Recent Submissions

  • Effective visualization of sparse image-to-image correspondences 

    Andújar Gran, Carlos Antonio; Chica Calaf, Antonio; Comino Trinidad, Marc (European Association for Computer Graphics (Eurographics), 2020)
    Conference report
    Open Access
    Finding robust correspondences between images is a crucial step in photogrammetry applications. The traditional approach to visualize sparse matches between two images is to place them side-by-side and draw link segments ...
  • A Tool for N-way analysis of programming exercises 

    Andújar Gran, Carlos Antonio; Comino Trinidad, Marc; Fairén González, Marta; Vinacua Pla, Álvaro (European Association for Computer Graphics (Eurographics), 2020)
    Conference report
    Open Access
    Programming exercises are a corner stone in Computer Science courses. If used properly, these exercises provide valuable feedback both to students and instructors. Unfortunately, the assessment of student submissions through ...
  • An interoperable workflow-based framework for the automation of building intelligent process control systems 

    Pascual Pañach, Josep; Cugueró Escofet, Miquel Àngel; Aguiló Martos, Pere; Sànchez-Marrè, Miquel (International Environmental Modelling and Software Society (iEMSs), 2018)
    Conference lecture
    Open Access
    One of the major problems to design and implement a control/supervision system for a process lies in the need to establish an ad-hoc system for each process installation. On the other side, an open challenge related to the ...
  • Convolutional Neural Networks, image recognition and financial time series forecasting 

    Arratia Quesada, Argimiro Alejandro; Sepúlveda, Eduardo (2019)
    Conference report
    Restricted access - publisher's policy
    Convolutional Neural Networks (CNN) are best known as good image classifiers. This model is recently been used for financial forecasting. The purpose of this work is to show that by converting financial information into ...
  • Do Google Trends forecast bitcoins? Stylized facts and statistical evidence 

    Arratia Quesada, Argimiro Alejandro; López Barrantes, Albert (2019)
    Conference report
    Open Access
    In early 2018 Bitcoin prices peaked at USD 20,000 and, almost two years later, we still continue debating if cryptocurrencies can actually become a currency for the everyday life or not. From the economic point of view, ...
  • Random forest as a tumour genetic marker extractor 

    Pérez Arnal, Raquel; Garcia Gasulla, Dario; Torrents Rodas, David; Pares, Ferran; Cortés García, Claudio Ulises; Labarta Mancho, Jesús José; Ayguadé Parra, Eduard (IOS Press, 2019)
    Conference report
    Open Access
    Finding tumour genetic markers is essential to biomedicine due to their relevance for cancer detection and therapy development. In this paper, we explore a recently released dataset of chromosome rearrangements in 2,586 ...
  • From bilingual to multilingual neural machine translation by incremental training 

    Escolano Peinado, Carlos; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (Association for Computational Linguistics, 2019)
    Conference lecture
    Open Access
    Multilingual Neural Machine Translation approaches are based on the use of task specific models and the addition of one more language can only be done by retraining the whole system. In this work, we propose a new training ...
  • On some strategies for missing values in positive semidefinite matrices 

    Belanche Muñoz, Luis Antonio; Vázquez García, Miguel (Thompson, 2005)
    Conference report
    Open Access
    This article presents our work on missing values in Positive Semi-Definite or PSD matrices. We show how simple properties of PSD matrices can be used to deal with missing values. We study several situations and investigate ...
  • Multilingual, multi-scale and multi-layer visualization of sequence-based intermediate representations 

    Escolano Peinado, Carlos; Ruiz Costa-Jussà, Marta; Lacroux, Elora; Vázquez Alcocer, Pere Pau (Association for Computational Linguistics, 2019)
    Conference report
    Restricted access - publisher's policy
    The main alternatives nowadays to dealwith sequences are Recurrent Neural Net-works (RNN), Convolutional Neural Networks(CNN) architectures and the Transformer. Inthis context, RNN’s, CNN’s and Transformerhave most commonly ...
  • Similarity-based heterogeneous neuron models 

    Belanche Muñoz, Luis Antonio (IOS Press, 2000)
    Conference report
    Open Access
    This paper introduces a general class of neuron models, accepting heterogeneous inputs in the form of mixtures of continuous (crisp or fuzzy) numbers, linguistic information, and discrete (either ordinal or nominal) ...
  • Fuzzy inputs and missing data in similarity-based heterogeneous neural networks 

    Belanche Muñoz, Luis Antonio; Valdés Ramos, Julio José (Springer, 1999)
    Conference report
    Open Access
    Fuzzy heterogeneous networks are recently introduced neural network models composed of neurons of a general class whose inputs and weights are mixtures of continuous variables (crisp and/or fuzzy) with discrete quantities, ...
  • A thermodynamic algorithm for feature selection 

    Belanche Muñoz, Luis Antonio; González Navarro, Félix Fernando (Thomson Editores Spain, 2007)
    Conference report
    Open Access
    The main purpose of Feature Selection (FS) is to find a reduced subset of attributes from a data set described by a feature set. This implies a search process in the space of possible solutions, trying to optimize an ...

View more