Pulsar candidate identification using advanced transformer-based models

doi:10.1016/j.cjph.2024.05.020

	Pulsar candidate identification using advanced transformer-based models
	Cao, Jie 1; Xu, Tingting 1; Deng, Linhua 1; Zhou, Xueliang 1; Li, Shangxi 1; Liu, Yuxia 1; Zhou, Weihong 1,2
发表期刊	CHINESE JOURNAL OF PHYSICS
	2024-08
卷号	90 页码:121-133
DOI	10.1016/j.cjph.2024.05.020
收录类别	SCI
关键词	Pulsars General Methods Data analysis Techniques Image processing
摘要	Rapid and accurate identification of pulsars is a significant topic for large radio telescope surveys. With the enhancement of astronomical instruments, modern radio telescopes are witnessing an exponential increase in pulsar candidate detections. The application of artificial intelligence for the identification of pulsar candidates is an automated and highly effective solution to tackle the challenge of processing and recognizing vast volumes of data. In this work, using the data released by two surveys, the Commensal Radio Astronomy FasT Survey (CRAFTS) and High -Time Resolution Universe (HTRU), we propose a new framework to identify pulsar candidates. Firstly, due to the small number of real pulsars, we compare the performance of different data augmentation methods and find that the pulsar samples generated by the Deep Convolutional Generative Adversarial Network (DCGAN) based on deep learning techniques are closer to real pulsars. Secondly, we use two transformer -based classification models, Vision Transformer (ViT) and Convolutional Vision Transformer (CvT), to classify pulsar candidates, and find that the evaluation indexes of pulsar candidate classification based on two transformers can reach 100%. Finally, we use the t -distributed Stochastic Neighbor Embedding (t-SNE) algorithm to visualize the results of our identification framework. The results showed that pulsar and non -pulsar samples are separated from each other in multidimensional space. Therefore, it is a new attempt to apply transformer technology to pulsar candidate classification, and it could be of great significance to subsequent theoretical research.
资助项目	National Nature Science Foundation of China[61561053]; Yunnan Fundamental Research Projects, China[202301AV070007]; Yunnan Fundamental Research Projects, China[202401AU070026]; Yunnan Revitalization Talent Support Program Innovation Team Project, China[202405AS350012]; Scientific Research Foundation Project of Yunnan Education Department, China[2023J0624]; Scientific Research Foundation Project of Yunnan Education Department, China[2024Y469]
项目资助者	National Nature Science Foundation of China[61561053] ; Yunnan Fundamental Research Projects, China[202301AV070007, 202401AU070026] ; Yunnan Revitalization Talent Support Program Innovation Team Project, China[202405AS350012] ; Scientific Research Foundation Project of Yunnan Education Department, China[2023J0624, 2024Y469]
语种	英语
学科领域	天文学 ; 射电天文学
文章类型	Article
出版者	ELSEVIER
出版地	RADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS
ISSN	0577-9073
URL	查看原文
WOS记录号	WOS:001246487300001
WOS研究方向	Physics
WOS类目	Physics, Multidisciplinary
关键词[WOS]	CLASSIFICATION ; DISCOVERY
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/114a53/27396
专题	中国科学院天体结构与演化重点实验室
作者单位	1.School of Mathematics and Computer Science, Yunnan Minzu University, Kunming 650504, China; 2.Key Laboratory for the Structure and Evolution of Celestial Objects, Chinese Academy China of Sciences, Kunming 650011, China
推荐引用方式 GB/T 7714	Cao, Jie,Xu, Tingting,Deng, Linhua,et al. Pulsar candidate identification using advanced transformer-based models[J]. CHINESE JOURNAL OF PHYSICS,2024,90:121-133.
APA	Cao, Jie.,Xu, Tingting.,Deng, Linhua.,Zhou, Xueliang.,Li, Shangxi.,...&Zhou, Weihong.(2024).Pulsar candidate identification using advanced transformer-based models.CHINESE JOURNAL OF PHYSICS,90,121-133.
MLA	Cao, Jie,et al."Pulsar candidate identification using advanced transformer-based models".CHINESE JOURNAL OF PHYSICS 90(2024):121-133.

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
Pulsar candidate ide（2574KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文