Pulsar candidate classification with deep convolutional neural networks

doi:10.1088/1674-4527/19/9/133

CORC > 国家天文台 > 中国科学院国家天文台

	Pulsar candidate classification with deep convolutional neural networks
	Wang, Yuan-Chao 1,2; Li, Ming-Tao 1,2; Pan, Zhi-Chen 3,4,5; Zheng, Jian-Hua 1,2
刊名	RESEARCH IN ASTRONOMY AND ASTROPHYSICS
	2019-09-01
卷号	19 期号:9 页码:10
关键词	pulsars: general methods: statistical methods: data analysis
ISSN号	1674-4527
DOI	10.1088/1674-4527/19/9/133
英文摘要	As the performance of dedicated facilities has continually improved, large numbers of pulsar candidates are being received, which makes selecting valuable pulsar signals from the candidates challenging. In this paper, we describe the design for a deep convolutional neural network (CNN) with 11 layers for classifying pulsar candidates. Compared to artificially designed features, the CNN chooses the sub-integrations plot and sub-bands plot for each candidate as inputs without carrying biases. To address the imbalance problem, a data augmentation method based on synthetic minority samples is proposed according to the characteristics of pulsars. The maximum pulses of pulsar candidates were first translated to the same position. and then new samples were generated by adding up multiple subplots of pulsars. The data augmentation method is simple and effective for obtaining varied and representative samples which keep pulsar characteristics. In experiments on the HTRU 1 dataset, it is shown that this model can achieve recall of 0.962 and precision of 0.963.
WOS关键词	DISCOVERY ; SELECTION ; SYSTEM
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:000485147000011
内容类型	期刊论文
源URL	[http://ir.bao.ac.cn/handle/114a11/27728]
专题	中国科学院国家天文台
通讯作者	Li, Ming-Tao
作者单位	1.Chinese Acad Sci, Natl Space Sci Ctr, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Natl Astron Observ, Beijing 100101, Peoples R China 4.Chinese Acad Sci, Ctr Astron Mega Sci, Beijing 100101, Peoples R China 5.Chinese Acad Sci, Natl Astron Observ, CAS Key Lab FAST, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Wang, Yuan-Chao,Li, Ming-Tao,Pan, Zhi-Chen,et al. Pulsar candidate classification with deep convolutional neural networks[J]. RESEARCH IN ASTRONOMY AND ASTROPHYSICS,2019,19(9):10.
APA	Wang, Yuan-Chao,Li, Ming-Tao,Pan, Zhi-Chen,&Zheng, Jian-Hua.(2019).Pulsar candidate classification with deep convolutional neural networks.RESEARCH IN ASTRONOMY AND ASTROPHYSICS,19(9),10.
MLA	Wang, Yuan-Chao,et al."Pulsar candidate classification with deep convolutional neural networks".RESEARCH IN ASTRONOMY AND ASTROPHYSICS 19.9(2019):10.