Pulsar Candidate Classification Using a Computer Vision Method from a Combination of Convolution and Attention

被引：3

作者：

Cai, Nannan ^{[1
,2
]}

Han, Jinlin ^{[1
,2
,3
]}

Jing, Weicong ^{[1
,2
]}

Zhang, Zekai ^{[4
]}

Zhou, Dejiang ^{[1
,2
]}

Chen, Xue ^{[1
,2
]}

机构：

[1] Chinese Acad Sci, Natl Astron Observ, Beijing 100101, Peoples R China

[2] Univ Chinese Acad Sci, Sch Astron, Beijing 100049, Peoples R China

[3] Chinese Acad Sci, CAS Key Lab FAST, NAOC, Beijing 100101, Peoples R China

[4] Boston Coll, Dept Phys, Chestnut Hill, MA 02467 USA

来源：

RESEARCH IN ASTRONOMY AND ASTROPHYSICS | 2023年 / 23卷 / 10期

基金：

中国国家自然科学基金;

关键词：

(stars:) pulsars: general; methods: data analysis; techniques: image processing; NEURAL-NETWORK; SELECTION;

D O I：

10.1088/1674-4527/accdc2

中图分类号：

P1 [天文学];

学科分类号：

0704 ;

摘要：

Artificial intelligence methods are indispensable to identifying pulsars from large amounts of candidates. We develop a new pulsar identification system that utilizes the CoAtNet to score two-dimensional features of candidates, implements a multilayer perceptron to score one-dimensional features, and relies on logistic regression to judge the corresponding scores. In the data preprocessing stage, we perform two feature fusions separately, one for one-dimensional features and the other for two-dimensional features, which are used as inputs for the multilayer perceptron and the CoAtNet respectively. The newly developed system achieves 98.77% recall, 1.07% false positive rate (FPR) and 98.85% accuracy in our GPPS test set.

引用

页数：9

共 33 条

[11] ImageNet Classification with Deep Convolutional Neural Networks
Krizhevsky, Alex
Sutskever, Ilya
Hinton, Geoffrey E.
[J]. COMMUNICATIONS OF THE ACM, 2017, 60 (06) : 84 - 90
[12] Gradient-based learning applied to document recognition
Lecun, Y
Bottou, L
Bengio, Y
Haffner, P
[J]. PROCEEDINGS OF THE IEEE, 1998, 86 (11) : 2278 - 2324
[13] Li X, 2019, Arxiv, DOI [arXiv:1903.06586, 10.48550/arXiv.1903.06586]
[14] Pulsar Candidate Sifting Using Multi-input Convolution Neural Networks
Lin, Haitao
Li, Xiangru
Zeng, Qingguo
[J]. ASTROPHYSICAL JOURNAL, 2020, 899 (02)
[15] Pulsars detection by machine learning with very few features
Lin, Haitao
Li, Xiangru
Luo, Ziying
[J]. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, 2020, 493 (02) : 1842 - 1854
[16] Fifty years of pulsar candidate selection: from simple filters to a new principled real-time classification approach
Lyon, R. J.
Stappers, B. W.
Cooper, S.
Brooke, J. M.
Knowles, J. D.
[J]. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, 2016, 459 (01) : 1104 - 1123
[17] SPINN: a straightforward machine learning solution to the pulsar candidate selection problem
Morello, V.
Barr, E. D.
Bailes, M.
Flynn, C. M.
Keane, E. F.
van Straten, W.
[J]. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, 2014, 443 (02) : 1651 - 1662
[18] THE FIVE-HUNDRED-METER APERTURE SPHERICAL RADIO TELESCOPE (FAST) PROJECT
Nan, Rendong
Li, Di
Jin, Chengjin
Wang, Qiming
Zhu, Lichun
Zhu, Wenbai
Zhang, Haiyan
Yue, Youling
Qian, Lei
[J]. INTERNATIONAL JOURNAL OF MODERN PHYSICS D, 2011, 20 (06): : 989 - 1024
[19] Sandler M, 2019, Arxiv, DOI [arXiv:1801.04381, DOI 10.48550/ARXIV.1801.04381]
[20] Simonyan K., 2014, arXiv

← 1 2 3 4 →