Recovering historical climate records using artificial neural networks in GPU
Resumen:
This article presents a parallel implementation of Artificial Neural Networks over Graphic Processing Units, and its application for recovering his-torical climate records from the Digi-Clima project. Several strategies are intro-duced to handle large volumes of historical pluviometer records, and the paral-lel deployment is described. The experimental evaluation demonstrates that the proposed approach is useful for recovering the climate information, achieving classification rates up to 76% for a set of real images from the Digi-Clima pro-ject. The parallel algorithm allows reducing the execution times, with an accel-eration factor of up to 2.15×.
| 2014 | |
|
Artificial neural networks Image processing Climate records GPU |
|
| Inglés | |
| Universidad de la República | |
| COLIBRI | |
| http://hdl.handle.net/20.500.12008/5169 | |
| Acceso abierto | |
| Licencia Creative Commons Atribución – No Comercial – Sin Derivadas (CC BY-NC-ND 4.0) |
| _version_ | 1807522945358102528 |
|---|---|
| author | Balarini, Juan Pablo |
| author2 | Nesmachnow, Sergio |
| author2_role | author |
| author_facet | Balarini, Juan Pablo Nesmachnow, Sergio |
| author_role | author |
| bitstream.checksum.fl_str_mv | 6429389a7df7277b72b7924fdc7d47a9 4afdbb8c545fd630ea7db775da747b2f ae2fe251842ade1134c5d9bb99b6eefe d41d8cd98f00b204e9800998ecf8427e c4bd7c444ed7abd5ef5ff2c39d5ecedc |
| bitstream.checksumAlgorithm.fl_str_mv | MD5 MD5 MD5 MD5 MD5 |
| bitstream.url.fl_str_mv | http://localhost:8080/xmlui/bitstream/20.500.12008/5169/5/license.txt http://localhost:8080/xmlui/bitstream/20.500.12008/5169/2/license_url http://localhost:8080/xmlui/bitstream/20.500.12008/5169/3/license_text http://localhost:8080/xmlui/bitstream/20.500.12008/5169/4/license_rdf http://localhost:8080/xmlui/bitstream/20.500.12008/5169/1/TR1409.pdf |
| collection | COLIBRI |
| dc.contributor.filiacion.es.fl_str_mv | Balarini Juan Pablo, Universidad de la República (Uruguay). Facultad de Ingenieria. Nesmachnow Sergio, Universidad de la República (Uruguay). Facultad de Ingenieria. |
| dc.creator.none.fl_str_mv | Balarini, Juan Pablo Nesmachnow, Sergio |
| dc.date.accessioned.none.fl_str_mv | 2015-12-14T12:42:56Z |
| dc.date.available.none.fl_str_mv | 2015-12-14T12:42:56Z |
| dc.date.issued.none.fl_str_mv | 2014 |
| dc.description.abstract.none.fl_txt_mv | This article presents a parallel implementation of Artificial Neural Networks over Graphic Processing Units, and its application for recovering his-torical climate records from the Digi-Clima project. Several strategies are intro-duced to handle large volumes of historical pluviometer records, and the paral-lel deployment is described. The experimental evaluation demonstrates that the proposed approach is useful for recovering the climate information, achieving classification rates up to 76% for a set of real images from the Digi-Clima pro-ject. The parallel algorithm allows reducing the execution times, with an accel-eration factor of up to 2.15×. |
| dc.format.extent.es.fl_str_mv | 12 p. |
| dc.format.mimetype.none.fl_str_mv | aplication/pdf |
| dc.identifier.citation.es.fl_str_mv | BALARINI, J., NESMACHNOW, S. "Recovering historical climate records using artificial neural networks in GPU". Montevideo : UR.FI-INCO, 2014. Reportes Técnicos 14-09. |
| dc.identifier.issn.none.fl_str_mv | 07976410 |
| dc.identifier.uri.none.fl_str_mv | http://hdl.handle.net/20.500.12008/5169 |
| dc.language.iso.none.fl_str_mv | en eng |
| dc.publisher.es.fl_str_mv | UR.FI-INCO |
| dc.relation.ispartof.es.fl_str_mv | Reportes Técnicos 14-09 |
| dc.rights.license.none.fl_str_mv | Licencia Creative Commons Atribución – No Comercial – Sin Derivadas (CC BY-NC-ND 4.0) |
| dc.rights.none.fl_str_mv | info:eu-repo/semantics/openAccess |
| dc.source.none.fl_str_mv | reponame:COLIBRI instname:Universidad de la República instacron:Universidad de la República |
| dc.subject.es.fl_str_mv | Artificial neural networks Image processing Climate records GPU |
| dc.title.none.fl_str_mv | Recovering historical climate records using artificial neural networks in GPU |
| dc.type.es.fl_str_mv | Reporte técnico |
| dc.type.none.fl_str_mv | info:eu-repo/semantics/report |
| dc.type.version.none.fl_str_mv | info:eu-repo/semantics/publishedVersion |
| description | This article presents a parallel implementation of Artificial Neural Networks over Graphic Processing Units, and its application for recovering his-torical climate records from the Digi-Clima project. Several strategies are intro-duced to handle large volumes of historical pluviometer records, and the paral-lel deployment is described. The experimental evaluation demonstrates that the proposed approach is useful for recovering the climate information, achieving classification rates up to 76% for a set of real images from the Digi-Clima pro-ject. The parallel algorithm allows reducing the execution times, with an accel-eration factor of up to 2.15×. |
| eu_rights_str_mv | openAccess |
| format | report |
| id | COLIBRI_9da4dca56bc09f60904e42585cdc3b30 |
| identifier_str_mv | BALARINI, J., NESMACHNOW, S. "Recovering historical climate records using artificial neural networks in GPU". Montevideo : UR.FI-INCO, 2014. Reportes Técnicos 14-09. 07976410 |
| instacron_str | Universidad de la República |
| institution | Universidad de la República |
| instname_str | Universidad de la República |
| language | eng |
| language_invalid_str_mv | en |
| network_acronym_str | COLIBRI |
| network_name_str | COLIBRI |
| oai_identifier_str | oai:colibri.udelar.edu.uy:20.500.12008/5169 |
| publishDate | 2014 |
| reponame_str | COLIBRI |
| repository.mail.fl_str_mv | mabel.seroubian@seciu.edu.uy |
| repository.name.fl_str_mv | COLIBRI - Universidad de la República |
| repository_id_str | 4771 |
| rights_invalid_str_mv | Licencia Creative Commons Atribución – No Comercial – Sin Derivadas (CC BY-NC-ND 4.0) |
| spelling | Balarini Juan Pablo, Universidad de la República (Uruguay). Facultad de Ingenieria.Nesmachnow Sergio, Universidad de la República (Uruguay). Facultad de Ingenieria.2015-12-14T12:42:56Z2015-12-14T12:42:56Z2014BALARINI, J., NESMACHNOW, S. "Recovering historical climate records using artificial neural networks in GPU". Montevideo : UR.FI-INCO, 2014. Reportes Técnicos 14-09.07976410http://hdl.handle.net/20.500.12008/5169This article presents a parallel implementation of Artificial Neural Networks over Graphic Processing Units, and its application for recovering his-torical climate records from the Digi-Clima project. Several strategies are intro-duced to handle large volumes of historical pluviometer records, and the paral-lel deployment is described. The experimental evaluation demonstrates that the proposed approach is useful for recovering the climate information, achieving classification rates up to 76% for a set of real images from the Digi-Clima pro-ject. The parallel algorithm allows reducing the execution times, with an accel-eration factor of up to 2.15×.Submitted by Luna Fabiana (fabiana.luna@seciu.edu.uy) on 2015-12-14T12:42:56Z No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) TR1409.pdf: 468996 bytes, checksum: c4bd7c444ed7abd5ef5ff2c39d5ecedc (MD5)Made available in DSpace on 2015-12-14T12:42:56Z (GMT). No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) TR1409.pdf: 468996 bytes, checksum: c4bd7c444ed7abd5ef5ff2c39d5ecedc (MD5) Previous issue date: 201412 p.aplication/pdfenengUR.FI-INCOReportes Técnicos 14-09Las obras depositadas en el Repositorio se rigen por la Ordenanza de los Derechos de la Propiedad Intelectual de la Universidad de la República.(Res. Nº 91 de C.D.C. de 8/III/1994 – D.O. 7/IV/1994) y por la Ordenanza del Repositorio Abierto de la Universidad de la República (Res. Nº 16 de C.D.C. de 07/10/2014)info:eu-repo/semantics/openAccessLicencia Creative Commons Atribución – No Comercial – Sin Derivadas (CC BY-NC-ND 4.0)Artificial neural networksImage processingClimate recordsGPURecovering historical climate records using artificial neural networks in GPUReporte técnicoinfo:eu-repo/semantics/reportinfo:eu-repo/semantics/publishedVersionreponame:COLIBRIinstname:Universidad de la Repúblicainstacron:Universidad de la RepúblicaBalarini, Juan PabloNesmachnow, SergioLICENSElicense.txtlicense.txttext/plain; charset=utf-84267http://localhost:8080/xmlui/bitstream/20.500.12008/5169/5/license.txt6429389a7df7277b72b7924fdc7d47a9MD55CC-LICENSElicense_urllicense_urltext/plain; charset=utf-849http://localhost:8080/xmlui/bitstream/20.500.12008/5169/2/license_url4afdbb8c545fd630ea7db775da747b2fMD52license_textlicense_texttext/html; charset=utf-821468http://localhost:8080/xmlui/bitstream/20.500.12008/5169/3/license_textae2fe251842ade1134c5d9bb99b6eefeMD53license_rdflicense_rdfapplication/rdf+xml; charset=utf-80http://localhost:8080/xmlui/bitstream/20.500.12008/5169/4/license_rdfd41d8cd98f00b204e9800998ecf8427eMD54ORIGINALTR1409.pdfTR1409.pdfapplication/pdf468996http://localhost:8080/xmlui/bitstream/20.500.12008/5169/1/TR1409.pdfc4bd7c444ed7abd5ef5ff2c39d5ecedcMD5120.500.12008/51692016-06-16 15:12:26.389oai:colibri.udelar.edu.uy:20.500.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Universidadhttps://udelar.edu.uy/https://www.colibri.udelar.edu.uy/oai/requestmabel.seroubian@seciu.edu.uyUruguayopendoar:47712024-07-25T14:34:02.298992COLIBRI - Universidad de la Repúblicafalse |
| spellingShingle | Recovering historical climate records using artificial neural networks in GPU Balarini, Juan Pablo Artificial neural networks Image processing Climate records GPU |
| status_str | publishedVersion |
| title | Recovering historical climate records using artificial neural networks in GPU |
| title_full | Recovering historical climate records using artificial neural networks in GPU |
| title_fullStr | Recovering historical climate records using artificial neural networks in GPU |
| title_full_unstemmed | Recovering historical climate records using artificial neural networks in GPU |
| title_short | Recovering historical climate records using artificial neural networks in GPU |
| title_sort | Recovering historical climate records using artificial neural networks in GPU |
| topic | Artificial neural networks Image processing Climate records GPU |
| url | http://hdl.handle.net/20.500.12008/5169 |
