Early-fusion Based Pulsar Identification with Smart Under-sampling

The discovery of pulsars is of great significance in the field of physics and astronomy. As the astronomical equipment produces a large amount of pulsar data, an algorithm for automatically identifying pulsars becomes urgent. We propose a deep learning framework for pulsar recognition. In response t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-07
Hauptverfasser: Zhang, ShiChuan, Kong, XiangCong, Zhou, YueYing, Chen, LingYao, Zheng, XiaoYing, Chun-Ling, Xu, Bao-Qiang Lao, An, Tao
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Zhang, ShiChuan
Kong, XiangCong
Zhou, YueYing
Chen, LingYao
Zheng, XiaoYing
Chun-Ling, Xu
Bao-Qiang Lao
An, Tao
description The discovery of pulsars is of great significance in the field of physics and astronomy. As the astronomical equipment produces a large amount of pulsar data, an algorithm for automatically identifying pulsars becomes urgent. We propose a deep learning framework for pulsar recognition. In response to the extreme imbalance between positive and negative examples and the hard negative sample issue presented in the HTRU Medlat Training Data,there are two coping strategies in our framework: the smart under-sampling and the improved loss function. We also apply the early-fusion strategy to integrate features obtained from different attributes before classification to improve the performance. To our best knowledge,this is the first study that integrates these strategies and techniques together in pulsar recognition. The experiment results show that our framework outperforms previous works with the respect to either the training time or F1 score. We can not only speed up the training time by 10X compared with the state-of-the-art work, but also get a competitive result in terms of F1 score.
doi_str_mv 10.48550/arxiv.2107.03071
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2107_03071</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2549840241</sourcerecordid><originalsourceid>FETCH-LOGICAL-a521-b1ae325390093ca523ea4c7a46321d186843fc61677e5bdb33af07f4fcc05ab33</originalsourceid><addsrcrecordid>eNotj1FLwzAUhYMgOOZ-gE8WfO68yU2a9tGNqYOBgvO53LaJZnRtTVp1_95u8-lwzzlczsfYDYe5TJWCe_K_7nsuOOg5IGh-wSYCkcepFOKKzULYAYBItFAKJ2yxIl8fYjsE1zbRgoKpotehDuSjdWWa3llXUn_Mflz_Gb3tyffRe1MZHwfad7VrPq7ZpaU6mNm_Ttn2cbVdPsebl6f18mETkxI8LjgZFAozgAzL0UJDstQkExS84mmSSrRlwhOtjSqqApEsaCttWYKi8Zyy2_PbE2DeeTduOeRH0PwEOjbuzo3Ot1-DCX2-awffjJtyoWSWShCS4x-L5lU8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2549840241</pqid></control><display><type>article</type><title>Early-fusion Based Pulsar Identification with Smart Under-sampling</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Zhang, ShiChuan ; Kong, XiangCong ; Zhou, YueYing ; Chen, LingYao ; Zheng, XiaoYing ; Chun-Ling, Xu ; Bao-Qiang Lao ; An, Tao</creator><creatorcontrib>Zhang, ShiChuan ; Kong, XiangCong ; Zhou, YueYing ; Chen, LingYao ; Zheng, XiaoYing ; Chun-Ling, Xu ; Bao-Qiang Lao ; An, Tao</creatorcontrib><description>The discovery of pulsars is of great significance in the field of physics and astronomy. As the astronomical equipment produces a large amount of pulsar data, an algorithm for automatically identifying pulsars becomes urgent. We propose a deep learning framework for pulsar recognition. In response to the extreme imbalance between positive and negative examples and the hard negative sample issue presented in the HTRU Medlat Training Data,there are two coping strategies in our framework: the smart under-sampling and the improved loss function. We also apply the early-fusion strategy to integrate features obtained from different attributes before classification to improve the performance. To our best knowledge,this is the first study that integrates these strategies and techniques together in pulsar recognition. The experiment results show that our framework outperforms previous works with the respect to either the training time or F1 score. We can not only speed up the training time by 10X compared with the state-of-the-art work, but also get a competitive result in terms of F1 score.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2107.03071</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Astronomy ; Machine learning ; Physics - Instrumentation and Methods for Astrophysics ; Pulsars ; Recognition ; Sampling ; Training</subject><ispartof>arXiv.org, 2021-07</ispartof><rights>2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27925</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2107.03071$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1088/1674-4527/21/10/257$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Zhang, ShiChuan</creatorcontrib><creatorcontrib>Kong, XiangCong</creatorcontrib><creatorcontrib>Zhou, YueYing</creatorcontrib><creatorcontrib>Chen, LingYao</creatorcontrib><creatorcontrib>Zheng, XiaoYing</creatorcontrib><creatorcontrib>Chun-Ling, Xu</creatorcontrib><creatorcontrib>Bao-Qiang Lao</creatorcontrib><creatorcontrib>An, Tao</creatorcontrib><title>Early-fusion Based Pulsar Identification with Smart Under-sampling</title><title>arXiv.org</title><description>The discovery of pulsars is of great significance in the field of physics and astronomy. As the astronomical equipment produces a large amount of pulsar data, an algorithm for automatically identifying pulsars becomes urgent. We propose a deep learning framework for pulsar recognition. In response to the extreme imbalance between positive and negative examples and the hard negative sample issue presented in the HTRU Medlat Training Data,there are two coping strategies in our framework: the smart under-sampling and the improved loss function. We also apply the early-fusion strategy to integrate features obtained from different attributes before classification to improve the performance. To our best knowledge,this is the first study that integrates these strategies and techniques together in pulsar recognition. The experiment results show that our framework outperforms previous works with the respect to either the training time or F1 score. We can not only speed up the training time by 10X compared with the state-of-the-art work, but also get a competitive result in terms of F1 score.</description><subject>Algorithms</subject><subject>Astronomy</subject><subject>Machine learning</subject><subject>Physics - Instrumentation and Methods for Astrophysics</subject><subject>Pulsars</subject><subject>Recognition</subject><subject>Sampling</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj1FLwzAUhYMgOOZ-gE8WfO68yU2a9tGNqYOBgvO53LaJZnRtTVp1_95u8-lwzzlczsfYDYe5TJWCe_K_7nsuOOg5IGh-wSYCkcepFOKKzULYAYBItFAKJ2yxIl8fYjsE1zbRgoKpotehDuSjdWWa3llXUn_Mflz_Gb3tyffRe1MZHwfad7VrPq7ZpaU6mNm_Ttn2cbVdPsebl6f18mETkxI8LjgZFAozgAzL0UJDstQkExS84mmSSrRlwhOtjSqqApEsaCttWYKi8Zyy2_PbE2DeeTduOeRH0PwEOjbuzo3Ot1-DCX2-awffjJtyoWSWShCS4x-L5lU8</recordid><startdate>20210721</startdate><enddate>20210721</enddate><creator>Zhang, ShiChuan</creator><creator>Kong, XiangCong</creator><creator>Zhou, YueYing</creator><creator>Chen, LingYao</creator><creator>Zheng, XiaoYing</creator><creator>Chun-Ling, Xu</creator><creator>Bao-Qiang Lao</creator><creator>An, Tao</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>GOX</scope></search><sort><creationdate>20210721</creationdate><title>Early-fusion Based Pulsar Identification with Smart Under-sampling</title><author>Zhang, ShiChuan ; Kong, XiangCong ; Zhou, YueYing ; Chen, LingYao ; Zheng, XiaoYing ; Chun-Ling, Xu ; Bao-Qiang Lao ; An, Tao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a521-b1ae325390093ca523ea4c7a46321d186843fc61677e5bdb33af07f4fcc05ab33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Astronomy</topic><topic>Machine learning</topic><topic>Physics - Instrumentation and Methods for Astrophysics</topic><topic>Pulsars</topic><topic>Recognition</topic><topic>Sampling</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhang, ShiChuan</creatorcontrib><creatorcontrib>Kong, XiangCong</creatorcontrib><creatorcontrib>Zhou, YueYing</creatorcontrib><creatorcontrib>Chen, LingYao</creatorcontrib><creatorcontrib>Zheng, XiaoYing</creatorcontrib><creatorcontrib>Chun-Ling, Xu</creatorcontrib><creatorcontrib>Bao-Qiang Lao</creatorcontrib><creatorcontrib>An, Tao</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, ShiChuan</au><au>Kong, XiangCong</au><au>Zhou, YueYing</au><au>Chen, LingYao</au><au>Zheng, XiaoYing</au><au>Chun-Ling, Xu</au><au>Bao-Qiang Lao</au><au>An, Tao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Early-fusion Based Pulsar Identification with Smart Under-sampling</atitle><jtitle>arXiv.org</jtitle><date>2021-07-21</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>The discovery of pulsars is of great significance in the field of physics and astronomy. As the astronomical equipment produces a large amount of pulsar data, an algorithm for automatically identifying pulsars becomes urgent. We propose a deep learning framework for pulsar recognition. In response to the extreme imbalance between positive and negative examples and the hard negative sample issue presented in the HTRU Medlat Training Data,there are two coping strategies in our framework: the smart under-sampling and the improved loss function. We also apply the early-fusion strategy to integrate features obtained from different attributes before classification to improve the performance. To our best knowledge,this is the first study that integrates these strategies and techniques together in pulsar recognition. The experiment results show that our framework outperforms previous works with the respect to either the training time or F1 score. We can not only speed up the training time by 10X compared with the state-of-the-art work, but also get a competitive result in terms of F1 score.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2107.03071</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-07
issn 2331-8422
language eng
recordid cdi_arxiv_primary_2107_03071
source arXiv.org; Free E- Journals
subjects Algorithms
Astronomy
Machine learning
Physics - Instrumentation and Methods for Astrophysics
Pulsars
Recognition
Sampling
Training
title Early-fusion Based Pulsar Identification with Smart Under-sampling
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T00%3A15%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Early-fusion%20Based%20Pulsar%20Identification%20with%20Smart%20Under-sampling&rft.jtitle=arXiv.org&rft.au=Zhang,%20ShiChuan&rft.date=2021-07-21&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2107.03071&rft_dat=%3Cproquest_arxiv%3E2549840241%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2549840241&rft_id=info:pmid/&rfr_iscdi=true