Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Digibug. Repositorio Institucional de la Universidad de Granada
Publicación Artículo científico (JournalArticle)

Multi-Label Quantification

  • Moreo Fernández, Alejandro
  • Aparicio, Manuel Francisco
  • Sebastiani, Fabrizio
The work of A. Moreo and F. Sebastiani has been supported by the SoBigData++ project, funded by the European Commission (Grant 871042) under the H2020 Programme INFRAIA-2019-1, by the AI4Media project, funded by the European Commission (Grant 951911) under the H2020 Programme ICT-48-2020, and by the SoBigData.it and FAIR projects funded by the Italian Ministry of University and Research under the NextGenerationEU program; the authors’ opinions do not necessarily reflect those of the funding agencies. The work of M. Francisco has been supported by the FPI 2017 predoctoral programme, from the Spanish Ministry of Economy and Competitiveness (MINECO), grant BES-2017-081202., Quantification, variously called supervised prevalence estimation or learning to quantify, is the supervised learning task of generating predictors of the relative frequencies (a.k.a. prevalence values) of the classes of interest in unlabelled data samples. While many quantification methods have been proposed in the past for binary problems and, to a lesser extent, single-label multiclass problems, the multi-label setting (i.e., the scenario in which the classes of interest are not mutually exclusive) remains by and large unexplored. A straightforward solution to the multi-label quantification problem could simply consist of recasting the problem as a set of independent binary quantification problems. Such a solution is simple but naïve, since the independence assumption upon which it rests is, in most cases, not satisfied. In these cases, knowing the relative frequency of one class could be of help in determining the prevalence of other related classes. We propose the first truly multi-label quantification methods, i.e., methods for inferring estimators of class prevalence values that strive to leverage the stochastic dependencies among the classes of interest in order to predict their relative frequencies more accurately. We show empirical evidence that natively multi-label solutions outperform the naïve approaches by a large margin. The code to reproduce all our experiments is available online., SoBigData++ project, funded by the European Commission (Grant 871042) under the H2020 Programme INFRAIA-2019-1, AI4Media project, funded by the European Commission (Grant 951911) under the H2020 Programme ICT-48-2020, SoBigData.it and FAIR projects funded by the Italian Ministry of University and Research under the NextGenerationEU program, PI 2017 predoctoral programme, from the Spanish Ministry of Economy and Competitiveness (MINECO), grant BES-2017-081202
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Optimizing museum construction material selection through mass spectrometry analysis

  • Alvarez-Martin, Alba
  • Díaz, Iván
  • King, R.
  • Bakker-Arkema, J.
  • Newsome, G.A.
  • Cano Díaz, Emilio
  • Creange, S.
  • Breitung, E.
  • Keune, K.
Assessing the suitability of display case construction materials is crucial to prevent museum object damage. This study evaluates three mass spectrometry (MS) approaches, HS-SPME-trap-enrichment-GC-MS, DTD-GC-MS, and DART-HRMS, for analysing volatile organic compound (VOC) emissions from exhibition and storage materials. Results were compared with the Oddy test, which assesses material corrosivity. HS-SPME-trap-enrichment improved sensitivity for detecting low-abundance corrosive volatiles, such as acetic acid, while DTD offered broader chemical profiling. Correlations between acetic acid emissions and lead corrosion in Oddy tests suggest GC-MS-based methods can predict material corrosivity. DART-HRMS effectively confirms specific additives, while GC-MS shows potential to serve as a screening tool for material classification. Though MS techniques provide faster analysis and detailed chemical insights than the Oddy test, they require a higher level of knowledge for data interpretation. With further refinement, MS approaches could complement to traditional corrosion testing, offering an efficient screening tool for evaluating materials used in conservation., This research was conducted within IPERION HS Task 5.1 funded by the European Union, H2020-INFRAIA-2019-1, under GA 871034. E.B., J.B.A ., and RK’s research is supported by an IMLS National Leadership Grant (MG-249353-OMS-21)., Peer reviewed