一种基于深度学习的阵列缺陷校正和DOA估计算法

Wenwei Fang;Zhihui Cao;Dingke Yu;Xin Wang;Zixian Ma;Bing Lan;Chunyi Song;Zhiwei Xu
{"title":"一种基于深度学习的阵列缺陷校正和DOA估计算法","authors":"Wenwei Fang;Zhihui Cao;Dingke Yu;Xin Wang;Zixian Ma;Bing Lan;Chunyi Song;Zhiwei Xu","doi":"10.23919/JCIN.2022.9906943","DOIUrl":null,"url":null,"abstract":"Array imperfections will lead to serious performance degradation of the deep neural network (DNN) based direction of arrival (DOA) estimation in the low earth orbit (LEO) satellite communication by producing a mismatch between inference data and training data. In this paper, we propose a lightweight deep learning-based algorithm for array imperfection correction and DOA estimation. By preprocessing the covariance matrix of the array antenna outputs to the image, the array imperfection correction and DOA estimation problems are correspondingly converted into the image-to-image transformation task and image recognition task. Furthermore, for the deployment of real-time DNN-based DOA estimation on the resource-constrained edge system, generative adversarial network (GAN) model compression is applied to obtain a lightweight student generator of Pix2Pix for array imperfection correction. The Mobilenet-V2 is then used to extract the DOA information from the covariance matrix image. Simulations results demonstrate that the DOA estimation performance is significantly improved through the array imperfection correction. The proposed algorithm also better satisfies the real-time demand with decreased inference time on the resource-constrained edge system.","PeriodicalId":100766,"journal":{"name":"Journal of Communications and Information Networks","volume":"7 3","pages":"296-308"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"A Lightweight Deep Learning-Based Algorithm for Array Imperfection Correction and DOA Estimation\",\"authors\":\"Wenwei Fang;Zhihui Cao;Dingke Yu;Xin Wang;Zixian Ma;Bing Lan;Chunyi Song;Zhiwei Xu\",\"doi\":\"10.23919/JCIN.2022.9906943\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Array imperfections will lead to serious performance degradation of the deep neural network (DNN) based direction of arrival (DOA) estimation in the low earth orbit (LEO) satellite communication by producing a mismatch between inference data and training data. In this paper, we propose a lightweight deep learning-based algorithm for array imperfection correction and DOA estimation. By preprocessing the covariance matrix of the array antenna outputs to the image, the array imperfection correction and DOA estimation problems are correspondingly converted into the image-to-image transformation task and image recognition task. Furthermore, for the deployment of real-time DNN-based DOA estimation on the resource-constrained edge system, generative adversarial network (GAN) model compression is applied to obtain a lightweight student generator of Pix2Pix for array imperfection correction. The Mobilenet-V2 is then used to extract the DOA information from the covariance matrix image. Simulations results demonstrate that the DOA estimation performance is significantly improved through the array imperfection correction. The proposed algorithm also better satisfies the real-time demand with decreased inference time on the resource-constrained edge system.\",\"PeriodicalId\":100766,\"journal\":{\"name\":\"Journal of Communications and Information Networks\",\"volume\":\"7 3\",\"pages\":\"296-308\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-09-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Communications and Information Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/9906943/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Communications and Information Networks","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/9906943/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

阵列缺陷会导致基于深度神经网络(DNN)的低地球轨道卫星通信到达方向(DOA)估计在推理数据和训练数据之间产生不匹配,从而导致严重的性能下降。本文提出了一种轻量级的基于深度学习的阵列缺陷校正和DOA估计算法。通过对阵列天线输出到图像的协方差矩阵进行预处理,将阵列缺陷校正和DOA估计问题相应转化为图像到图像的转换任务和图像识别任务。此外,为了在资源受限的边缘系统上部署基于dnn的实时DOA估计,采用生成式对抗网络(GAN)模型压缩,获得轻量级的Pix2Pix学生生成器,用于阵列缺陷校正。然后使用Mobilenet-V2从协方差矩阵图像中提取DOA信息。仿真结果表明,通过对阵列缺陷进行校正,可以显著提高DOA估计的性能。该算法在资源受限的边缘系统上减少了推理时间,更好地满足了实时性需求。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Lightweight Deep Learning-Based Algorithm for Array Imperfection Correction and DOA Estimation
Array imperfections will lead to serious performance degradation of the deep neural network (DNN) based direction of arrival (DOA) estimation in the low earth orbit (LEO) satellite communication by producing a mismatch between inference data and training data. In this paper, we propose a lightweight deep learning-based algorithm for array imperfection correction and DOA estimation. By preprocessing the covariance matrix of the array antenna outputs to the image, the array imperfection correction and DOA estimation problems are correspondingly converted into the image-to-image transformation task and image recognition task. Furthermore, for the deployment of real-time DNN-based DOA estimation on the resource-constrained edge system, generative adversarial network (GAN) model compression is applied to obtain a lightweight student generator of Pix2Pix for array imperfection correction. The Mobilenet-V2 is then used to extract the DOA information from the covariance matrix image. Simulations results demonstrate that the DOA estimation performance is significantly improved through the array imperfection correction. The proposed algorithm also better satisfies the real-time demand with decreased inference time on the resource-constrained edge system.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信