Journal Article10.1088/1674-4527/accdc2
Pulsar Candidate Classification Using A Computer Vision Method Combining with Convolution and Attention
2
TL;DR: In this article , a new pulsar identification system that utilizes the CoAtNet to score two-dimensional features of candidates, uses a multilayer perceptron to score onedimensional features, and uses logistic regression to judge the scores above.
read more
Abstract:
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, uses a multilayer perceptron to score one-dimensional features, and uses logistic regression to judge the scores above. In the data preprocessing stage, we performed 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 and 98.85\% accuracy in our GPPS test set.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Dealing with the data imbalance problem on pulsar candidates sifting based on feature selection
Haitao Lin,Xiangru Li +1 more
TL;DR: An algorithm of feature selection called K-fold Relief-Greedy algorithm (KFRG) is designed and experiments verified that ML models based on KFRG are capable for PCS, correctly separating pulsars from non-pulsars even if the candidates are highly class-imbalanced.
1
Pulsar candidate identification using advanced transformer-based models
Jie Cao,Linhua Deng,Yuxia Liu +2 more
References
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
The five-hundred-meter aperture spherical radio telescope (fast) project
Rendong Nan,Di Li,Di Li,Chengjin Jin,Wang Qiming,Lichun Zhu,Wenbai Zhu,Haiyan Zhang,Youling Yue,Lei Qian +9 more
TL;DR: Wang et al. as discussed by the authors proposed the Five Hundred Meter Aperture Spherical Radio Telescope (FAST) to build the largest single-dish radio telescope in the world.
857
Fifty years of pulsar candidate selection: from simple filters to a new principled real-time classification approach
TL;DR: In this paper, the Gaussian Hellinger Very Fast Decision Tree (GH-VFDT) was used to select promising candidates using a purpose-built tree-based machine learning classifier.
The FAST Galactic Plane Pulsar Snapshot survey: I. Project design and pulsar discoveries ⋆
Jin-Lin Han,Chen Wang,Pengfei Wang,Tao Wang,D. J. Zhou,Jinghai Sun,Yi Yan,Wei-Qi Su,Wei-Cong Jing,Xue Chen,Gao Xingye,Li-Gang Hou,Jun Xu,Kejia Lee,Kejia Lee,Na Wang,Peng Jiang,Renxin Xu,Jun Yan,Heng-Qian Gan,Xin Guan,Wen-Jun Huang,Jinchen Jiang,Hui Li,Yun-Peng Men,Chun Sun,Bojun Wang,Hong-Guang Wang,Shuang-Qiang Wang,Jin-Tao Xie,Heng Xu,Rui Yao,Xiao-Peng You,Dongjun Yu,Jian-Ping Yuan,R. Yuen,Chunfeng Zhang,Yan Zhu +37 more
TL;DR: The GPPS survey as mentioned in this paper was designed to discover pulsars within the Galactic plane from the FAST L-band 19-beam receiver, and the results of the survey have been published.
144
SPINN: a straightforward machine learning solution to the pulsar candidate selection problem
TL;DR: SPINN (Straightforward Pulsar Identification using Neural Networks), a high-performance machine learning solution developed to process increasingly large data outputs from pulsar surveys, has been cross-validated on candidates from the southern High Time Resolution Universe (HTRU) survey and shown to identify every known pulsar found in the survey data while maintaining a false positive rate of 0.64 as mentioned in this paper.
102