Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 8
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Characterization and exploitation of community structure in cover song networks

  • Serrà Julià, Joan
  • Zanin, Massimiliano
  • Herrera Boyer, Perfecto, 1964-
  • Serra, Xavier
The use of community detection algorithms is explored within the framework of cover song identification, i.e. the automatic detection of different audio renditions of the same underlying musical piece. Until now, this task has been posed as a typical query-by-example task, where one submits a query song and the system retrieves a list of possible matches ranked by their similarity to the query. In this work, we propose a new approach which uses song communities (clusters, groups) to provide more relevant answers to a given query. Starting from the output of a state-of-the-art system, songs are embedded in a complex weighted network whose links represent similarity (related musical content). Communities inside the network are then recognized as groups of covers and this information is used to enhance the results of the system. In particular, we show that this approach increases both the coherence and the accuracy of the system. Furthermore, we provide insight into the internal organization of individual cover song communities, showing that there is a tendency for the original song to be central within the community. We postulate that the methods and results presented here could be relevant to other query-by-example tasks., This work has been supported by the following projects: Classical Planet (TSI-070100–2009-407; MITYC) and DRIMS (TIN2009–14247-C02–01; MICINN).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Music retagging using label propagation and robust principal component analysis

  • Yang, Yi-Hsuan
  • Bogdanov, Dmitry
  • Herrera Boyer, Perfecto, 1964-
  • Sordo, Mohamed
Comunicació presentada a: WWW'12 Companion: The 21st International Conference on World Wide Web celebrat del 16 al 20 d'abril de 2012 a Lió, França., The emergence of social tagging websites such as Last.fm has provided new opportunities for learning computational models that automatically tag music. Researchers typically obtain music tags from the Internet and use them to construct machine learning models. Nevertheless, such tags are usually noisy and sparse. In this paper, we present a preliminary study that aims at refining (retagging) social tags by exploiting the content similarity between tracks and the semantic redundancy of the track-tag matrix. The evaluated algorithms include a graph-based label propagation method that is often used in semi-supervised learning and a robust principal component analysis (PCA) algorithm that has led to state-of-the-art results in matrix completion. The results indicate that robust PCA with content similarity constraint is particularly effective; it improves the robustness of tagging against three types of synthetic errors and boosts the recall rate of music auto-tagging by 7% in a real-world setting., This work was supported by a grant from the National Science Council of Taiwan under contract NSC 100-2218-E001-009 and partially supported by the following projects: Classical Planet: TSI-070100-2009-407 (MITYC), DRIMS: TIN2009-14247-C02-01 (MICINN) and MIRES: EC-FP7 ICT2011.1.5 Networked Media and Search Systems, grant agreement No. 287711.
Repisalud
Publicación Artículo científico (JournalArticle)

Characterization of the Taenia spp HDP2 sequence and development of a novel PCR-based assay for discrimination of Taenia saginata from Taenia asiatica

  • Gonzalez, Luis Miguel
  • Bailo-Barroso, Begoña
  • Ferrer, Elizabeth
  • Fernandez García, Maria D
  • Harrison, Leslie Js
  • Parkhouse, Michael Re
  • McManus, Donald P
  • Garate, Teresa
A previously described Taenia saginata HDP2 DNA sequence, a 4-kb polymorphic fragment, was previously used as the basis for developing PCR diagnostic protocols for the species-specific discrimination of T. saginata from T. solium and for the differentiation of T. saginata from T. asiatica. The latter was shown subsequently to lack the required specificity, so we undertook genetic studies of the HDP2 sequence from T. saginata and T. asiatica to determine why, and to develop a novel HDP2-PCR protocol for the simultaneous unambiguous identification of human taeniids. Sequencing and further analysis of the HDP2 DNA fragments of 19 Asiatic isolates of T. saginata and T. asiatica indicated that the HDP2 sequences of both species exhibited clear genomic variability, due to polymorphic variable fragments, that could correspond to the non-transcribed region of ribosomal DNA. This newly observed polymorphism allowed us to develop a novel, reproducible and reliable HDP2-PCR protocol which permitted the simultaneous discrimination of all T. saginata and T. asiatica isolates examined. This species-specific identification was based on, and facilitated by, the clear size difference in amplicon profiles generated: fragments of 1300 bp, 600 bp and 300 bp were produced for T. asiatica, amplicons of 1300 bp and 300 bp being obtained for T. saginata. Control T. solium samples produced one amplicon of 600 bp with the HDP2-PCR protocol. The assay has the potential to prove useful as a diagnostic tool in areas such as South East Asia where T. saginata, T. asiatica and T. solium coexist.
Repisalud
Publicación Artículo científico (JournalArticle)

Plasma metabolomic fingerprint of advanced cirrhosis stages among HIV/HCV-coinfected and HCV-monoinfected patients

  • Salgüero Fernandez, Sergio
  • Rojo, David
  • Berenguer, Juan
  • González-García, Juan
  • Fernandez-Rodriguez, Amanda
  • Brochado-Kith, Oscar
  • Díez, Cristina
  • Hontañón, Víctor
  • Virseda-Berdices, Ana
  • Martínez, Javier
  • Ibañez-Samaniego, Luis
  • Llop-Herrera, Elba
  • Barbas, Coral
  • Resino, Salvador
  • Jimenez-Sousa, Maria Angeles
Background & aims: Hepatitis C virus (HCV), human immunodeficiency virus (HIV) and cirrhosis induce metabolic disorders. Here, we aimed to evaluate the association of plasma metabolites with Child-Turcotte-Pugh (CTP) score and hepatic decompensation in HIV/HCV-coinfected and HCV-monoinfected patients with advanced cirrhosis. Methods: A cross-sectional study was carried out in 62 HIV/HCV-coinfected and 28 HCV-monoinfected patients. Metabolomics analysis was performed by gas chromatography-mass spectrometry (GC-MS) and liquid chromatography-mass spectrometry (LC-MS). The statistical association analysis was performed by partial least squares discriminant analysis (PLS-DA) and generalized linear model (GLM) with binomial distribution (to analyse HIV coinfection, high alcohol intake, treatment with statins, previous HCV therapy failure and decompensation) and ordinal logistic regression (OLR) models to analyse different stages of cirrhosis (CTP score). Results: The statistical analysis identified plasma metabolites associated with HIV coinfection, high alcohol intake, CTP score and hepatic decompensation. Overall, fatty acids, bile acids, aromatic and sulphur amino acids, butyrate derivatives, oxidized phospholipids, energy-related metabolites and bacterial fermentation-related metabolites were increased in more advanced cirrhosis stages; while lysophosphatidylcholines and lysophosphatidylethanolamines, branched-chain amino acids (BCAA) and metabolites of tricarboxylic acid cycle, among others, were decreased in more advanced cirrhosis. Most of the significant metabolites displayed a similar trend after stratifying for HIV/HCV- and HCV-infected patients. Glycolic acid, LPC (16:0) and taurocholic acid had high accuracy for discriminating patients according to decompensated cirrhosis (CTP ≥ 7). Conclusion: Altered plasma metabolomic profile was associated with advanced stages of cirrhosis in HIV/HCV-coinfected and HCV-monoinfected patients.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Fostering university students’ engagement in teamwork and innovation behaviors through game-based learning (GBL)

  • Martín-Hernández, Pilar
  • Gil-Lacruz, Marta
  • Gil-Lacruz, Ana I.
  • Azkue-Beteta, Juan Luis
  • Lira, Eva M.
  • Cantarero, Luis
Higher Education Instituions (HEIs) should be the driving force behind the training of college students in terms of both hard and soft skills (for example, innovation and teamwork competencies), and they should also do so without neglecting their health and well-being, perhaps more than ever in these complex times of the SARS-CoV2 pandemic. Game-based learning (GBL) could be a powerful and useful tool in this regard. There is, however, some controversy surrounding the use of games for learning purposes in higher education institutions, and most of the research done about this issue corresponds to GBL through digital games. Under this background, the main objective of this study was to test the effect of GBL on the intrinsic motivation (IM), teamwork engagement (TWE), team building (TB), teamwork competence (TWC), and innovation behaviors (IWB) of 142 college students of Health Sciences and Social Work. After rehearsing in small groups, the game was tested (T2). Our results obtained through the differential analyses confirmed that undergraduates were more intrinsically motivated, experienced more TWE, TB, and TWC, and developed more IWB than before playing the game (T1). Therefore, the development of core personal skills might be promoted effectively by games in an efficient, engaging, and motivating way.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

The Moderating Role of Teamwork Engagement and Teambuilding on the Effect of Teamwork Competence as a Predictor of Innovation Behaviors among University Students

  • Martín-Hernández, Pilar
  • Gil-Lacruz, Marta
  • Tesán-Tesán, Ana Cristina
  • Pérez-Nebra, Amalia Raquel
  • Azkue-Beteta, Juan Luis
  • Rodrigo-Estevan, María Luz
Sustainable innovation is the cornerstone of economic growth and development of regions and nations, as well as of organizational competitiveness and success. Innovation is a complex process that relies on individuals and often implies social activities based on interaction with others. Higher Education (HE) is expected to prepare innovative and teamwork-competent individuals. However, it has been noted that, so far, HE has not really addressed the question of how to train innovative college students capable of working in teams. To face such challenges, incorporating active teaching and learning methodologies, such as game-based learning (GBL), could be of great utility, as well as conducting much more research about the effect of teamwork-related factors on IWB, such as teamwork engagement (TWE) and teambuilding (TB). Under this background, our aim was to test the predictor effect of teamwork competence (TWE) on IWB, exploring the moderating role of TWE and TB in a sample comprising 142 college students of Health Sciences and Social Work. Our obtained results, through a multiple additive moderation analysis, showed that TWC positively predicted IWB. Moreover, this effect was moderated by TWE and TB. Therefore, these findings set light around how to foster IWB in HE.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Music retagging using label propagation and robust principal component analysis

  • Yang, Yi-Hsuan
  • Bogdanov, Dmitry
  • Herrera Boyer, Perfecto, 1964-
  • Sordo, Mohamed
Comunicació presentada a: WWW'12 Companion: The 21st International Conference on World Wide Web celebrat del 16 al 20 d'abril de 2012 a Lió, França., The emergence of social tagging websites such as Last.fm has provided new opportunities for learning computational models that automatically tag music. Researchers typically obtain music tags from the Internet and use them to construct machine learning models. Nevertheless, such tags are usually noisy and sparse. In this paper, we present a preliminary study that aims at refining (retagging) social tags by exploiting the content similarity between tracks and the semantic redundancy of the track-tag matrix. The evaluated algorithms include a graph-based label propagation method that is often used in semi-supervised learning and a robust principal component analysis (PCA) algorithm that has led to state-of-the-art results in matrix completion. The results indicate that robust PCA with content similarity constraint is particularly effective; it improves the robustness of tagging against three types of synthetic errors and boosts the recall rate of music auto-tagging by 7% in a real-world setting., This work was supported by a grant from the National Science Council of Taiwan under contract NSC 100-2218-E001-009 and partially supported by the following projects: Classical Planet: TSI-070100-2009-407 (MITYC), DRIMS: TIN2009-14247-C02-01 (MICINN) and MIRES: EC-FP7 ICT2011.1.5 Networked Media and Search Systems, grant agreement No. 287711.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Characterization and exploitation of community structure in cover song networks

  • Serrà Julià, Joan
  • Zanin, Massimiliano
  • Herrera Boyer, Perfecto, 1964-
  • Serra, Xavier
The use of community detection algorithms is explored within the framework of cover song identification, i.e. the automatic detection of different audio renditions of the same underlying musical piece. Until now, this task has been posed as a typical query-by-example task, where one submits a query song and the system retrieves a list of possible matches ranked by their similarity to the query. In this work, we propose a new approach which uses song communities (clusters, groups) to provide more relevant answers to a given query. Starting from the output of a state-of-the-art system, songs are embedded in a complex weighted network whose links represent similarity (related musical content). Communities inside the network are then recognized as groups of covers and this information is used to enhance the results of the system. In particular, we show that this approach increases both the coherence and the accuracy of the system. Furthermore, we provide insight into the internal organization of individual cover song communities, showing that there is a tendency for the original song to be central within the community. We postulate that the methods and results presented here could be relevant to other query-by-example tasks., This work has been supported by the following projects: Classical Planet (TSI-070100–2009-407; MITYC) and DRIMS (TIN2009–14247-C02–01; MICINN).