基于深度卷积神经网络的脉冲星候选分类

Yuanchao Wang, Mingtao Li, Z. Pan, Jianhua Zheng
{"title":"基于深度卷积神经网络的脉冲星候选分类","authors":"Yuanchao Wang, Mingtao Li, Z. Pan, Jianhua Zheng","doi":"10.1088/1674--4527/19/9/133","DOIUrl":null,"url":null,"abstract":"As performance of dedicated facilities continually improved, massive pulsar candidates are being received, which makes selecting valuable pulsar signals from candidates challenging. In this paper, we designed a deep convolutional neural network (CNN) with 11 layers for classifying pulsar candidates. Compared to artificial designed features, CNN chose sub-integrations plot and sub-bands plot in each candidate as inputs without carrying biases. To address the imbalanced problem, data augmentation method based on synthetic minority samples is proposed according to characteristics of pulsars. The maximum pulses of pulsar candidates were first translated to the same position, 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 the experiments on HTRU 1 dataset, it shows that this model can achieve recall as 0.962 while precision as 0.963.","PeriodicalId":8459,"journal":{"name":"arXiv: Instrumentation and Methods for Astrophysics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"20","resultStr":"{\"title\":\"Pulsar Candidates Classification with Deep Convolutional Neural Networks\",\"authors\":\"Yuanchao Wang, Mingtao Li, Z. Pan, Jianhua Zheng\",\"doi\":\"10.1088/1674--4527/19/9/133\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As performance of dedicated facilities continually improved, massive pulsar candidates are being received, which makes selecting valuable pulsar signals from candidates challenging. In this paper, we designed a deep convolutional neural network (CNN) with 11 layers for classifying pulsar candidates. Compared to artificial designed features, CNN chose sub-integrations plot and sub-bands plot in each candidate as inputs without carrying biases. To address the imbalanced problem, data augmentation method based on synthetic minority samples is proposed according to characteristics of pulsars. The maximum pulses of pulsar candidates were first translated to the same position, 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 the experiments on HTRU 1 dataset, it shows that this model can achieve recall as 0.962 while precision as 0.963.\",\"PeriodicalId\":8459,\"journal\":{\"name\":\"arXiv: Instrumentation and Methods for Astrophysics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"20\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv: Instrumentation and Methods for Astrophysics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1088/1674--4527/19/9/133\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv: Instrumentation and Methods for Astrophysics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1088/1674--4527/19/9/133","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 20

摘要

随着专用设备性能的不断提高,大量脉冲星候选者被接收,这使得从候选者中选择有价值的脉冲星信号变得具有挑战性。本文设计了一个11层的深度卷积神经网络(CNN)用于脉冲星候选分类。与人工设计的特征相比,CNN在每个候选特征中选择子积分图和子带图作为输入,不带偏差。为了解决不平衡问题,根据脉冲星的特点,提出了基于合成少数派样本的数据增强方法。首先将候选脉冲星的最大脉冲转换到同一位置,然后将多个脉冲星子图相加生成新样本。数据增强方法简单有效,可获得保持脉冲星特征的多样化、代表性样本。在HTRU 1数据集上的实验表明,该模型的查全率为0.962,查准率为0.963。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Pulsar Candidates Classification with Deep Convolutional Neural Networks
As performance of dedicated facilities continually improved, massive pulsar candidates are being received, which makes selecting valuable pulsar signals from candidates challenging. In this paper, we designed a deep convolutional neural network (CNN) with 11 layers for classifying pulsar candidates. Compared to artificial designed features, CNN chose sub-integrations plot and sub-bands plot in each candidate as inputs without carrying biases. To address the imbalanced problem, data augmentation method based on synthetic minority samples is proposed according to characteristics of pulsars. The maximum pulses of pulsar candidates were first translated to the same position, 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 the experiments on HTRU 1 dataset, it shows that this model can achieve recall as 0.962 while precision as 0.963.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Space-based weather observatory at Earth-Moon Lagrange point L1 to monitor earth's magnetotail effects on the Moon The Deep Neural Network based Photometry Framework for Wide Field Small Aperture Telescopes. The Largest Russian Optical Telescope BTA: Current Status and Modernization Prospects DRAGraces: A pipeline for the GRACES high-resolution spectrograph at Gemini. Overview and reassessment of noise budget of starshade exoplanet imaging
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1