013false100true score desc 2gaptrue5mapcontentxmltrue50object_type_i,object_type_i_lookup,coverage_period_mt,geographic_area_mt,geographic_coordinates_mt,author_role_mt,contributor_role_mt,org_id_mt,org_role_mt,supervisor_mt,supervisor_id_mi,supervisor_id_mi_lookup,fields_of_research_mi,fields_of_research_mi_lookup,display_type_i,display_type_i_lookup,seo_code_mi,seo_code_mi_lookup,copyright_i,license_i,license_i_lookup,oa_compliance_t,oa_notes_t,grant_id_t,funding_body_t,description_of_resource_t,software_required_t,project_description_t,keywords_mt,project_name_t,project_id_t,isdatasetof_mt,isdatasetof_mt_lookup,notes_t,date_dt,xsd_display_option_mi,xsd_display_option_mi_lookup,file_downloads_i,created_date_dt,updated_date_dt,research_program_mt,title_t,depositor_i,isderivationof_mt,assigned_user_id_mt,assigned_group_id_mi,assigned_group_id_mi_lookup,isdatacomponentof_mt,isannotationof_mt,author_id_mi,author_id_mi_lookup,alternative_title_mt,pid_t,publisher_t,author_mt,contributor_mt,contributor_id_mi,contributor_id_mi_lookup,refereed_i,series_t,journal_name_t,newspaper_t,conference_name_t,book_title_t,identifier_mt,edition_t,subject_mi,subject_mi_lookup,place_of_publication_t,start_page_t,end_page_t,chapter_number_t,issue_number_t,volume_number_t,conference_dates_t,conference_location_t,patent_number_t,country_of_issue_t,description_t,date_available_dt,language_mt,phonetic_title_t,language_of_title_mt,translated_title_t,phonetic_journal_name_t,translated_journal_name_t,phonetic_book_title_t,translated_book_title_t,phonetic_newspaper_t,file_attachment_name_mt,translated_newspaper_t,phonetic_conference_name_t,translated_conference_name_t,issn_mt,isbn_mt,isi_loc_t,prn_t,output_availability_t,na_explanation_t,sensitivity_explanation_t,file_attachment_content_mt,org_unit_name_t,org_name_t,report_number_t,sequence_i,genre_t,genre_type_t,formatted_title_t,formatted_abstract_t,parent_publication_t,convener_t,ismemberof_mt,ismemberof_mt_lookup,link_mt,link_description_mt,rights_t,views_i,scopus_id_t,thomson_citation_count_i,gs_citation_count_i,gs_cited_by_link_t,scopus_citation_count_i,status_i,status_i_lookup,first_author_in_document_derived_t,first_author_in_fez_derived_t,ands_collection_type_t,start_date_dt,end_date_dt,access_conditions_t,extent_t,contact_details_email_mt,contact_details_physical_mt,loc_subject_heading_mt,depositor_affiliation_i,surrounding_features_mt,condition_mt,style_mt,period_mt,category_mt,subcategory_mt,structural_systems_mt,adt_id_t,subtype_t,language_of_parent_title_t,proceedings_title_t,file_description_mt,herdc_code_i,herdc_code_i_lookup,herdc_status_i,herdc_status_i_lookup,institutional_status_i,institutional_status_i_lookup,herdc_notes_t,follow_up_flags_i,follow_up_flags_i_lookup,follow_up_flags_imu_i,follow_up_flags_imu_i_lookup,scopus_doc_type_t,scopus_doc_type_t_lookup,wok_doc_type_t,wok_doc_type_t_lookup,conference_id_i,total_chapters_t,publisher_id_i,translated_proceedings_title_t,native_script_title_t,roman_script_title_t,native_script_book_title_t,roman_script_book_title_t,native_script_journal_name_t,roman_script_journal_name_t,native_script_conference_name_t,roman_script_conference_name_t,total_pages_t,native_script_proceedings_title_t,roman_script_proceedings_title_t,language_of_book_title_mt,language_of_journal_name_mt,language_of_proceedings_title_mt,doi_t,author_count_t,collection_year_dt,location_mt,building_materials_mt,architectural_features_mt,interior_features_mt,sherpa_colour_t,ain_detail_t,rj_2010_rank_t,rj_2010_title_t,rj_2012_rank_t,rj_2012_title_t,rc_2010_rank_t,rc_2010_title_t,herdc_code_description_t,score,citation_t1true60 (label AND status_i:(2)) 6display_type_idisplay_type_i_lookup_exactkeywords_mftdate_year_tauthor_id_miauthor_id_mi_lookup_exactauthor_mftjournal_name_t_ftsubject_misubject_mi_lookup_exactgenre_type_t_ftismemberof_mftismemberof_mt_lookup_exactsubtype_t_ftscopus_doc_type_t_ftscopus_doc_type_t_lookup_exact(_authlister_t:(1)) AND (status_i:(2)) 31982014-10-28T00:00:00Z1052016-10-31T21:43:35Z2016-10-31T21:43:35ZArterial Spin Labeling en epilepsiabibliuned:master-Ciencias-FMed-MbotellerEn el presente trabajo se utilizan imágenes funcionales de Resonancia Magnética, Arterial Spin Labeling, para estudiar la perfusión sanguínea cerebral en un grupo de pacientes epilépticos respecto a un grupo control. Para calibrar y normalizar estas imágenes se dispone de otras de tipo estructural (T1) que ofrecen información morfológica. El resultado permite con un análisis two sample t-test mostrar mapas con regiones de hiper e hipoperfusión de cada paciente respecto a la perfusión media del grupo control.0Doctoral Thesis5562<a class="citation_author_name" title="Navegar por nombre de Autor de Boteller Mas, Marta" href="/fez/list/author/Boteller Mas, Marta/">Boteller Mas, Marta</a>. (<span class="citation_date">2014</span>). <i><a class="citation_title" title="Click para ver : Arterial Spin Labeling en epilepsia" href="/fez/view/bibliuned:master-Ciencias-FMed-Mboteller">Arterial Spin Labeling en epilepsia</a></i> Master Thesis, <span class="citation_publisher">Universidad Nacional de Educación a Distancia (España). Facultad de Ciencias.</span>Recordmaster TesisPublishedFísicaUniversidad Nacional de Educación a Distancia (España). Facultad de Ciencias.Boteller Mas, MartaSanta Marta Pastrana, Cristinabibliuned:master-Ciencias-FMed-Mbotellerhttp://e-spacio.uned.es/fez/view/bibliuned:master-Ciencias-FMed-MbotellerspaBoteller_Mas_Marta_TCI.pdfpresmd_Boteller_Mas_Marta_TCI.xmlbibliuned:master-Ciencias-FMedbibliuned:Settrabajosfindemasterbibliuned:SetopenaireMáster Universitario en Física Médica (UNED)Set de items trabajo fin de másterSet de openaireBoteller MasAcceso abierto1.159715934232014-01-01T00:00:00Z5612014-05-29T23:19:27ZEl derecho de información del consumidor ecologista. Etiquetas ecológicas y procedimiento EMAS III = The right to information environmentalist consumer. Environmental labels and EMAS III procedurebibliuned:REDUE-2014-26-60600Doctoral Thesis8602<a class="citation_author_name" title="Browse by Author Name for Cutini, Angelica" href="/fez/list/author/Cutini, Angelica/">Cutini, Angelica</a> . (<span class="citation_date">2014</span>) <a class="citation_title" title="Click to view : El derecho de información del consumidor ecologista. Etiquetas ecológicas y procedimiento EMAS III = The right to information environmentalist consumer. Environmental labels and EMAS III procedure" href="/fez/view/bibliuned:REDUE-2014-26-6060">El derecho de información del consumidor ecologista. Etiquetas ecológicas y procedimiento EMAS III = The right to information environmentalist consumer. Environmental labels and EMAS III procedure</a>. RecordArtículo de revistaPublishedhttp://udcdata.info/021523DerechoUniversidad Nacional de Educación a Distancia (España). Facultad de DerechoCutini, Angelicahttp://e-spacio.uned.es/fez/view/bibliuned:REDUE-2014-26-6060bibliuned:REDUE-2014-26-6060esDocumento.pdfbibliuned:REDUE-2014-26bibliuned:Setopenairebibliuned:SetarticuloRevista de derecho de la Unión Europea (REDUE). Año 2014, primer semestre, n. 26Set de openaireSet de artículoCutiniAcceso abierto1.020350834232022-09-19T00:00:00Z32024-02-29T07:23:47Z2024-02-29T07:23:47ZStreet images classification according to COVID-19 risk in Lima, Peru: a convolutional neural networks feasibility analysisbibliuned:557-Jmcastillo-0011Objectives During the COVID-19 pandemic, convolutional neural networks (CNNs) have been used in clinical medicine (eg, X-rays classification). Whether CNNs could inform the epidemiology of COVID-19 classifying street images according to COVID-19 risk is unknown, yet it could pinpoint high-risk places and relevant features of the built environment. In a feasibility study, we trained CNNs to classify the area surrounding bus stops (Lima, Peru) into moderate or extreme COVID-19 risk. Design CNN analysis based on images from bus stops and the surrounding area. We used transfer learning and updated the output layer of five CNNs: NASNetLarge, InceptionResNetV2, Xception, ResNet152V2 and ResNet101V2. We chose the best performing CNN, which was further tuned. We used GradCam to understand the classification process. Setting Bus stops from Lima, Peru. We used five images per bus stop. Primary and secondary outcome measures Bus stop images were classified according to COVID-19 risk into two labels: moderate or extreme. Results NASNetLarge outperformed the other CNNs except in the recall metric for the moderate label and in the precision metric for the extreme label; the ResNet152V2 performed better in these two metrics (85% vs 76% and 63% vs 60%, respectively). The NASNetLarge was further tuned. The best recall (75%) and F1 score (65%) for the extreme label were reached with data augmentation techniques. Areas close to buildings or with people were often classified as extreme risk. Conclusions This feasibility study showed that CNNs have the potential to classify street images according to levels of COVID-19 risk. In addition to applications in clinical medicine, CNNs and street images could advance the epidemiology of COVID-19 at the population level.0212<a class="citation_author_name" title="Navegar por nombre de Autor de Carrillo Larco, Rodrigo M" href="/fez/list/author/Carrillo Larco, Rodrigo M/">Carrillo Larco, Rodrigo M</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Castillo Cara, Manuel" href="/fez/list/author/Castillo Cara, Manuel/">Castillo Cara, Manuel</a> y <a class="citation_author_name" title="Navegar por nombre de Autor de Hernández Santa Cruz , Jose Francisco" href="/fez/list/author/Hernández Santa Cruz , Jose Francisco/">Hernández Santa Cruz , Jose Francisco</a> . (<span class="citation_date">2022</span>) <a class="citation_title" title="Click para ver : Street images classification according to COVID-19 risk in Lima, Peru: a convolutional neural networks feasibility analysis" href="/fez/view/bibliuned:557-Jmcastillo-0011">Street images classification according to COVID-19 risk in Lima, Peru: a convolutional neural networks feasibility analysis</a>. RecordArtículo de revistaPublishedInformáticaThe registered version of this article, first published in BMJ Open (2022) 12, is available online at the publisher's website: BMJ Publishing Group https://bmjopen.bmj.com/content/12/9/e063411BMJ Publishing GroupCarrillo Larco, Rodrigo MCastillo Cara, ManuelHernández Santa Cruz , Jose Francisco1BMJ Openbibliuned:557-Jmcastillo-0011http://e-spacio.uned.es/fez/view/bibliuned:557-Jmcastillo-0011912engCastillo-Cara_JM_Street.pdfpresmd_Castillo-Cara_JM_Street.xml2044-6055bibliuned:557bibliuned:Setarticulobibliuned:SetopenaireDepartamento de Informática y Automática (UNED). ArtículosSet de artículoSet de openairehttp://creativecommons.org/licenses/by-nc/4.0License Creative CommonsCarrillo LarcoAcceso abiertohttps://bmjopen.bmj.com/content/12/9/e0634110.769627633132016-01-01T00:00:00Z1612016-11-11T19:46:23Z2019-01-10T18:36:00ZTEIScribe: A graphic tool for composing and testing TEI documents in the context of the EVI-LINHD environmentbibliuned:363-Egonzalez10Digital Humanities (DH) can be seen as a boundary discipline that requires cooperation and common agreements and views among many scientific communities (del Río Riande, 2016a). This is the case of Virtual Research Environments (VREs), as they facilitate researchers and users from different communities a place to develop, store, share and preserve their work (Carusi and Reimer, 2010). The first DH Center in Spain, LINHD, the Digital Innovation Lab at UNED has started developing EVILINHD, the first VRE for Spanish-speakers (González-Blanco, 2016; del Río Riande, 2016b). The environment offers researchers a collaborative space in the cloud to manage all phases of their projects: the edition process, storage into the database, and text visualization in several output formats, such as HTML. In order to facilitate digital scholarly editing a specific tagging tool has been developed as a cloud application implemented with Vaadin, an open-source Java framework and integrated in EVILINHD: TEIScribe (TEIScribe, 2016). TEIScribe helps the DH community to concurrently label texts with TEI without XML knowledge through a graphic and intuitive design that aims to break language and technological barriers. The tool, that was conceived and developed for the BIESES project in order to boost collaborative work (BIESES, 2016), is based on some of the existing collaborative cloud editors (such as FontoXML, or CWRC writer), so its learning curve is low. The creation, modification and eliminating of labels and attributes is done with only a few mouse clicks. Since not all projects have the same labeling needs (Spadini, 2015), each text in TEIScribe is linked to a particular scheme that establishes the TEI-file structure (an XML file). All documents employed by the application are stored in a NoSQL database, a documental database, namely eXistDB, which organizes the different XML documents and schemes by project, and their correspondence. In this way, the tool greatly simplifies the user's work, since it can automatically detect and highlight mistakes on labels, which do not meet the requirement of associated schemes.0ponencia congreso10402<a class="citation_author_name" title="Navegar por nombre de Autor de González-Blanco García, Elena" href="/fez/list/author/González-Blanco García, Elena/">González-Blanco García, Elena</a>(<span class="citation_date">2016</span>) .<a class="citation_title" title="Click para ver : TEIScribe: A graphic tool for composing and testing TEI documents in the context of the EVI-LINHD environment" href="/fez/view/bibliuned:363-Egonzalez10">TEIScribe: A graphic tool for composing and testing TEI documents in the context of the EVI-LINHD environment</a>. <b></b>.En: <span class="citation_conference_location">Viena (Austria)</span>. ()RecordPonencia de CongresoPublishedFilologíaGonzález-Blanco García, Elenabibliuned:363-Egonzalez10http://e-spacio.uned.es/fez/view/bibliuned:363-Egonzalez10Viena (Austria)engGonzalez_Blanco_Elena_EVILINHD_TEIScribe.pdfpresmd_Gonzalez_Blanco_Elena_EVILINHD_TEIScribe.xmlbibliuned:363bibliuned:SetPonenciasbibliuned:SetopenaireDepartamento de Literatura Española (UNED). PonenciasSet de ponenciasSet de openairehttp://creativecommons.org/licences/by-nc-nd/4.0Licencia de acceso Creative CommonsGonzález-Blanco GarcíaAcceso abierto0.769627631982021-10-01T00:00:00Z842023-01-13T03:42:56Z2023-01-13T03:52:22ZDependency parsing as sequence labeling for low-resource languagesbibliuned:master-ETSInformatica-TL-AmunozEl procesamiento de lenguaje natural (PLN) ha experimentado claros avances en los últimos años. Sin embargo, la mayoría de mejoras y estudios se han centrado en un selecto grupo de idiomas, siendo el ingles su principal representante, ignorando como funcionan estos métodos en idiomas menos privilegiados, que normalmente reciben el nombre de idiomas con pocos recursos. Este trabajo trata sobre idiomas con pocos recursos, y se centra en una tarea central de PLN conocida como análisis sintáctico de dependencias; ésta consiste en analizar automáticamente la estructura sintáctica de dependencias de una oración, conectando sus palabras mediante relaciones asimétricas binarias entre una palabra gobernante y una palabra subordinada sintácticamente. En concreto, nuestra contribución se encuentra en la intersección entre la velocidad de análisis e idiomas con pocos recursos. En este contexto, recientemente se ha propuesto realizar el análisis de dependencias como una tarea de etiquetado de secuencias. Este enfoque computa un árbol linealizado de n etiquetas dada una frase de longitud n, y otorga una buena relación entre velocidad y precisión. Además, ofrece una forma sencilla de incorporar información sintáctica como una word embedding o característica de entrada. En primer lugar, comparamos el rendimiento de cinco linealizaciones para análisis de dependencias como etiquetado de secuencias en escenarios con pocos recursos. Estas linealizaciones pertenecen a diferentes familias y proponen formular el problema como: (i) seleccionar el gobernante sintáctico para cada palabra, (ii) encontrar una representación de los arcos entre tokens utilizando paréntesis equilibrados y (iii) asociar a cada token subsecuencias de transiciones de un analizador basado en transiciones. Sin embargo, aún existe poco conocimiento sobre cómo se comportan estas linealizaciones en cofiguraciones con pocos recursos. En este trabajo, primero estudiamos su nivel de eficiencia, simulando configuraciones con datos restringidos partiendo de un conjunto diverso de treebanks con muchos recursos. Los resultados muestran que las codificaciones de selección del gobernante sintáctico son más eficientes y obtienen mejores resultados en condiciones ideales (gold), pero que esta ventaja se desvanece en favor de las estrategias de paréntesis equilibrados cuando la configuración utilizada es más similar a una cofiguración realista, como la esperada en idiomas con realmente pocos recursos. En segundo lugar, proponemos un método basado en morfología combinado con aprendizaje translingüe para intentar mejorar el rendimiento del análisis de dependencias en idiomas con pocos recursos. Para ello, primero entrenamos un sistema de exón morfológica para idiomas objetivo con pocos recursos, y después lo aplicamos a treebanks con muchos recursos de idiomas similares para crear un treebank flexionado translingüe (o x-inected treebank) que se asemeje al idioma con pocos recursos objetivo. A continuación, utilizamos los treebanks flexionados para entrenar los analizadores sintácticos de etiquetado de secuencias en dos escenarios: (i) un escenario zero-shot (entrenando un modelo en el x-inected treebank y ejecutándolo sobre el idioma objetivo), y (ii) un escenario few-shot (entrenando un modelo utilizando un grupo compuesto por x-inected treebank junto con el treebank con pocos recursos y ejecutándolos sobre el idioma objetivo). Nuestro objetivo es comprobar la utilidad del método propuesto en situaciones con distinta disponibilidad de datos anotados. Los resultados muestran que el método propuesto puede ser de ayuda en algunas situaciones, pero se necesita estudiar más en profundidad para entender como los distintos factores pueden afectar a los resultados y comprobar si estas tendencias se mantienen usando otros paradigmas, como analizadores basados en transiciones y basados en grafos.0Doctoral Thesis1572<a class="citation_author_name" title="Navegar por nombre de Autor de Muñoz Ortiz, Alberto" href="/fez/list/author/Muñoz Ortiz, Alberto/">Muñoz Ortiz, Alberto</a>. (<span class="citation_date">2021</span>). <i><a class="citation_title" title="Click para ver : Dependency parsing as sequence labeling for low-resource languages" href="/fez/view/bibliuned:master-ETSInformatica-TL-Amunoz">Dependency parsing as sequence labeling for low-resource languages</a></i> Master Thesis, <span class="citation_publisher">Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Lenguajes y Sistemas Informáticos</span>Recordmaster TesisPublishedIngeniería InformáticaUniversidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Lenguajes y Sistemas InformáticosMuñoz Ortiz, AlbertoAraujo Serna, LourdesVilares Calvo, Davidbibliuned:master-ETSInformatica-TL-Amunozhttp://e-spacio.uned.es/fez/view/bibliuned:master-ETSInformatica-TL-AmunozengMunozAlberto_TFM.pdfpresmd_MunozAlberto_TFM.xmlbibliuned:master-ETSInformatica-TLbibliuned:Settrabajosfindemasterbibliuned:SetopenaireMáster Universitario en Tecnologías del Lenguaje (UNED)Set de items trabajo fin de másterSet de openaireMuñoz OrtizAcceso abierto0.5699155331982023-01-01T00:00:00Z112024-02-17T07:41:17Z2024-02-17T07:43:26ZNLU for integral management of watch functionalitiesbibliuned:master-ETSInformatica-TL-MnubedaConversational assistants and chatbots have become popular tools that can quickly answer users' requests to help them solve simple tasks. One of the most important goals of a conversational assistant is to understand a user's intent, that is, NLU. To carry out this aim, intent classification is one of the most important tasks. Thus, this thesis aims to design and implement a benchmark to test different models that can be included for a intent recognition system in order to improve a stage that already exists in Aura (Telef´onica's virtual assistant). The resulting module can classify user utterances regarding watch actions. Recent advances in natural language by using labels from a predefined set of intents. The best model achieves an improvement of accuracy concerning the solution that is currently used by the company.0Doctoral Thesis332<a class="citation_author_name" title="Navegar por nombre de Autor de Úbeda Castañeda, María de las Nieves" href="/fez/list/author/Úbeda Castañeda, María de las Nieves/">Úbeda Castañeda, María de las Nieves</a>. (<span class="citation_date">2023</span>). <i><a class="citation_title" title="Click para ver : NLU for integral management of watch functionalities" href="/fez/view/bibliuned:master-ETSInformatica-TL-Mnubeda">NLU for integral management of watch functionalities</a></i> Master Thesis, <span class="citation_publisher">Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Lenguajes y Sistemas Informáticos</span>Recordmaster TesisPublishedIngeniería InformáticaUniversidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Lenguajes y Sistemas InformáticosÚbeda Castañeda, María de las NievesPeñas, Anselmobibliuned:master-ETSInformatica-TL-Mnubedahttp://e-spacio.uned.es/fez/view/bibliuned:master-ETSInformatica-TL-MnubedaengUbeda_MariaNieves_TFM.pdfpresmd_Ubeda_MariaNieves_TFM.xmlbibliuned:master-ETSInformatica-TLbibliuned:Settrabajosfindemasterbibliuned:SetopenaireMáster Universitario en Tecnologías del Lenguaje (UNED)Set de items trabajo fin de másterSet de openaireÚbeda CastañedaAcceso abierto0.509568733132017-01-01T00:00:00Z4152017-06-21T23:07:28Z2020-09-17T19:37:22ZTowards Interoperability in the European Poetry Community: The Standardization of Philological Conceptsbibliuned:363-Egonzalez14This paper stems from the Poetry Standardization and Linked Open Data project (POSTDATA). As its name reveals, one of the main aims of POSTDATA is to provide a means to publish European poetry (EP) data as Linked Open Data (LOD). Thus, developing a metadata application profile (MAP) as a common semantic model to be used by the EP community is a crucial step of this project. This MAP will enhance interoperability among the community members in particular, and among the EP community and other contexts in general (e.g. bibliographic records). This paper presents the methodology followed in the process of defining the concepts of the domain model of this MAP, as well as some issues that arise when labeling philological terms.0ponencia congreso7042<a class="citation_author_name" title="Navegar por nombre de Autor de Bermúdez Sabel, Helena" href="/fez/list/author/Bermúdez Sabel, Helena/">Bermúdez Sabel, Helena</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Curado Malta, Mariana" href="/fez/list/author/Curado Malta, Mariana/">Curado Malta, Mariana</a> y <a class="citation_author_name" title="Navegar por nombre de Autor de González-Blanco García, Elena" href="/fez/list/author/González-Blanco García, Elena/">González-Blanco García, Elena</a>(<span class="citation_date">2017</span>) .<a class="citation_title" title="Click para ver : Towards Interoperability in the European Poetry Community: The Standardization of Philological Concepts" href="/fez/view/bibliuned:363-Egonzalez14">Towards Interoperability in the European Poetry Community: The Standardization of Philological Concepts</a>. <b></b>.En: <span class="citation_conference_location">Galway (Ireland)</span>. ()RecordPonencia de CongresoPublishedLiteraturaSpringer International PublishingBermúdez Sabel, HelenaCurado Malta, MarianaGonzález-Blanco García, Elenabibliuned:363-Egonzalez14http://e-spacio.uned.es/fez/view/bibliuned:363-Egonzalez14Galway (Ireland)engGonzalez_Blanco_Interoperability.pdfpresmd_Gonzalez_Blanco_Interoperability.xmlbibliuned:363bibliuned:SetPonenciasbibliuned:Setopenairebibliuned:DptoSCC-ETSI-PonenciasDepartamento de Literatura Española (UNED). PonenciasSet de ponenciasSet de openaireDepartamento de Sistemas de Comunicación y Control. E.T.S.I. Informática (UNED). Ponenciashttp://creativecommons.org/licences/by-nc-nd/4.0Licencia de acceso Creative CommonsBermúdez SabelAcceso abierto0.509568734232012-01-01T00:00:00Z6222013-02-21T21:17:17ZUna etiqueta de plomo con fitónimos procedente de Mas Vell : (Vallmoll, ager Tarraconensis)bibliuned:ETFSerieII-2012-25-6030Presentación de una nueva etiqueta de plomo hallada casualmente en una zona rural del ager Tarraconensis. La pieza presenta dos líneas de texto en las que se ha podido reconocer la presencia de dos fitónimos. La placa está provista de un apéndice lateral en el que se sitúa el agujero para el hilo o cuerda que la unía a la vasija o contenedor. Este elemento resulta muy poco usual en este tipo de documentos epigráficos.A new lead label has been found by chance in a rural area of the ager Tarraconensis. The piece has two writing lines with two plant names. The plate is provided with a lateral appendix with a hole for the filament that connected it to the vessel or box. This element is very unusual in this type of epigraphic documents.05032<a class="citation_author_name" title="Browse by Author Name for Gorostidi Pi, Diana" href="/fez/list/author/Gorostidi Pi, Diana/">Gorostidi Pi, Diana</a> and <a class="citation_author_name" title="Browse by Author Name for Rodà de Llanza, Isabel" href="/fez/list/author/Rodà de Llanza, Isabel/">Rodà de Llanza, Isabel</a> . (<span class="citation_date">2012</span>) <a class="citation_title" title="Click para ver : Una etiqueta de plomo con fitónimos procedente de Mas Vell : (Vallmoll, ager Tarraconensis)" href="/fez/view/bibliuned:ETFSerieII-2012-25-6030">Una etiqueta de plomo con fitónimos procedente de Mas Vell : (Vallmoll, ager Tarraconensis)</a>. RecordArtículo de revistaPublishedhttp://udcdata.info/068273HistoriaUniversidad Nacional de Educación a Distancia (España). Facultad de Geografía e HistoriaGorostidi Pi, DianaRodà de Llanza, Isabelbibliuned:ETFSerieII-2012-25-6030http://e-spacio.uned.es/fez/view/bibliuned:ETFSerieII-2012-25-6030spaDocumento.pdfbibliuned:ETFSerieII-2012bibliuned:Setopenairebibliuned:SetarticuloEspacio, tiempo y forma. Serie II, Historia antigua. Año 2012, n. 25Set de openaireSet de artículohttp://creativecommons.org/licenses/by-nc-nd/4.0Licencia Creative CommonsGorostidi PiAcceso abierto0.509568731982020-10-06T00:00:00Z2572021-09-22T19:18:19Z2021-09-22T19:18:19ZWhite Matter Hyperintensities Segmentation with Prototype Learningbibliuned:master-ETSInformatica-IAA-OalarconThis paper proposes a new method -based on meta-learning- for the WMH Segmentation Challenge, organized by UMC Utrecht, VU Amsterdam, and NUHS Singapore hospitals. The purpose of this challenge is to compare methods for the semantic segmentation of white matter hyperintensities (WMH), which are brain white matter lesions, of presumably vascular origin in brain imaging obtained with magnetic resonance. White matter hyperintensities are found in patients with brain diseases like Parkinson, Alzheimer or stroke. Semantic segmentation refers to the process of linking each pixel in an image to a class label. The semantic segmentation of images has had a great advance with convolution neural networks, but they require a large number of images to be able to obtain good results. Convolutional neural networks are a type of neural networks specialized on images which architecture is similar to neurons’ pattern in human brain and they were inspired by the organization of the visual cortex. With the aim to reduce the number of images required in training, in this work, we propose the use of meta-learning algorithms, in particular prototype learning, to do this semantic segmentation. In addition, this approach also allows the network to be used in a different task for which it was not trained, which can improve its potential use. Results obtained suggest that it could be possible to use the network trained to a specific task (i.e., detect WMH in the brain), to another task (i.e. detect any kind of tumors in the brain).0Doctoral Thesis3642<a class="citation_author_name" title="Navegar por nombre de Autor de Alarcón Palomar, Óscar" href="/fez/list/author/Alarcón Palomar, Óscar/">Alarcón Palomar, Óscar</a>. (<span class="citation_date">2020</span>). <i><a class="citation_title" title="Click para ver : White Matter Hyperintensities Segmentation with Prototype Learning" href="/fez/view/bibliuned:master-ETSInformatica-IAA-Oalarcon">White Matter Hyperintensities Segmentation with Prototype Learning</a></i> Master Thesis, <span class="citation_publisher">Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial.</span>Recordmaster TesisPublishedIngeniería InformáticaUniversidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial.Alarcón Palomar, ÓscarSantos Martín, Olga C.bibliuned:master-ETSInformatica-IAA-Oalarconhttp://e-spacio.uned.es/fez/view/bibliuned:master-ETSInformatica-IAA-OalarconengAlarcon_Palomar_Oscar_TFM.pdfpresmd_Alarcon_Palomar_Oscar_TFM.xmlbibliuned:master-ETSInformatica-IAAbibliuned:Settrabajosfindemasterbibliuned:SetopenaireMáster Universitario en I.A. Avanzada: Fundamentos, Métodos y Aplicaciones (UNED)Set de items trabajo fin de másterSet de openaireAlarcón PalomarAcceso abierto0.509568731982008-09-01T00:00:00Z1222021-07-01T23:04:02Z2021-07-01T23:04:02ZEvaluation of unsupervised clustering algorithms for variable stars databibliuned:master-ETSInformatica-IAA-PherreraThe aim of this master thesis is to assess the validity of unsupervised clustering algorithms to variable stars data classification for the Gaia mission. The use of these techniques allows to identify natural clustering without using any previous information about the classes and its distribution and, therefore, allows to discover new classes of objects. With this objective, we evaluate two probabilistic algorithms, one in which each cluster is characterized by a parametric distribution, and other, by a no-parametric distribution in a hierarchical clustering: Autoclass and HMAC (Hierarchical Mode Association Clustering). Both methods are evaluated against the same criteria, reproducibility, computation time, sensitivity to new classes and interpretability, in datasets that can grow up to 108 instances. These criteria are the first step to assess the feasibility of application of the algorithm but they are not enough to evaluate the goodness of clustering results. Despite the popular use of the unsupervised clustering techniques, the performance evaluation of clustering is an open question. It includes knowing how many clusters are actually present and how real is the clustering itself. Our clustering evaluation starts applying the expert knowledge and using a labeled dataset what allows to match some clusters with some variable stars types, but this is not enough to reach the objective of identifying each cluster. A review of the existing indices to evaluate clustering with objective criteria is included. Clusters and data are then analyzed to understand the results obtained with both methods biased by the method itself. A clustering combination method of these two algorithms is also tested as a technique that optimizes according multiple objective functions and trying to avoid some limitations of both algorithms.0Doctoral Thesis2432<a class="citation_author_name" title="Navegar por nombre de Autor de Herrera Plaza, Pilar" href="/fez/list/author/Herrera Plaza, Pilar/">Herrera Plaza, Pilar</a>. (<span class="citation_date">2008</span>). <i><a class="citation_title" title="Click para ver : Evaluation of unsupervised clustering algorithms for variable stars data" href="/fez/view/bibliuned:master-ETSInformatica-IAA-Pherrera">Evaluation of unsupervised clustering algorithms for variable stars data</a></i> Master Thesis, <span class="citation_publisher">Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial.</span>Recordmaster TesisPublishedIngeniería InformáticaUniversidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial.Herrera Plaza, PilarSarro Baro, Luis M.bibliuned:master-ETSInformatica-IAA-Pherrerahttp://e-spacio.uned.es/fez/view/bibliuned:master-ETSInformatica-IAA-PherreraengHerrera_Plaza_Pilar_TFM.pdfpresmd_Herrera_Plaza_Pilar_TFM.xmlbibliuned:master-ETSInformatica-IAAbibliuned:Settrabajosfindemasterbibliuned:SetopenaireMáster Universitario en I.A. Avanzada: Fundamentos, Métodos y Aplicaciones (UNED)Set de items trabajo fin de másterSet de openaireHerrera PlazaacceptedVersion0.444553934232022-04-01T00:00:00Z02024-01-25T05:56:47Z2024-01-25T05:56:47ZToxicological effects of three different types of highly pure graphene oxide in the midge Chironomus ripariusbibliuned:DptoFMyF-FCIE-Articulos-Mmorales-0003Graphene oxide (GO) is a carbon nanomaterial used in electronics, biomedicine, environmental remediation and biotechnology. The production of graphene will increase in the upcoming years. The carbon nanoparticles (NPs) are released into the environment and accumulated in aquatic ecosystems. Information on the effects of GO in aquatic environments and its impact on organisms is still lacking. The aim of this study was to synthesise and characterise label-free GO with controlled lateral dimensions and thickness – small GO (sGO), large GO (lGO) and monolayer GO (mlGO) – and determine their impact on Chironomus riparius, a sentinel species in the freshwater ecosystem. Superoxide dismutase (SOD) and lipid peroxidation (LPO) was evaluated after exposures for 24 h and 96 h to 50, 500, and 3000 μg/L. GOs accumulated in the gut of C. riparius and disturbed its antioxidant metabolism. We suggest that all types of GO exposure can upregulate of SOD. Moreover, both lGO and mlGO treatments caused LPO damage in C. riparius in comparison to sGO, proving its favourable lateral size impact in this organism. Our results indicate that GOs could accumulate and induce significant oxidative stress on C. riparius. This work shows new information about the potential oxidative stress of these NMs in aquatic organisms.0312<a class="citation_author_name" title="Navegar por nombre de Autor de Martín, Folgar, Raquel" href="/fez/list/author/Martín, Folgar, Raquel/">Martín, Folgar, Raquel</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Esteban Arranz, Adrián" href="/fez/list/author/Esteban Arranz, Adrián/">Esteban Arranz, Adrián</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Negri, Viviana" href="/fez/list/author/Negri, Viviana/">Negri, Viviana</a> y <a class="citation_author_name" title="Navegar por nombre de Autor de Morales, Mónica" href="/fez/list/author/Morales, Mónica/">Morales, Mónica</a> . (<span class="citation_date">2022</span>) <a class="citation_title" title="Click para ver : Toxicological effects of three different types of highly pure graphene oxide in the midge Chironomus riparius" href="/fez/view/bibliuned:DptoFMyF-FCIE-Articulos-Mmorales-0003">Toxicological effects of three different types of highly pure graphene oxide in the midge Chironomus riparius</a>. RecordArtículo de revistaPublishedCienciasLa versión registrada de este artículo, publicado por primera vez en "Science of The Total Environment, Volume 815, 2022, 152465", está disponible en línea en el sitio web del editor: Elsevier, https://doi.org/10.1016/j.scitotenv.2021.152465ElsevierMartín, Folgar, RaquelEsteban Arranz, AdriánNegri, VivianaMorales, MónicaScience of The Total Environmentbibliuned:DptoFMyF-FCIE-Articulos-Mmorales-0003http://e-spacio.uned.es/fez/view/bibliuned:DptoFMyF-FCIE-Articulos-Mmorales-0003815eng0048-9697bibliuned:DptoFMyF-FCIE-Articulosbibliuned:Setarticulobibliuned:SetopenaireDepartamento de Física matemática y de Fluidos. ArtículosSet de artículoSet de openairehttps://creativecommons.org/licenses/by/4.0/Licencia Creative CommonsMartínAcceso cerradohttps://doi.org/10.1016/j.scitotenv.2021.1524650.444553934172017-01-01T00:00:00Z8312018-05-29T19:26:13Z2018-05-29T19:26:13ZKnowledge-Based Cataloguing of Deep Multi-Wavelength Cosmological Surveystesisuned:ED-Pg-SisInt-MjmarquezI developed an expert data processing pipeline to improve the quality of the astronomical multi-colour galaxy catalogues. This pipeline acts in three main areas: (1) rening surface brightness measurements, (2) agging contaminated sources, and (3) improving the crossmatching of galaxies by modelling their colours. In order to develop this expert system, we start by building the knowledge model of entities and tasks involved and, as the result of this, we populate an ontology with instances of these classes. This ontology was created in line with the existing ones of the International Virtual Observatory Alliance(IVOA) initiative which intends to unify the Astronomy data models used across the scientic community. We achieved this goal through the use of articial intelligence methodologies. We used Bayesian model decision, active contour from Articial Vision and rule-based systems, all three of these methodologies are integrated into a single modular expert system versatile and exible enough to be used partially or entirely as a module of another processing system, as well as an input for a rened IVOA ontology. We performed a validation of the system with synthetic data and real astronomical images and catalogues from the Cosmic Evolution Survey (COSMOS). The outcome of this step conrmed the validity of our proposal. The results on a reduced but representative COSMOS data set conrmed that the photometric cross matching solution and the labelling of sources to determine their contamination status is a signicant improvement with respect to the existing methodologies. Regarding the renement of source contours, the experiment conducted with synthetic data as well as the results on real data demonstrated that this methodology is more exible in the determination of contours and it allows a good degree of automatism; however the computational cost and the observed lack of certainty for all cases indicates that this proposal needs further development. Overall it can be concluded that our system constitutes a significant advance in the cataloguing of galaxies in multi-band image cubes. We achieved this with an expert system that can be run without much human supervision.0Doctoral Thesis5372<a class="citation_author_name" title="Navegar por nombre de Autor de Márquez Sánchez, María José" href="/fez/list/author/Márquez Sánchez, María José/">Márquez Sánchez, María José</a>. <b><i><a class="citation_title" title="Click para ver : Knowledge-Based Cataloguing of Deep Multi-Wavelength Cosmological Surveys" href="/fez/view/tesisuned:ED-Pg-SisInt-Mjmarquez">Knowledge-Based Cataloguing of Deep Multi-Wavelength Cosmological Surveys</a></i></b> . <span class="citation_date">2017</span>. <span class="citation_publisher">Universidad Nacional de Educación a Distancia (España). Escuela Internacional de Doctorado. Programa de Doctorado en Sistemas Inteligentes</span>RecordDoctoral ThesisPublishedIngeniería InformáticaUniversidad Nacional de Educación a Distancia (España). Escuela Internacional de Doctorado. Programa de Doctorado en Sistemas InteligentesMárquez Sánchez, María JoséSarro Baro, Luis ManuelBudavári, Tamástesisuned:ED-Pg-SisInt-Mjmarquezhttp://e-spacio.uned.es/fez/view/tesisuned:ED-Pg-SisInt-MjmarquezengMARQUEZ_SANCHEZ_MJose_Tesis.pdfpresmd_MARQUEZ_SANCHEZ_MJose_Tesis.xmltesisuned:ED_Pg_SisIntbibliuned:Setthesisbibliuned:SetopenaireEscuela de Doctorado. Programa de doctorado en Sistemas Inteligentes (UNED)Set de Tesis Doctorales de la UNEDSet de openairehttps://creativecommons.org/licenses/by-nc-nd/4.0Licencia de acceso Creative CommonsMárquez SánchezAcceso abierto0.444553934232023-04-10T00:00:00Z252023-11-30T06:08:29Z2023-11-30T06:08:29ZClimate transition risk in determining credit risk: evidence from firms listed on the STOXX Europe 600 indexbibliuned:DptoEEC-FCEE-Articulos-Rarguedas-0003This paper assesses whether a climate factor is relevant to measure default risk in a sample of main companies listed on the STOXX Europe 600 exchange from 2010 to 2020. The starting point is a factorial panel datamodel which is subsequently modified to capture the climate impact through different functional forms.We find that relevant differences in default risk exist before and after the Paris Agreement. Our analysis also indicates that this difference cannot be explained by means of traditional financial factors. Finally, we further show that a climate change risk and opportunities label is a significant factor in evaluating credit risk, both prior to and post-Paris agreement. These results are important to the extent that they suggest that companies’ market performance itself allows to measure differences in credit risk between companies and to link them with climate risk factors. This approach may be useful as a complement or in combination with the traditional use of exogenous climate factors that have been widely used in the literature in this field.0792<a class="citation_author_name" title="Navegar por nombre de Autor de Ramos-García, Daniel" href="/fez/list/author/Ramos-García, Daniel/">Ramos-García, Daniel</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de López-Martín, Carmen" href="/fez/list/author/López-Martín, Carmen/">López-Martín, Carmen</a> y <a class="citation_author_name" title="Navegar por nombre de Autor de Arguedas-Sanz, Raquel" href="/fez/list/author/Arguedas-Sanz, Raquel/">Arguedas-Sanz, Raquel</a> . (<span class="citation_date">2023</span>) <a class="citation_title" title="Click para ver : Climate transition risk in determining credit risk: evidence from firms listed on the STOXX Europe 600 index" href="/fez/view/bibliuned:DptoEEC-FCEE-Articulos-Rarguedas-0003">Climate transition risk in determining credit risk: evidence from firms listed on the STOXX Europe 600 index</a>. RecordArtículo de revistaPublishedEconomíaLa versión publicada de este artículo, publicado por primera vez en Empirical Economics, está disponible en línea en el sitio web del editor: Springer, https://doi.org/10.1007/s00181-023-02416-8SpringerRamos-García, DanielLópez-Martín, CarmenArguedas-Sanz, RaquelEmpirical Economicsbibliuned:DptoEEC-FCEE-Articulos-Rarguedas-0003http://e-spacio.uned.es/fez/view/bibliuned:DptoEEC-FCEE-Articulos-Rarguedas-000320912114565engArguedas_Sanz_Raquel_Climate_transition_risk.pdfpresmd_Arguedas_Sanz_Raquel_Climate_transition_risk.xml1435-8921bibliuned:DptoEEC-FCEE-Articulosbibliuned:Setarticulobibliuned:SetopenaireDepartamento de Economía de la Empresa y Contabilidad (UNED). ArtículosSet de artículoSet de openairehttp://creativecommons.org/licenses/by-nc-nd/4.0Licencia Creative CommonsRamos-GarcíaAcceso abiertohttps://doi.org/10.1007/s00181-023-02416-80.444553934232024-02-22T00:00:00Z32024-03-12T07:54:30Z2024-03-12T07:54:30ZThe Link between Abstract Thinking Style and Subjective Well-Being: Its Impact when People are in (Real or Perceived) Financial Scarcitybibliuned:DptoPSyO-FPSI-Articulos-Ifernandez-0006For constructionism, language is the link among different levels of analysis of emotional events, from individual to interpersonal and macrosocial. The interaction among these emotional levels allows us to construe an emotional episode and label it with an emotion word, coordinate with the emotions perceived in others, and represent events as a society. Across two studies, we found similarities and differences among inner emotions experienced (individual level), emotions perceived in others (descriptive feeling rules, interpersonal level) and emotions shared on the internet (socioemotional conventions, macro- social level), with all these emotional targets focused on the COVID–19 outbreak. The results indicate a similarity between the emotional meaning of COVID–19 in society and the descriptive feeling rules, whereas the reported inner emotions were clearly distinct: Joy was irrelevant at the interpersonal and macrosocial levels but clearly important at the individual level. A mismatch also appeared for fear and hope. While fear was the most predominant emotion at the interpersonal and macrosocial levels during most of the phases, it was moderately predominant at the individual level. Hope followed the opposite pattern, being the most relevant emotion at the individual level but less relevant at the interpersonal and macrosocial levels. Each level might have different consequences: Mixed emotions at the individual level might promote resilience; fear perceived in other people might motivate protective behaviors; and sadness socially shared during Christmas might generate greater empathy. These results support the complexity of emotional concepts and the suitability of exploring them at different levels of analysis0212<a class="citation_author_name" title="Navegar por nombre de Autor de Caballero González, Amparo" href="/fez/list/author/Caballero González, Amparo/">Caballero González, Amparo</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Itziar, Fernández Sedano" href="/fez/list/author/Itziar, Fernández Sedano/">Itziar, Fernández Sedano</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Laforet, Bronwyn" href="/fez/list/author/Laforet, Bronwyn/">Laforet, Bronwyn</a> y <a class="citation_author_name" title="Navegar por nombre de Autor de Carrera Levillain, Pilar" href="/fez/list/author/Carrera Levillain, Pilar/">Carrera Levillain, Pilar</a> . (<span class="citation_date">2024</span>) <a class="citation_title" title="Click para ver : The Link between Abstract Thinking Style and Subjective Well-Being: Its Impact when People are in (Real or Perceived) Financial Scarcity" href="/fez/view/bibliuned:DptoPSyO-FPSI-Articulos-Ifernandez-0006">The Link between Abstract Thinking Style and Subjective Well-Being: Its Impact when People are in (Real or Perceived) Financial Scarcity</a>. RecordArtículo de revistaPublishedPsicologíaThe published version of this article, first published in The Spanish Journal of Psychology (2024) 27, 7 p.1-9, is available online at the publisher's website: Cambridge University Press, http://doi.org/10.1017/SJP.2024.6Cambridge University PressCaballero González, AmparoItziar, Fernández SedanoLaforet, BronwynCarrera Levillain, Pilar1The Spanish Journal of Psychologybibliuned:DptoPSyO-FPSI-Articulos-Ifernandez-0006http://e-spacio.uned.es/fez/view/bibliuned:DptoPSyO-FPSI-Articulos-Ifernandez-000619727engFernandez_Sedano_Iciar_The_link.pdfpresmd_Fernandez_Sedano_Iciar_The_link.xml1138-7416; eISSN 1988-2904bibliuned:DptoPSyO-FPSI-Articulosbibliuned:Setarticulobibliuned:SetopenaireDepartamento de Psicología Social y de las Organizaciones (UNED). ArtículosSet de artículoSet de openairehttp://creativecommons.org/licenses/by-nc/4.0License Creative CommonsCaballero GonzálezAcceso abiertohttp://doi.org/10.1017/SJP.2024.60.44455393198152023-11-30T15:15:57Z2023-11-30T15:15:57ZDetección de postura en conjuntos de datos multilingüebibliuned:master-ETSInformatica-ICD-JavilaLa detección de postura en el aprendizaje automático es la tarea de identificar automáticamente la actitud expresada en un texto hacia una proposición específica. Esto es fundamental para el procesamiento del lenguaje natural, ya que proporciona informació n valiosa sobre las opiniones de las personas hacia diferentes propuestas. Puede tener aplicaciones importantes en diversos campos, desde la gestión de la reputación en línea hasta la toma de decisiones políticas. Esta tarea se lleva a cabo mediante algori tmos de minería de texto y aprendizaje automático, que analizan características clave en el texto para determinar su postura. Sin embargo, la mayoría de las investigaciones se han centrado en el inglés, lo que limita la aplicabilidad de los modelos a otros idiomas. Algunos estudios han abordado esta limitación mediante conjuntos de datos en diferentes idiomas, pero se han enfrentado a desafíos debido a desequilibrios en clases y a grandes diferencias entre los contextos de cada idioma. En esta línea, se pre sentó la tarea de evaluación Intra Multilingual Multi Target Stance Classification 2023 . Su objetivo es clasificar la postura de textos en varios idiomas y con respecto a múltiples objetivos. La tarea implica clasificar comentarios sobre propuestas políticas como de apoyo, oposición o neutralidad. El conjunto de datos se construyó utilizando la plataforma de la Conferencia sobre el Futuro de Europa (CoFE), que incluye propuestas políticas y comentarios en cualquiera de los 24 idiomas oficiales de la Unión E uropea. Este conjunto de datos presenta una oportunidad atractiva para estudiar la detección de postura en un entorno verdaderamente multilingüe. Este trabajo presenta los resultados obtenidos en esta tarea. El objetivo principal de este estudio fue desarrollar e investigar diversos modelos de aprendizaje automático y aprendizaje profundo para la clasificación de la postura. Se exploraron técnicas c omo el transfer learning , data augmentation y label spreading , para ampliar el conjunto de datos de entrenamiento y aprovechar modelos preentrenados. Los resultados muestran que las estrategias empleadas en este trabajo mejoran significativamente los resultados de referencia proporcionados por la tarea. Estos resultados, después de su presentación en la tarea, se han publicado como parte de las actas de CLEF 2023 (Avila et al., 2023)0Doctoral Thesis562<a class="citation_author_name" title="Navegar por nombre de Autor de Ávila Gómez, Jorge Pablo" href="/fez/list/author/Ávila Gómez, Jorge Pablo/">Ávila Gómez, Jorge Pablo</a>. (). <i><a class="citation_title" title="Click para ver : Detección de postura en conjuntos de datos multilingüe" href="/fez/view/bibliuned:master-ETSInformatica-ICD-Javila">Detección de postura en conjuntos de datos multilingüe</a></i> Master Thesis, <span class="citation_publisher">Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial</span>Recordmaster TesisPublishedIngeniería InformáticaUniversidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia ArtificialÁvila Gómez, Jorge PabloRodrigo Yuste, ÁlvaroCenteno Sánchez, Robertobibliuned:master-ETSInformatica-ICD-JavilaAvilaGomezJorgePablo-TFM.pdfpresmd_AvilaGomezJorgePablo-TFM.xmlbibliuned:master-ETSInformatica-ICDbibliuned:Settrabajosfindemasterbibliuned:SetopenaireMáster Universitario en Ingeniería y Ciencia de Datos (UNED)Set de items trabajo fin de másterSet de openaireÁvila GómezAcceso abierto0.444553934232008-01-01T00:00:00Z10752009-04-23T23:45:29ZConsecuencias en la cartografía de cultivos mediterráneos de la combinación de datos ráster-vector : enriquecimiento de una base SIGPAC a través de la teledetecciónbibliuned:ETFSerieVI-F3F305CF-2CA7-EDAD-2992-31550E0D3BFBEl objetivo de este artículo es el estudio de las implicaciones del enriquecimiento de cartografía vectorial a partir de cartografía ráster obtenidamediante teledetección. El banco
de pruebas es una base vectorial SIGPAC de seis comarcas catalanas enriquecida con un mapa de cultivos mediterráneos ráster elaborado a partir de la clasificación mixta de siete imágenes Landsat
TMdel 2004. Se han ensayado dos niveles de fidelidad en el clasificador y dos niveles de pureza en la composición del polígono. Los resultados se analizan a nivel global y por cultivo,
observándose, entre otras cuestiones, que el enriquecimiento vectorial suele ser positivo a ambos niveles. Asimismo, la exigencia de mayor fidelidad y una pureza con restricción conlleva mayor
exactitud aunque un menor número de polígonos etiquetados, lo que sólo significa más error si estos se consideran errores.The objective of this article is to analyze the consequences of enriching vector cartography fromraster
cartography obtained using remote sensing. The testing ground is a SIGPAC vector base of six Catalan regions
enriched with a raster map of Mediterranean crops elaborated from the mixed classification of seven
Landsat TMimages of year 2004. Two levels of fidelity in the classifier and two levels of purity in the polygon
composition have been tested. The outcomes are analyzed at global level and per crop, giving as a result,
among other issues, that the vector enrichment is usually positive at both levels. Likewise, the exigency of
greater fidelity and a purity with restriction yields greater exactitude despite of a smaller number of labeled
polygons, which onlymeansmore error if they are considered errors.06582<a class="citation_author_name" title="Browse by Author Name for Serra Cabot, Pere" href="/fez/list/author/Serra Cabot, Pere/">Serra Cabot, Pere</a>, <a class="citation_author_name" title="Browse by Author Name for Moré, Gerard" href="/fez/list/author/Moré, Gerard/">Moré, Gerard</a> and <a class="citation_author_name" title="Browse by Author Name for Pons, Xavier" href="/fez/list/author/Pons, Xavier/">Pons, Xavier</a> . (<span class="citation_date">2008</span>) <a class="citation_title" title="Click para ver : Consecuencias en la cartografía de cultivos mediterráneos de la combinación de datos ráster-vector : enriquecimiento de una base SIGPAC a través de la teledetección" href="/fez/view/bibliuned:ETFSerieVI-F3F305CF-2CA7-EDAD-2992-31550E0D3BFB">Consecuencias en la cartografía de cultivos mediterráneos de la combinación de datos ráster-vector : enriquecimiento de una base SIGPAC a través de la teledetección</a>. RecordArtículo de revistaPublishedhttp://udcdata.info/068128GeografíaUniversidad Nacional de Educación a Distancia (España). Facultad de Geografía e HistoriaSerra Cabot, PereMoré, GerardPons, Xavierbibliuned:ETFSerieVI-F3F305CF-2CA7-EDAD-2992-31550E0D3BFBhttp://e-spacio.uned.es/fez/view/bibliuned:ETFSerieVI-F3F305CF-2CA7-EDAD-2992-31550E0D3BFBspaDocumento.pdfbibliuned:ETFSerieVI2008bibliuned:Setopenairebibliuned:SetarticuloEspacio, tiempo y forma. Serie VI, Geografía. Nueva época. Año 2008, n. 1Set de openaireSet de artículohttp://creativecommons.org/licenses/by-nc-nd/4.0Licencia Creative CommonsSerra CabotAcceso abierto0.444553931982020-06-01T00:00:00Z3962021-09-20T21:49:28Z2021-09-20T21:49:28ZCapturing, Modelling, Analyzing and providing Feedback in Martial Arts with Artificial Intelligence to support Psychomotor Learning Activitiesbibliuned:master-ETSInformatica-IAA-AcasasThis Master’s Thesis explores how Artificial Intelligence (IA) can assist in the learning of psychomotor activities, specifically the learning of a martial art, through the development of an AI-based application that executes in an Android device. Martial arts are an interesting domain for this because it encompasses most of the characteristics that can be found in other psychomotor activities. Different methods for capturing, modelling and analyzing human motion, as well as providing feedback to the user have been reviewed. In addition, another bibliographical review of 27 publications has been carried out to evaluate till what extend these methods have been already applied to martial arts. For this research work, inertial methods have been selected for capturing motion. In particular, the inertial sensors of an Android device have been used for capturing the execution of a set of movements of American Kenpo Karate from 20 volunteers. The captured data was then modeled, by segmenting and labelling the movements, and smoothing the time series using Exponentially Weighted Moving Averages. The resulting dataset, formed by 240 movements, was then used for training and comparing three neural network-based classifiers: FC-ANN, 1D-CNN and LSTM. Neural networks were selected because of their ability of learn complex functions and the fact that some neural network architectures have been created specifically for analyze time series. Further, the weights learned by a neural network can be transferred to other domains through the technique known as transfer learning. Obtained results suggest that LSTM is the type of neural network that can better classify the movements studied, obtaining an accuracy of 1.0 in the training set, and an accuracy of 0.94 in the testing set. For demonstrating that those methods can be applied, an AI-based real-time Android application has been developed. This application employs the studied methods, as well as a feedback strategy created using the results of a questionnaire carried out with the purpose of identifying the issues that online learning of a psychomotor activity can entails. The application has then been tested, generating a good impression in the users. Following the open science philosophy, all contributions are shared in the GitHub repository.0Doctoral Thesis5232<a class="citation_author_name" title="Navegar por nombre de Autor de Casas Ortiz, Alberto" href="/fez/list/author/Casas Ortiz, Alberto/">Casas Ortiz, Alberto</a>. (<span class="citation_date">2020</span>). <i><a class="citation_title" title="Click para ver : Capturing, Modelling, Analyzing and providing Feedback in Martial Arts with Artificial Intelligence to support Psychomotor Learning Activities" href="/fez/view/bibliuned:master-ETSInformatica-IAA-Acasas">Capturing, Modelling, Analyzing and providing Feedback in Martial Arts with Artificial Intelligence to support Psychomotor Learning Activities</a></i> Master Thesis, <span class="citation_publisher">Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial.</span>Recordmaster TesisPublishedIngeniería InformáticaUniversidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial.Casas Ortiz, AlbertoSantos, Olga C.bibliuned:master-ETSInformatica-IAA-Acasashttp://e-spacio.uned.es/fez/view/bibliuned:master-ETSInformatica-IAA-AcasasengCasas_Ortiz_Alberto_TFM.pdfpresmd_Casas_Ortiz_Alberto_TFM.xmlbibliuned:master-ETSInformatica-IAAbibliuned:Settrabajosfindemasterbibliuned:SetopenaireMáster Universitario en I.A. Avanzada: Fundamentos, Métodos y Aplicaciones (UNED)Set de items trabajo fin de másterSet de openaireCasas OrtizAcceso abierto0.444553934232021-01-01T00:00:00Z82024-01-31T07:31:19Z2024-01-31T07:31:19ZSiCoDeF² Net: Siamese Convolution Deconvolution Feature Fusion Network for One-Shot Classificationbibliuned:DptoSCC-ETSI-Articulos-Rpastor-00010Nowadays, deep convolutional neural networks (CNNs) for face recognition exhibit a performance comparable to human ability in the presence of the appropriate amount of labelled training data. However, training CNNs remains as an arduous task due to the lack of training samples. To overcome this drawback, applications demand one-shot learning to improve the obtained performances over traditional machine learning approaches by learning representative information about data categories from few training samples. In this context, Siamese convolutional network ( SiConvNet ) provides an interesting deep architecture to tackle the data limitation. In this regard, applying the convolution operation on real world images by using the trainable correlative Gaussian kernel adds correlations to the output images, which hinder the recognition process due to the blurring effects introduced by the convolution kernel application. As a result the pixel-wise and channel-wise correlations or redundancies could appear in both single and multiple feature maps obtained by a hidden layer. In this sense, convolution-based models fail to generalize the feature representation because of both the strong correlations presence in neighboring pixels and the channel-wise high redundancies between different channels of the feature maps, which hamper the effective training. Deconvolution operation helps to overcome the shortcomings that limit the conventional SiConvNet performance, learning successfully correlation-free features representation. In this paper, a simple but efficient Siamese convolution deconvolution feature fusion network ( SiCoDeF 2 Net ) is proposed to learn the invariant and discriminative complementary features generated from both the (i) sub-convolution (SCoNet) and (ii) sub deconvolutional (SDeNet) networks using a concatenation operation which significantly improves the one-shot unconstrained facial recognition task. Extensive experiments performed on several widely used benchmarks, provide promising results, where the proposed SiCoDeF 2 Net model significantly outperforms the current state-of-art in terms of classification accuracy, F1, precision and recall. The code will be available on: https://github.com/purbayankar/SiCoDeF2Net .0312<a class="citation_author_name" title="Navegar por nombre de Autor de Kumar Roy, Swalpa" href="/fez/list/author/Kumar Roy, Swalpa/">Kumar Roy, Swalpa</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Kar, Purbayan" href="/fez/list/author/Kar, Purbayan/">Kar, Purbayan</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Paoletti, Mercedes E." href="/fez/list/author/Paoletti, Mercedes E./">Paoletti, Mercedes E.</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Haut, Juan M." href="/fez/list/author/Haut, Juan M./">Haut, Juan M.</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Pastor-Vargas, Rafael" href="/fez/list/author/Pastor-Vargas, Rafael/">Pastor-Vargas, Rafael</a> y <a class="citation_author_name" title="Navegar por nombre de Autor de Robles-Gómez, Antonio" href="/fez/list/author/Robles-Gómez, Antonio/">Robles-Gómez, Antonio</a> . (<span class="citation_date">2021</span>) <a class="citation_title" title="Click para ver : SiCoDeF² Net: Siamese Convolution Deconvolution Feature Fusion Network for One-Shot Classification" href="/fez/view/bibliuned:DptoSCC-ETSI-Articulos-Rpastor-00010">SiCoDeF² Net: Siamese Convolution Deconvolution Feature Fusion Network for One-Shot Classification</a>. RecordArtículo de revistaPublishedIEEEKumar Roy, SwalpaKar, PurbayanPaoletti, Mercedes E.Haut, Juan M.Pastor-Vargas, RafaelRobles-Gómez, AntonioIEEE Accessbibliuned:DptoSCC-ETSI-Articulos-Rpastor-00010http://e-spacio.uned.es/fez/view/bibliuned:DptoSCC-ETSI-Articulos-Rpastor-000109engPastor_Vargas_Rafael_SiCoDeF2Net.pdfpresmd_Pastor_Vargas_Rafael_SiCoDeF2Net.xml2169-3536bibliuned:DptoSCC-ETSI-Articulosbibliuned:Setarticulobibliuned:SetopenaireDepartamento de Sistemas de Comunicación y Control. E.T.S.I. Informática (UNED). ArtículosSet de artículoSet de openairehttps://creativecommons.org/licenses/by/4.0/deed.esLicencia Creative CommonsKumar RoyAcceso abierto10.1109/ACCESS.2021.31076260.379539234232022-03-09T00:00:00Z22024-03-12T06:08:40Z2024-03-12T06:08:40ZDisentangling Emotions during the Coronavirus Outbreak in Spain: Inner Emotions, Descriptive Feeling Rules and Socioemotional Conventionsbibliuned:DptoPSyO-FPSI-Articulos-Ifernandez-0003For constructionism, language is the link among different levels of analysis of emotional events, from individual to interpersonal and macrosocial. The interaction among these emotional levels allows us to construe an emotional episode and label it with an emotion word, coordinate with the emotions perceived in others, and represent events as a society. Across two studies, we found similarities and differences among inner emotions experienced (individual level), emotions perceived in others (descriptive feeling rules, interpersonal level) and emotions shared on the internet (socioemotional conventions, macro- social level), with all these emotional targets focused on the COVID–19 outbreak. The results indicate a similarity between the emotional meaning of COVID–19 in society and the descriptive feeling rules, whereas the reported inner emotions were clearly distinct: Joy was irrelevant at the interpersonal and macrosocial levels but clearly important at the individual level. A mismatch also appeared for fear and hope. While fear was the most predominant emotion at the interpersonal and macrosocial levels during most of the phases, it was moderately predominant at the individual level. Hope followed the opposite pattern, being the most relevant emotion at the individual level but less relevant at the interpersonal and macrosocial levels. Each level might have different consequences: Mixed emotions at the individual level might promote resilience; fear perceived in other people might motivate protective behaviors; and sadness socially shared during Christmas might generate greater empathy. These results support the complexity of emotional concepts and the suitability of exploring them at different levels of analysis0262<a class="citation_author_name" title="Navegar por nombre de Autor de Caballero , Amparo" href="/fez/list/author/Caballero , Amparo/">Caballero , Amparo</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Villar , Sergio" href="/fez/list/author/Villar , Sergio/">Villar , Sergio</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Itziar, Fernández Sedano" href="/fez/list/author/Itziar, Fernández Sedano/">Itziar, Fernández Sedano</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Sevillano, Verónica" href="/fez/list/author/Sevillano, Verónica/">Sevillano, Verónica</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Gavilán, Pablo" href="/fez/list/author/Gavilán, Pablo/">Gavilán, Pablo</a> y <a class="citation_author_name" title="Navegar por nombre de Autor de Carrera, Pilar" href="/fez/list/author/Carrera, Pilar/">Carrera, Pilar</a> . (<span class="citation_date">2022</span>) <a class="citation_title" title="Click para ver : Disentangling Emotions during the Coronavirus Outbreak in Spain: Inner Emotions, Descriptive Feeling Rules and Socioemotional Conventions" href="/fez/view/bibliuned:DptoPSyO-FPSI-Articulos-Ifernandez-0003">Disentangling Emotions during the Coronavirus Outbreak in Spain: Inner Emotions, Descriptive Feeling Rules and Socioemotional Conventions</a>. RecordArtículo de revistaPublishedPsicologíaThe published version of this article, first published in The Spanish Journal of Psychology (2022) 25, 12 p.1-12, is available online at the publisher's website: Cambridge University Press, https://doi.org/10.1017/SJP.2022.7Cambridge University PressCaballero , AmparoVillar , SergioItziar, Fernández SedanoSevillano, VerónicaGavilán, PabloCarrera, Pilar1The Spanish Journal of Psychologybibliuned:DptoPSyO-FPSI-Articulos-Ifernandez-0003http://e-spacio.uned.es/fez/view/bibliuned:DptoPSyO-FPSI-Articulos-Ifernandez-00031121225engFernandez_Sedano_Iciar_Disentangling.pdfpresmd_Fernandez_Sedano_Iciar_Disentangling.xml1138-7416; eISSN 1988-2904bibliuned:DptoPSyO-FPSI-Articulosbibliuned:Setarticulobibliuned:SetopenaireDepartamento de Psicología Social y de las Organizaciones (UNED). ArtículosSet de artículoSet de openairehttps://creativecommons.org/licenses/by-nc-nd/4.0/es/License Creative CommonsCaballero Acceso abiertohttps://doi.org/10.1017/SJP.2022.70.379539234232023-06-16T00:00:00Z22024-03-13T06:42:01Z2024-03-13T08:09:44ZGaia Data Release 3. Non-stellar content and source classificationbibliuned:95-Lmsarro-0013Context. As part of the third Gaia Data Release, we present the contributions of the non-stellar and classifcation modules from the eighth coordination unit (CU8) of the Data Processing and Analysis Consortium, which is responsible for the determination of source astrophysical parameters using Gaia data. This is the third in a series of three papers describing the work done within CU8 for this release. Aims. For each of the five relevant modules from CU8, we summarise their objectives, the methods they employ, their performance, and the results they produce for Gaia DR3. We further advise how to use these data products and highlight some limitations. Methods. The Discrete Source Classier (DSC) module provides classification probabilities associated with five types of sources: quasars, galaxies, stars, white dwarfs, and physical binary stars. A subset of these sources are processed by the Outlier Analysis (OA) module, which performs an unsupervised clustering analysis, and then associates labels with the clusters to complement the DSC classfication. The Quasi Stellar Object Classifier (QSOC) and the Unresolved Galaxy Classfier (UGC) determine the redshifts of the sources classfied as quasar and galaxy by the DSC module. Finally, the Total Galactic Extinction (TGE) module uses the extinctions of individual stars determined by another CU8 module to determine the asymptotic extinction along all lines of sight for Galactic latitudes |b| > 5◦. Results. Gaia DR3 includes 1591 million sources with DSC classications; 56 million sources to which the OA clustering is applied; 1.4 million sources with redshift estimates from UGC; 6.4 million sources with QSOC redshift; and 3.1 million level 9 HEALPixes of size 0.013 deg2 where the extinction is evaluated by TGE. Conclusions. Validation shows that results are in good agreement with values from external catalogues; for example 90% of the QSOC redshifts have absolute error lower than 0.1 for sources with empty warning flags, while UGC redshifts have a mean error of 0.008 ± 0.037 if evaluated on a clean set of spectra. An internal validation of the OA results further shows that 30 million sources are located in high confidence regions of the clustering map.0242<a class="citation_author_name" title="Navegar por nombre de Autor de Delchambre, L." href="/fez/list/author/Delchambre, L./">Delchambre, L.</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Bailer-Jones, C.A.L." href="/fez/list/author/Bailer-Jones, C.A.L./">Bailer-Jones, C.A.L.</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Bellas-Velidis, I." href="/fez/list/author/Bellas-Velidis, I./">Bellas-Velidis, I.</a> y <a class="citation_author_name" title="Navegar por nombre de Autor de Sarro Baro, Luis Manuel" href="/fez/list/author/Sarro Baro, Luis Manuel/">Sarro Baro, Luis Manuel</a> . (<span class="citation_date">2023</span>) <a class="citation_title" title="Click para ver : Gaia Data Release 3. Non-stellar content and source classification" href="/fez/view/bibliuned:95-Lmsarro-0013">Gaia Data Release 3. Non-stellar content and source classification</a>. RecordArtículo de revistaPublishedIngeniería InformáticaThe registered version of this paper, first published in Astronomy & Astrophysics (2023) Vol.674, A31, is available online at the publisher's website: EDP Sciences, https://doi.org/10.1051/0004-6361/202243423EDP SciencesDelchambre, L.Bailer-Jones, C.A.L.Bellas-Velidis, I.Sarro Baro, Luis ManuelAstronomy & Astrophysics (A&A)bibliuned:95-Lmsarro-0013http://e-spacio.uned.es/fez/view/bibliuned:95-Lmsarro-0013A31674engSarro_Baro_Luis_Manuel_GDR3_Non_stellar_Content.pdfpresmd_Sarro_Baro_Luis_Manuel_GDR3_Non_stellar_Content.xml1432-0746bibliuned:95bibliuned:Setarticulobibliuned:SetopenaireDepartamento de Inteligencia Artificial (UNED). ArtículosSet de artículoSet de openairehttps://creativecommons.org/licenses/by/4.0/Licencia Creative CommonsDelchambreAcceso abiertohttps://doi.org/10.1051/0004-6361/2022434230.379539234232018-11-29T00:00:00Z52024-01-27T06:39:36Z2024-01-27T06:39:36ZFeature engineering for sentiment analysis in e-health forumsbibliuned:DptoLSI-ETSI-GPLNyRI-Jrodriguez-0004Introduction Exploiting information in health-related social media services is of great interest for patients, researchers and medical companies. The challenge is, however, to provide easy, quick and relevant access to the vast amount of information that is available. One step towards facilitating information access to online health data is opinion mining. Even though the classification of patient opinions into positive and negative has been previously tackled, most works make use of machine learning methods and bags of words. Our first contribution is an extensive evaluation of different features, including lexical, syntactic, semantic, network-based, sentiment-based and word embeddings features to represent patient-authored texts for polarity classification. The second contribution of this work is the study of polar facts (i.e. objective information with polar connotations). Traditionally, the presence of polar facts has been neglected and research in polarity classification has been bounded to opinionated texts. We demonstrate the existence and importance of polar facts for the polarity classification of health information. Material and methods We annotate a set of more than 3500 posts to online health forums of breast cancer, crohn and different allergies, respectively. Each sentence in a post is manually labeled as “experience”, “fact” or “opinion”, and as “positive”, “negative” and “neutral”. Using this data, we train different machine learning algorithms and compare traditional bags of words representations with word embeddings in combination with lexical, syntactic, semantic, network-based and emotional properties of texts to automatically classify patient-authored contents into positive, negative and neutral. Beside, we experiment with a combination of textual and semantic representations by generating concept embeddings using the UMLS Metathesaurus. Results We reach two main results: first, we find that it is possible to predict polarity of patient-authored contents with a very high accuracy (≈ 70 percent) using word embeddings, and that this considerably outperforms more traditional representations like bags of words; and second, when dealing with medical information, negative and positive facts (i.e. objective information) are nearly as frequent as negative and positive opinions and experiences (i.e. subjective information), and their importance for polarity classification is crucial.0352<a class="citation_author_name" title="Navegar por nombre de Autor de Carrillo de Albornoz, Jorge" href="/fez/list/author/Carrillo de Albornoz, Jorge/">Carrillo de Albornoz, Jorge</a>, <a class="citation_author_name" title="Navegar por nombre de Autor de Rodríguez-Vidal, Javier" href="/fez/list/author/Rodríguez-Vidal, Javier/">Rodríguez-Vidal, Javier</a> y <a class="citation_author_name" title="Navegar por nombre de Autor de Plaza, Laura" href="/fez/list/author/Plaza, Laura/">Plaza, Laura</a> . (<span class="citation_date">2018</span>) <a class="citation_title" title="Click para ver : Feature engineering for sentiment analysis in e-health forums" href="/fez/view/bibliuned:DptoLSI-ETSI-GPLNyRI-Jrodriguez-0004">Feature engineering for sentiment analysis in e-health forums</a>. RecordArtículo de revistaPublishedInformáticaEste es el manuscrito aceptado del artículo publicado por Public Library of Science en "Plos One 13 (11): e0207996", disponible en línea: https://doi.org/10.1371/journal.pone.0207996Public Library of ScienceCarrillo de Albornoz, JorgeRodríguez-Vidal, JavierPlaza, LauraPlos Onebibliuned:DptoLSI-ETSI-GPLNyRI-Jrodriguez-0004http://e-spacio.uned.es/fez/view/bibliuned:DptoLSI-ETSI-GPLNyRI-Jrodriguez-00041113engRodriguez_Vidal_Javier_Feature_Sentiment_Anal.pdfpresmd_Rodriguez_Vidal_Javier_Feature_Sentiment_Anal.xml1932-6203bibliuned:DptoLSI-ETSI-GPLNyRIbibliuned:Setarticulobibliuned:SetopenaireGrupo de Procesamiento del Lenguaje Natural y Recuperación de InformaciónSet de artículoSet de openairehttp://creativecommons.org/licenses/by-nc-nd/4.0Licencia Creative CommonsCarrillo de AlbornozAcceso abiertohttps://doi.org/10.1371/journal.pone.02079960.3795392117211728223322222221117322111732