果显示,3种模型都能有效地识别电磁干扰,并且在识别的准确率上和召回率上各有优劣。在对识别结果进行抑制后,使得雷达数据质量都得到明显的提高。
- Abstract:
- In recent years, the development of radio communication technology has significantly increased Electromagnetic interference(EMI)from artificial radio, which has a detrimental impact on the quality of weather radar data. Current research on detecting and suppressing EMI mostly focuses on the primary radar products. This paper proposes a method to identify and suppress EMI using deep convolutional neural networks applied to the I/Q data of the front end of radar receivers. Specifically, this paper designed a fully convolutional network with residual structure. As well as UNet and DeepLab V3+ were selected to compare the identification effect together, following which a linear interpolation method is used to suppress the electromagnetic interference. The results show that all three models can effectively identify EMI, and each has its advantages and disadvantages in the accuracy and recall rate. Suppressing EMI based on the identification significantly improves the quality of radar data.
参考文献/References:
[1] Vaccarono M,Chandrasekar C V,Bechini R.Survey on Electromagnetic Interference in Weather Radars in Northwestern Italy[J].Environments,2019,6(12):126.
[2] Saltikoff E,Cho J Y N,Tristant P. The Threat to Weather Radars by Wireless Technology[J].Bulletin of the American Meteorological Society,2016,97(7):1159-1167.
[3] Cho J Y N.Signal Processing Algorithms for the Terminal Doppler Weather Radar:Build 2[J].Signal Processing Algorithms for the Terminal Doppler,2010:89.
[4] Yin J,Unal C M H,Russchenberg H W J.Narrow-Band Clutter Mitigation in Spectral Polarimetric Weather Radar[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(8):4655-4667.
[5] Lakshmanan V,Hondl K,Stumpf G.Quality control of weather radar data using texture features and a neural network[C].Preprints,31st Radar Conference,2003:522-525.
[6] Cho J Y N.A New Radio Frequency Interference Filter for Weather Radars[J].Journal of Atmospheric and Oceanic Technology,2017,34(7):1393-1406.
[7] Simonyan K,Zisserman A.Very Deep Convolutional Networks for Large-Scale Image Recognition[C].International Conference on Learning Representations.Computational and Biological Learning Society,2015.
[8] Krizhevsky A,Sutskever I,Hinton G E. ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[9] Long J,Shelhamer E,Darrell T.Fully Convolutional Networks for Semantic Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[10] Chen L C,Papandreou G,Kokkinos I.Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs[J].Computer Science,2014(4):357-361.
[11] Chen L C,Papandreou G,Kokkinos I.DeepLab:Semantic Image Segmentation with Deep Convolutional Nets,Atrous Convolution,and Fully Connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848.
[12] Nishiguchi K,Kobayashi M.Improved algorithm for estimating pulse repetition intervals[J].IEEE Transactions on Aerospace and Electronic Systems,2000,36(2):407-421.
[13] He K,Zhang X,Ren S,et al.Deep Residual Learning for Image Recognition[J].computer vision and pattern recognition,2016:770-778.
[14] Ronneberger O.U-Net Convolutional Networks for Biomedical Image Segmentation[J].Medical Image Computing and Computer-Assisted Intervention(MICCAI),Springer,LNCS,2017,9351:234-241.
[15] Chen L C,Zhu Y,Papandreou G,et al.Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation[C].European Conference on Computer Vision.Springer,Cham,2018.
[16] Chollet F.Xception:Deep learning with depthwise separable convolutions[J].Proceedings of the IEEE conference on computer vision and pattern recognition.2017:1251-1258.
[17] Chen L C,Papandreou G,Schroff F.Rethinking Atrous Convolution for Semantic Image Segmentation[J].Computer Vision and Pattern Recognition,2017:801-818.
[18] Kanopoulos N,Vasanthavada N,Baker R L.Design of an image edge detection filter using the Sobel operator[J].IEEE Journal of Solid-State Circuits,1988,23(2):358-367.
[19] Loshchilov I,Hutter F.SGDR:Stochastic Gradient Descent with Warm Restarts[J].ICLR&apos,2016(9):17.
备注/Memo
收稿日期:2023-03-08