Comparative Study of Neural Network Frameworks for the Next Generation of Adaptive Optics Systems
Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a t...
Gespeichert in:
| Veröffentlicht in: | Sensors (Basel, Switzerland) Switzerland), 2017-06, Vol.17 (6), p.1263 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 6 |
| container_start_page | 1263 |
| container_title | Sensors (Basel, Switzerland) |
| container_volume | 17 |
| creator | González-Gutiérrez, Carlos Santos, Jesús Daniel Martínez-Zarzuela, Mario Basden, Alistair G Osborn, James Díaz-Pernas, Francisco Javier De Cos Juez, Francisco Javier |
| description | Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a tomographic reconstructor based on a machine learning architecture named "CARMEN" are presented. Basic concepts of adaptive optics are introduced first, with a short explanation of three different control systems used on real telescopes and the sensors utilised. The operation of the reconstructor, along with the three neural network frameworks used, and the developed CUDA code are detailed. Changes to the size of the reconstructor influence the training and execution time of the neural network. The native CUDA code turns out to be the best choice for all the systems, although some of the other frameworks offer good performance under certain circumstances. |
| doi_str_mv | 10.3390/s17061263 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_5492298</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2108703667</sourcerecordid><originalsourceid>FETCH-LOGICAL-c403t-50ced15ff8c0555e3b774314d46d039db3b10abe80a659a556f624d1805404343</originalsourceid><addsrcrecordid>eNpdkU1Lw0AQhhdR_D74ByTgRQ_V2c8kF0GKVqHoQT0vm2Rio0227m7U_nu3Wot6egfmmXdmeAk5oHDKeQ5nnqagKFN8jWxTwcQgYwzWf9VbZMf7ZwDGOc82yRbLZCoEU9vEDG07M86E5g2T-9BX88TWyS32zkyjhHfrXpIrZ1pcVD6prUvCBGPrIyQj7HAxarvF0EVlZl82d1FKn9zPfcDW75GN2kw97i91lzxeXT4Mrwfju9HN8GI8KAXwMJBQYkVlXWclSCmRF2kqOBWVUBXwvCp4QcEUmIFRMjdSqloxUdEMpADBBd8l59--s75osSqxC_EHPXNNa9xcW9Pov52umegn-6alyBnLs2hwvDRw9rVHH3Tb-BKnU9Oh7b2mOciU53FrRI_-oc-2d118TzMKWQpcqTRSJ99U6az3DuvVMRT0Iji9Ci6yh7-vX5E_SfFPj7SS5g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2108703667</pqid></control><display><type>article</type><title>Comparative Study of Neural Network Frameworks for the Next Generation of Adaptive Optics Systems</title><source>DOAJ Directory of Open Access Journals</source><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><source>Free Full-Text Journals in Chemistry</source><creator>González-Gutiérrez, Carlos ; Santos, Jesús Daniel ; Martínez-Zarzuela, Mario ; Basden, Alistair G ; Osborn, James ; Díaz-Pernas, Francisco Javier ; De Cos Juez, Francisco Javier</creator><creatorcontrib>González-Gutiérrez, Carlos ; Santos, Jesús Daniel ; Martínez-Zarzuela, Mario ; Basden, Alistair G ; Osborn, James ; Díaz-Pernas, Francisco Javier ; De Cos Juez, Francisco Javier</creatorcontrib><description>Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a tomographic reconstructor based on a machine learning architecture named "CARMEN" are presented. Basic concepts of adaptive optics are introduced first, with a short explanation of three different control systems used on real telescopes and the sensors utilised. The operation of the reconstructor, along with the three neural network frameworks used, and the developed CUDA code are detailed. Changes to the size of the reconstructor influence the training and execution time of the neural network. The native CUDA code turns out to be the best choice for all the systems, although some of the other frameworks offer good performance under certain circumstances.</description><identifier>ISSN: 1424-8220</identifier><identifier>EISSN: 1424-8220</identifier><identifier>DOI: 10.3390/s17061263</identifier><identifier>PMID: 28574426</identifier><language>eng</language><publisher>Switzerland: MDPI AG</publisher><subject>Adaptive optics ; Adaptive systems ; Atmospheric correction ; Comparative studies ; Extremely large telescopes ; Neural networks ; Telescopes</subject><ispartof>Sensors (Basel, Switzerland), 2017-06, Vol.17 (6), p.1263</ispartof><rights>2017. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2017 by the authors. 2017</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c403t-50ced15ff8c0555e3b774314d46d039db3b10abe80a659a556f624d1805404343</citedby><cites>FETCH-LOGICAL-c403t-50ced15ff8c0555e3b774314d46d039db3b10abe80a659a556f624d1805404343</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC5492298/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC5492298/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,864,885,27924,27925,53791,53793</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/28574426$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>González-Gutiérrez, Carlos</creatorcontrib><creatorcontrib>Santos, Jesús Daniel</creatorcontrib><creatorcontrib>Martínez-Zarzuela, Mario</creatorcontrib><creatorcontrib>Basden, Alistair G</creatorcontrib><creatorcontrib>Osborn, James</creatorcontrib><creatorcontrib>Díaz-Pernas, Francisco Javier</creatorcontrib><creatorcontrib>De Cos Juez, Francisco Javier</creatorcontrib><title>Comparative Study of Neural Network Frameworks for the Next Generation of Adaptive Optics Systems</title><title>Sensors (Basel, Switzerland)</title><addtitle>Sensors (Basel)</addtitle><description>Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a tomographic reconstructor based on a machine learning architecture named "CARMEN" are presented. Basic concepts of adaptive optics are introduced first, with a short explanation of three different control systems used on real telescopes and the sensors utilised. The operation of the reconstructor, along with the three neural network frameworks used, and the developed CUDA code are detailed. Changes to the size of the reconstructor influence the training and execution time of the neural network. The native CUDA code turns out to be the best choice for all the systems, although some of the other frameworks offer good performance under certain circumstances.</description><subject>Adaptive optics</subject><subject>Adaptive systems</subject><subject>Atmospheric correction</subject><subject>Comparative studies</subject><subject>Extremely large telescopes</subject><subject>Neural networks</subject><subject>Telescopes</subject><issn>1424-8220</issn><issn>1424-8220</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpdkU1Lw0AQhhdR_D74ByTgRQ_V2c8kF0GKVqHoQT0vm2Rio0227m7U_nu3Wot6egfmmXdmeAk5oHDKeQ5nnqagKFN8jWxTwcQgYwzWf9VbZMf7ZwDGOc82yRbLZCoEU9vEDG07M86E5g2T-9BX88TWyS32zkyjhHfrXpIrZ1pcVD6prUvCBGPrIyQj7HAxarvF0EVlZl82d1FKn9zPfcDW75GN2kw97i91lzxeXT4Mrwfju9HN8GI8KAXwMJBQYkVlXWclSCmRF2kqOBWVUBXwvCp4QcEUmIFRMjdSqloxUdEMpADBBd8l59--s75osSqxC_EHPXNNa9xcW9Pov52umegn-6alyBnLs2hwvDRw9rVHH3Tb-BKnU9Oh7b2mOciU53FrRI_-oc-2d118TzMKWQpcqTRSJ99U6az3DuvVMRT0Iji9Ci6yh7-vX5E_SfFPj7SS5g</recordid><startdate>20170602</startdate><enddate>20170602</enddate><creator>González-Gutiérrez, Carlos</creator><creator>Santos, Jesús Daniel</creator><creator>Martínez-Zarzuela, Mario</creator><creator>Basden, Alistair G</creator><creator>Osborn, James</creator><creator>Díaz-Pernas, Francisco Javier</creator><creator>De Cos Juez, Francisco Javier</creator><general>MDPI AG</general><general>MDPI</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20170602</creationdate><title>Comparative Study of Neural Network Frameworks for the Next Generation of Adaptive Optics Systems</title><author>González-Gutiérrez, Carlos ; Santos, Jesús Daniel ; Martínez-Zarzuela, Mario ; Basden, Alistair G ; Osborn, James ; Díaz-Pernas, Francisco Javier ; De Cos Juez, Francisco Javier</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c403t-50ced15ff8c0555e3b774314d46d039db3b10abe80a659a556f624d1805404343</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Adaptive optics</topic><topic>Adaptive systems</topic><topic>Atmospheric correction</topic><topic>Comparative studies</topic><topic>Extremely large telescopes</topic><topic>Neural networks</topic><topic>Telescopes</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>González-Gutiérrez, Carlos</creatorcontrib><creatorcontrib>Santos, Jesús Daniel</creatorcontrib><creatorcontrib>Martínez-Zarzuela, Mario</creatorcontrib><creatorcontrib>Basden, Alistair G</creatorcontrib><creatorcontrib>Osborn, James</creatorcontrib><creatorcontrib>Díaz-Pernas, Francisco Javier</creatorcontrib><creatorcontrib>De Cos Juez, Francisco Javier</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Access via ProQuest (Open Access)</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>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Sensors (Basel, Switzerland)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>González-Gutiérrez, Carlos</au><au>Santos, Jesús Daniel</au><au>Martínez-Zarzuela, Mario</au><au>Basden, Alistair G</au><au>Osborn, James</au><au>Díaz-Pernas, Francisco Javier</au><au>De Cos Juez, Francisco Javier</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Comparative Study of Neural Network Frameworks for the Next Generation of Adaptive Optics Systems</atitle><jtitle>Sensors (Basel, Switzerland)</jtitle><addtitle>Sensors (Basel)</addtitle><date>2017-06-02</date><risdate>2017</risdate><volume>17</volume><issue>6</issue><spage>1263</spage><pages>1263-</pages><issn>1424-8220</issn><eissn>1424-8220</eissn><abstract>Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a tomographic reconstructor based on a machine learning architecture named "CARMEN" are presented. Basic concepts of adaptive optics are introduced first, with a short explanation of three different control systems used on real telescopes and the sensors utilised. The operation of the reconstructor, along with the three neural network frameworks used, and the developed CUDA code are detailed. Changes to the size of the reconstructor influence the training and execution time of the neural network. The native CUDA code turns out to be the best choice for all the systems, although some of the other frameworks offer good performance under certain circumstances.</abstract><cop>Switzerland</cop><pub>MDPI AG</pub><pmid>28574426</pmid><doi>10.3390/s17061263</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1424-8220 |
| ispartof | Sensors (Basel, Switzerland), 2017-06, Vol.17 (6), p.1263 |
| issn | 1424-8220 1424-8220 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_5492298 |
| source | DOAJ Directory of Open Access Journals; MDPI - Multidisciplinary Digital Publishing Institute; EZB-FREE-00999 freely available EZB journals; PubMed Central; Free Full-Text Journals in Chemistry |
| subjects | Adaptive optics Adaptive systems Atmospheric correction Comparative studies Extremely large telescopes Neural networks Telescopes |
| title | Comparative Study of Neural Network Frameworks for the Next Generation of Adaptive Optics Systems |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T12%3A42%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Comparative%20Study%20of%20Neural%20Network%20Frameworks%20for%20the%20Next%20Generation%20of%20Adaptive%20Optics%20Systems&rft.jtitle=Sensors%20(Basel,%20Switzerland)&rft.au=Gonz%C3%A1lez-Guti%C3%A9rrez,%20Carlos&rft.date=2017-06-02&rft.volume=17&rft.issue=6&rft.spage=1263&rft.pages=1263-&rft.issn=1424-8220&rft.eissn=1424-8220&rft_id=info:doi/10.3390/s17061263&rft_dat=%3Cproquest_pubme%3E2108703667%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2108703667&rft_id=info:pmid/28574426&rfr_iscdi=true |