Identification of Radio Frequency Interference Using Multi-scale TransUNet

doi:10.1088/1538-3873/ad54ef

YNAO OpenIR > 射电天文研究组

	Identification of Radio Frequency Interference Using Multi-scale TransUNet
	Zhang, Xuan 1; Liang, Bo 1; Hao LF(郝龙飞)2 ; Feng, Song 1; Wei, Shoulin 1; Dai, Wei 1; Dao, Yihang 1
发表期刊	PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC
	2024-06-01
卷号	136 期号:6
DOI	10.1088/1538-3873/ad54ef
产权排序	第2完成单位
收录类别	SCI
摘要	Radio observation is a method for conducting astronomical observations using radio waves. A common challenge in radio observations is Radio Frequency Interference (RFI), which refers to the unintentional or intentional interference of radio signals from other wireless sources within the radio frequency band. Such interference contaminates the astronomical signals received by radio telescopes, significantly affecting time-frequency domain astronomical observations and research. Consequently, identifying RFI is crucial. In this paper, we employ a deep learning approach to detect RFI present in observation data and propose an improved network structure based on TransUNet. This network leverages the principles of a multi-scale convolutional attention mechanism. It introduces an auxiliary branch to extract high-dimensional image information and an enhanced coordinate attention mechanism for feature map extraction, enabling more comprehensive and accurate identification of RFI in time-frequency images. We introduce a novel architecture named the Multi-Scale TransUNet Network, abbreviated as MS-TransUNet. We utilized observation data from the 40 m radio telescope at the Yunnan Observatory as a data set for training, validating, and testing the network. Compared with previous deep learning networks (U-Net, RFI-Net, R-Net, DSC, EMSCA-UNet), the recall rate and f2 score have been significantly improved. Specifically, the recall rate is improved by at least 2.99%, and the f2 score is improved by at least 2.46%. Experiments demonstrate that this network is exceptional in identifying RFI more comprehensively while ensuring high precision.
资助项目	National Key Research and Development Program of China[2020SKA0110300]; National Key Research and Development Program of China[2020SKA0120100]; National Natural Science Foundation of China[12063003]; National Natural Science Foundation of China[12073076]; Yunnan Ten Thousand Talents Plan Young & Elite Talents Project; Yunnan Key Laboratory of Computer Technologies Application
项目资助者	National Key Research and Development Program of China[2020SKA0110300, 2020SKA0120100] ; National Natural Science Foundation of China[12063003, 12073076] ; Yunnan Ten Thousand Talents Plan Young & Elite Talents Project ; Yunnan Key Laboratory of Computer Technologies Application
语种	英语
学科领域	天文学 ; 射电天文学
文章类型	Article
出版者	IOP Publishing Ltd
出版地	TEMPLE CIRCUS, TEMPLE WAY, BRISTOL BS1 6BE, ENGLAND
ISSN	0004-6280
URL	查看原文
WOS记录号	WOS:001259073800001
WOS研究方向	Astronomy & Astrophysics
WOS类目	Astronomy & Astrophysics
关键词[WOS]	MITIGATION
引用统计
文献类型	期刊论文
版本	出版稿
条目标识符	http://ir.ynao.ac.cn/handle/114a53/27435
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 and Yunnan Key Laboratory of Computer Technologies Application, Kunming, 650500, People's Republic of China; 2.Yunnan Observatories, Chinese Academy of Science, Kunming, 650000, People's Republic of China
推荐引用方式 GB/T 7714	Zhang, Xuan,Liang, Bo,Hao LF,et al. Identification of Radio Frequency Interference Using Multi-scale TransUNet[J]. PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC,2024,136(6).
APA	Zhang, Xuan.,Liang, Bo.,郝龙飞.,Feng, Song.,Wei, Shoulin.,...&Dao, Yihang.(2024).Identification of Radio Frequency Interference Using Multi-scale TransUNet.PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC,136(6).
MLA	Zhang, Xuan,et al."Identification of Radio Frequency Interference Using Multi-scale TransUNet".PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC 136.6(2024).

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
Identification of Ra（984KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文