Characterization of climatological time series using autoencoders

Descripción del Articulo

Common problems in climatological time series data are high dimensionality, correlation between the sequential values and noise due to calibration of meteorological stations influencing dramatically in the quality of clustering, classification, climate pattern finding and data processing. One way to...

Descripción completa

Detalles Bibliográficos
Autores: Alfonte Zapana, Reynaldo, López Del Alamo, Cristian, Llerena Quenaya, Jan Franco, Cuadros Valdivia, Ana María
Formato: artículo
Fecha de Publicación:2017
Institución:Universidad La Salle
Repositorio:ULASALLE-Institucional
Lenguaje:inglés
OAI Identifier:oai:repositorio.ulasalle.edu.pe:20.500.12953/29
Enlace del recurso:http://repositorio.ulasalle.edu.pe/handle/20.500.12953/29
Nivel de acceso:acceso restringido
Materia:Research Subject Categories::TECHNOLOGY
id ULSA_d05ad032fb8f8274b7d28e8b6042dc41
oai_identifier_str oai:repositorio.ulasalle.edu.pe:20.500.12953/29
network_acronym_str ULSA
network_name_str ULASALLE-Institucional
repository_id_str 3920
dc.title.es_ES.fl_str_mv Characterization of climatological time series using autoencoders
title Characterization of climatological time series using autoencoders
spellingShingle Characterization of climatological time series using autoencoders
Alfonte Zapana, Reynaldo
Research Subject Categories::TECHNOLOGY
Research Subject Categories::TECHNOLOGY
title_short Characterization of climatological time series using autoencoders
title_full Characterization of climatological time series using autoencoders
title_fullStr Characterization of climatological time series using autoencoders
title_full_unstemmed Characterization of climatological time series using autoencoders
title_sort Characterization of climatological time series using autoencoders
author Alfonte Zapana, Reynaldo
author_facet Alfonte Zapana, Reynaldo
López Del Alamo, Cristian
Llerena Quenaya, Jan Franco
Cuadros Valdivia, Ana María
author_role author
author2 López Del Alamo, Cristian
Llerena Quenaya, Jan Franco
Cuadros Valdivia, Ana María
author2_role author
author
author
dc.contributor.author.fl_str_mv Alfonte Zapana, Reynaldo
López Del Alamo, Cristian
Llerena Quenaya, Jan Franco
Cuadros Valdivia, Ana María
dc.subject.es_ES.fl_str_mv Research Subject Categories::TECHNOLOGY
topic Research Subject Categories::TECHNOLOGY
Research Subject Categories::TECHNOLOGY
dc.subject.ocde.es_ES.fl_str_mv Research Subject Categories::TECHNOLOGY
description Common problems in climatological time series data are high dimensionality, correlation between the sequential values and noise due to calibration of meteorological stations influencing dramatically in the quality of clustering, classification, climate pattern finding and data processing. One way to deal with this problem is through feature extraction technique. In order to extract features from large climatological time series data, we propose a feature extraction method based on autoencoder neural network (AUTOE). As a first step, time series is standardized. Then, different architectures of autoencoder is applied on it to reduce dimensionality. Finally, k-means clustering algorithm are used to evaluate them through quality measures. As a result, autoencoder performs well and is competitive with other feature extraction techniques over Synthetic Control Chart Time Series.
publishDate 2017
dc.date.accessioned.none.fl_str_mv 2018-11-21T17:09:28Z
dc.date.available.none.fl_str_mv 2018-11-21T17:09:28Z
dc.date.issued.fl_str_mv 2017-11-08
dc.type.es_ES.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.citation.es_ES.fl_str_mv @INPROCEEDINGS{8285717, author={R. A. Zapana and C. Lopez del Alamo and J. F. L. Quenaya and A. M. C. Valdivia}, booktitle={2017 IEEE Latin American Conference on Computational Intelligence (LA-CCI)}, title={Characterization of climatological time series using autoencoders}, year={2017}, volume={}, number={}, pages={1-6}, keywords={climatology;control charts;feature extraction;geophysics computing;meteorology;neural nets;pattern clustering;time series;common problems;climatological time series data;high dimensionality;climate pattern;data processing;feature extraction technique;feature extraction method;autoencoder neural network;Synthetic Control Chart Time Series;autoencoders;AUTOE;Time series analysis;Feature extraction;Discrete wavelet transforms;Discrete cosine transforms;Dimensionality reduction;Meteorology;Dimensionality reduction;autoencoder;time series}, doi={10.1109/LA-CCI.2017.8285717}, ISSN={}, month={Nov},}
dc.identifier.isbn.none.fl_str_mv 978-1-5386-3734-0
dc.identifier.uri.none.fl_str_mv http://repositorio.ulasalle.edu.pe/handle/20.500.12953/29
dc.identifier.journal.es_ES.fl_str_mv 2017 IEEE Latin American Conference on Computational Intelligence (LA-CCI)
dc.identifier.doi.es_ES.fl_str_mv 10.1109/LA-CCI.2017.8285717
identifier_str_mv @INPROCEEDINGS{8285717, author={R. A. Zapana and C. Lopez del Alamo and J. F. L. Quenaya and A. M. C. Valdivia}, booktitle={2017 IEEE Latin American Conference on Computational Intelligence (LA-CCI)}, title={Characterization of climatological time series using autoencoders}, year={2017}, volume={}, number={}, pages={1-6}, keywords={climatology;control charts;feature extraction;geophysics computing;meteorology;neural nets;pattern clustering;time series;common problems;climatological time series data;high dimensionality;climate pattern;data processing;feature extraction technique;feature extraction method;autoencoder neural network;Synthetic Control Chart Time Series;autoencoders;AUTOE;Time series analysis;Feature extraction;Discrete wavelet transforms;Discrete cosine transforms;Dimensionality reduction;Meteorology;Dimensionality reduction;autoencoder;time series}, doi={10.1109/LA-CCI.2017.8285717}, ISSN={}, month={Nov},}
978-1-5386-3734-0
2017 IEEE Latin American Conference on Computational Intelligence (LA-CCI)
10.1109/LA-CCI.2017.8285717
url http://repositorio.ulasalle.edu.pe/handle/20.500.12953/29
dc.language.iso.eng_US.fl_str_mv eng
language eng
dc.rights.es_ES.fl_str_mv info:eu-repo/semantics/restrictedAccess
eu_rights_str_mv restrictedAccess
dc.publisher.es_ES.fl_str_mv Universidad La Salle
dc.source.es_ES.fl_str_mv Universidad La Salle
Repositorio institucional - ULASALLE
dc.source.none.fl_str_mv reponame:ULASALLE-Institucional
instname:Universidad La Salle
instacron:ULASALLE
instname_str Universidad La Salle
instacron_str ULASALLE
institution ULASALLE
reponame_str ULASALLE-Institucional
collection ULASALLE-Institucional
bitstream.url.fl_str_mv http://repositorio.ulasalle.edu.pe/bitstream/20.500.12953/29/1/link_articulo.txt
http://repositorio.ulasalle.edu.pe/bitstream/20.500.12953/29/2/license.txt
http://repositorio.ulasalle.edu.pe/bitstream/20.500.12953/29/3/link_articulo.txt.txt
bitstream.checksum.fl_str_mv d8f83f401daa19fb8d691f44a0e197ac
8a4605be74aa9ea9d79846c1fba20a33
ff7e1448e009c4bcbdbb6665899403b2
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
repository.name.fl_str_mv Repositorio Institucional de la Universidad La Salle
repository.mail.fl_str_mv repositorio@ulasalle.edu.pe
_version_ 1764532734512857088
spelling Alfonte Zapana, ReynaldoLópez Del Alamo, CristianLlerena Quenaya, Jan FrancoCuadros Valdivia, Ana María2018-11-21T17:09:28Z2018-11-21T17:09:28Z2017-11-08@INPROCEEDINGS{8285717, author={R. A. Zapana and C. Lopez del Alamo and J. F. L. Quenaya and A. M. C. Valdivia}, booktitle={2017 IEEE Latin American Conference on Computational Intelligence (LA-CCI)}, title={Characterization of climatological time series using autoencoders}, year={2017}, volume={}, number={}, pages={1-6}, keywords={climatology;control charts;feature extraction;geophysics computing;meteorology;neural nets;pattern clustering;time series;common problems;climatological time series data;high dimensionality;climate pattern;data processing;feature extraction technique;feature extraction method;autoencoder neural network;Synthetic Control Chart Time Series;autoencoders;AUTOE;Time series analysis;Feature extraction;Discrete wavelet transforms;Discrete cosine transforms;Dimensionality reduction;Meteorology;Dimensionality reduction;autoencoder;time series}, doi={10.1109/LA-CCI.2017.8285717}, ISSN={}, month={Nov},}978-1-5386-3734-0http://repositorio.ulasalle.edu.pe/handle/20.500.12953/292017 IEEE Latin American Conference on Computational Intelligence (LA-CCI)10.1109/LA-CCI.2017.8285717Common problems in climatological time series data are high dimensionality, correlation between the sequential values and noise due to calibration of meteorological stations influencing dramatically in the quality of clustering, classification, climate pattern finding and data processing. One way to deal with this problem is through feature extraction technique. In order to extract features from large climatological time series data, we propose a feature extraction method based on autoencoder neural network (AUTOE). As a first step, time series is standardized. Then, different architectures of autoencoder is applied on it to reduce dimensionality. Finally, k-means clustering algorithm are used to evaluate them through quality measures. As a result, autoencoder performs well and is competitive with other feature extraction techniques over Synthetic Control Chart Time Series.Trabajo de investigaciónDoble ciegoengUniversidad La Salleinfo:eu-repo/semantics/restrictedAccessUniversidad La SalleRepositorio institucional - ULASALLEreponame:ULASALLE-Institucionalinstname:Universidad La Salleinstacron:ULASALLEResearch Subject Categories::TECHNOLOGYResearch Subject Categories::TECHNOLOGYCharacterization of climatological time series using autoencodersinfo:eu-repo/semantics/articleORIGINALlink_articulo.txtlink_articulo.txttext/plain45http://repositorio.ulasalle.edu.pe/bitstream/20.500.12953/29/1/link_articulo.txtd8f83f401daa19fb8d691f44a0e197acMD51LICENSElicense.txtlicense.txttext/plain; charset=utf-81748http://repositorio.ulasalle.edu.pe/bitstream/20.500.12953/29/2/license.txt8a4605be74aa9ea9d79846c1fba20a33MD52TEXTlink_articulo.txt.txtlink_articulo.txt.txtExtracted texttext/plain45http://repositorio.ulasalle.edu.pe/bitstream/20.500.12953/29/3/link_articulo.txt.txtff7e1448e009c4bcbdbb6665899403b2MD5320.500.12953/29oai:repositorio.ulasalle.edu.pe:20.500.12953/292021-06-11 14:39:34.132Repositorio Institucional de la Universidad La Sallerepositorio@ulasalle.edu.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
score 13.971837
Characterization of climatological time series using autoencoders
Nota importante:
La información contenida en este registro es de entera responsabilidad de la institución que gestiona el repositorio institucional donde esta contenido este documento o set de datos. El CONCYTEC no se hace responsable por los contenidos (publicaciones y/o datos) accesibles a través del Repositorio Nacional Digital de Ciencia, Tecnología e Innovación de Acceso Abierto (ALICIA).

Ejemplares Similares