Gravitational Wave Detection Based on Squeeze-and-excitation Shrinkage Networks and Multiple Detector Coherent SNR

doi:10.1088/1674-4527/ac846c

	Gravitational Wave Detection Based on Squeeze-and-excitation Shrinkage Networks and Multiple Detector Coherent SNR
	Yan, Rui-Qing 5; Liu, Wei 4; Yin, Zong-Yao 5; Ma, Rong 5; Chen, Si-Ying 5; Hu, Dan 2,3; Wu, Dan 1; Yu, Xian-Chuan 5
刊名	RESEARCH IN ASTRONOMY AND ASTROPHYSICS
	2022-11-01
卷号	22 期号:11 页码:13
关键词	methods: data analysis methods: statistical gravitational waves
ISSN号	1674-4527
DOI	10.1088/1674-4527/ac846c
通讯作者	Yan, Rui-Qing(yanruiqing@mail.bnu.edu.cn)
英文摘要	Deep learning techniques have been applied to the detection of gravitational wave signals in the past few years. Most existing methods focus on the data obtained by a single detector. However, the signal-to-noise ratio (SNR) of gravitational wave signals in a single detector is pretty low, making it hard for deep neural networks to learn effective features. Therefore, how to use the observation signals obtained by multiple detectors in deep learning methods is a serious issue. We simulate binary neutron star signals from multiple detectors, including the Advanced LIGO and Virgo detectors. We calculate coherent SNR of multiple detectors using a fully coherent all-sky search method and obtain the coherent SNR data required for our proposed deep learning method. Inspired by the principle of attention network Squeeze-and-Excitation Networks (SENet) and the soft thresholding shrinkage function, we propose a novel Squeeze-and-Excitation Shrinkage (SES) module to better extract effective features. Then we use this module to establish a gravitational wave squeeze-and-excitation shrinkage network (GW-SESNet) detection model. We train and validate the performance of our model on the coherent SNR data set. Our model obtains satisfactory classification accuracy and can excellently complete the task of gravitational wave detection.
资助项目	National Natural Science Foundation of China ; Beijing Natural Science Foundation[4224091] ; China Postdoctoral Science Foundation[2021M693402]
WOS关键词	CLASSIFICATION
WOS研究方向	Astronomy & Astrophysics
语种	英语
出版者	NATL ASTRONOMICAL OBSERVATORIES, CHIN ACAD SCIENCES
WOS记录号	WOS:000870859600001
资助机构	National Natural Science Foundation of China ; Beijing Natural Science Foundation ; China Postdoctoral Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50275]
专题	智能机器人系统研究
通讯作者	Yan, Rui-Qing
作者单位	1.Chinese Acad Sci, Natl Astron Observ, Beijing 100101, Peoples R China 2.Univ N Carolina, BRIC, Chapel Hill, NC 27599 USA 3.Univ N Carolina, Dept Radiol, Chapel Hill, NC 27599 USA 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 5.Beijing Normal Univ, Sch Artificial Intelligence, Beijing 100875, Peoples R China
推荐引用方式 GB/T 7714	Yan, Rui-Qing,Liu, Wei,Yin, Zong-Yao,et al. Gravitational Wave Detection Based on Squeeze-and-excitation Shrinkage Networks and Multiple Detector Coherent SNR[J]. RESEARCH IN ASTRONOMY AND ASTROPHYSICS,2022,22(11):13.
APA	Yan, Rui-Qing.,Liu, Wei.,Yin, Zong-Yao.,Ma, Rong.,Chen, Si-Ying.,...&Yu, Xian-Chuan.(2022).Gravitational Wave Detection Based on Squeeze-and-excitation Shrinkage Networks and Multiple Detector Coherent SNR.RESEARCH IN ASTRONOMY AND ASTROPHYSICS,22(11),13.
MLA	Yan, Rui-Qing,et al."Gravitational Wave Detection Based on Squeeze-and-excitation Shrinkage Networks and Multiple Detector Coherent SNR".RESEARCH IN ASTRONOMY AND ASTROPHYSICS 22.11(2022):13.