Radio frequency interference detection using efficient multiscale convolutional attention Unet

doi:10.1093/mnras/stae868

YNAO OpenIR > 射电天文研究组

	Radio frequency interference detection using efficient multiscale convolutional attention Unet
	Gu, Fei 1; Hao LF(郝龙飞)2 ; Liang, Bo 1; Feng, Song 1; Wei, Shoulin 1; Dai, Wei 1; Xu YH(徐永华)2 ; Li ZX(李志玄)2 ; Dao, Yihang 1
发表期刊	MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY
	2024-03-23
卷号	529 期号:4 页码:4719-4727
DOI	10.1093/mnras/stae868
产权排序	第2完成单位
收录类别	SCI ; EI
关键词	methods: data analysis techniques: image processing
摘要	Studying the Universe through radio telescope observation is crucial. However, radio telescopes capture not only signals from the universe but also various interfering signals, known as radio frequency interference (RFI). The presence of RFI can significantly impact data analysis. Ensuring the accuracy, reliability, and scientific integrity of research findings by detecting and mitigating or eliminating RFI in observational data, presents a persistent challenge in radio astronomy. In this study, we proposed a novel deep learning model called EMSCA-UNet for RFI detection. The model employs multiscale convolutional operations to extract RFI features of various scale sizes. Additionally, an attention mechanism is utilized to assign different weights to the extracted RFI feature maps, enabling the model to focus on vital features for RFI detection. We evaluated the performance of the model using real data observed from the 40 m radio telescope at Yunnan Observatory. Furthermore, we compared our results to other models, including U-Net, RFI-Net, and R-Net, using four commonly employed evaluation metrics: precision, recall, F1 score, and IoU. The results demonstrate that our model outperforms the other models on all evaluation metrics, achieving an average improvement of approximately 5 per cent compared to U-Net. Our model not only enhances the accuracy and comprehensiveness of RFI detection but also provides more detailed edge detection while minimizing the loss of useful signals.
资助项目	National Key Research and Development Program[2020SKA0110300]; National Key Research and Development Program[2020SKA0120100]; National Key Research and Development Program of China[12063003]; National Key Research and Development Program of China[12073076]; National Natural Science Foundation of China; Yunnan Ten Thousand Talents Plan Young Elite Talents
项目资助者	National Key Research and Development Program[2020SKA0110300, 2020SKA0120100] ; National Key Research and Development Program of China[12063003, 12073076] ; National Natural Science Foundation of China ; Yunnan Ten Thousand Talents Plan Young Elite Talents
语种	英语
学科领域	天文学 ; 射电天文学
文章类型	Article
出版者	OXFORD UNIV PRESS
出版地	GREAT CLARENDON ST, OXFORD OX2 6DP, ENGLAND
ISSN	0035-8711
URL	查看原文
WOS记录号	WOS:001208268900025
WOS研究方向	Astronomy & Astrophysics
WOS类目	Astronomy & Astrophysics
关键词[WOS]	MITIGATION
EI入藏号	20241816026984
EI主题词	Data handling
EI分类号	461.4 Ergonomics and Human Factors Engineering - 657.2 Extraterrestrial Physics and Stellar Phenomena - 701.1 Electricity: Basic Concepts and Phenomena - 711 Electromagnetic Waves - 716.1 Information Theory and Signal Processing - 716.3 Radio Systems and Equipment - 723.2 Data Processing and Image Processing - 903.1 Information Sources and Analysis
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ynao.ac.cn/handle/114a53/27151
专题	射电天文研究组
作者单位	1.Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China; 2.Yunnan Observatories, Chinese Academy of Science, Kunming 650000, Yunnan, China
推荐引用方式 GB/T 7714	Gu, Fei,Hao LF,Liang, Bo,et al. Radio frequency interference detection using efficient multiscale convolutional attention Unet[J]. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY,2024,529(4):4719-4727.
APA	Gu, Fei.,郝龙飞.,Liang, Bo.,Feng, Song.,Wei, Shoulin.,...&Dao, Yihang.(2024).Radio frequency interference detection using efficient multiscale convolutional attention Unet.MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY,529(4),4719-4727.
MLA	Gu, Fei,et al."Radio frequency interference detection using efficient multiscale convolutional attention Unet".MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 529.4(2024):4719-4727.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Radio frequency inte（1045KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文