Now showing items 21-40 of 80

  • Construcció dirigida de models predictius 

    Piqué Sellés, Jordi (Universitat Politècnica de Catalunya, 2017-06)
    Bachelor thesis
    Open Access
    Els algorismes de Machine Learning, en especial les xarxes neuronals, han experimentat un increment notable en les seves capacitats d’aprenentatge en els últims anys. No obstant això, la llegibilitat i la comprensió del ...
  • Creation and development of an AI teaching assistant 

    Benedito Saura, Ernest (Universitat Politècnica de Catalunya / Universitat de Barcelona, 2018-01)
    Master thesis
    Open Access
    During this project, an end-to-end solution has been provided, creating and developing a Chatbot that, using Artificial Intelligence, is able to solve doubts that students may have within the domain of a university subject. ...
  • Deep learning applied to speech synthesis 

    Pascual de la Puente, Santiago (Universitat Politècnica de Catalunya, 2016-06-30)
    Master thesis
    Open Access
    Deep Learning has been applied successfully to speech processing problems. In this work we explore its capabilities, focusing concretely in recurrent neural architectures to build a state of the art Text-To-Speech system ...
  • Deep Learning for Protein Function Prediction 

    Alba Avilés, Manuel (Universitat Politècnica de Catalunya, 2017-09-26)
    Master thesis
    Open Access
    Covenantee:  Technische Universität München
    The assignment of functions to proteins is a bottleneck due to the need of costly and time-consuming molecular experiments. This is the reason why more often data analysis methods are used for protein an- notation. In this ...
  • Detection of quantum phase transitions via machine learning algorithms 

    Pérez Díaz, Joel (Universitat Politècnica de Catalunya, 2019-08-31)
    Master thesis
    Open Access
    A Neural Network is trained to classify Mott Insulator and Superfluid phases in an optical lattice using data generated with Diffusion Monte Carlo algorithms (DMC). The trained model is used to predict the phase transition ...
  • Discovering ship navigation patterns towards environment impact modeling 

    Gutiérrez Torre, Alberto (Universitat Politècnica de Catalunya, 2017-04-28)
    Master thesis
    Open Access
    Covenantee:  Barcelona Supercomputing Centre
    Ship positioning and maneuvering information is highly relevant to understand the levels of pollution on coastal cities and sea-life quality, containing latent patterns of vessels behavior, that are of utility on earth ...
  • Disseny d'un algorisme per l'avaluació de l'activitat física i l'intensitat de l'exercici basat en l'Smartphone 

    Carbonés Fargas, Bernat (Universitat Politècnica de Catalunya, 2014-07-23)
    Bachelor thesis
    Open Access
    [ANGLÈS] The designed algorithm allows non-intrusive physical activity recognition using accelerometer data from the smartphone. Fourteen subjects of the same age (mean = 22 years) have used the Android application RSAF ...
  • Earthquake simulation by Fiber Bundle Model and machine learning techniques 

    Monterrubio-Velasco, Marisol; Carrasco-Jiménez, José Carlos; Aguilar-Meléndez, Armando; Castillo, Octavio; Puente, Josep de la (Barcelona Supercomputing Center, 2018-04-24)
    Conference report
    Open Access
  • Embedded feature selection methods for microarray classification 

    Munne Hernandez, Enric (Universitat Politècnica de Catalunya, 2010-06-14)
    Master thesis
    Restricted access - confidentiality agreement
    Covenantee:  École polytechnique de Louvain
  • Emotion recognition based on the speech, using a Naive Bayes classifier 

    Urbano Romeu, Ángel (Universitat Politècnica de Catalunya, 2016-06-30)
    Bachelor thesis
    Open Access
    Covenantee:  Institut für Computertechnik
    Speech emotion recognition is one of the latest challenges in speech processing. Besides facial expressions or gestures, speech has proven as one of the most promising modalities for the automatic emotion recognition. To ...
  • Enhanced Industrial Machinery Condition Monitoring Methodology based on Novelty Detection and Multi-Modal Analysis 

    Cariño Corrales, Jesús Adolfo; Delgado Prieto, Miquel; Zurita Millán, Daniel; Millan, Marta; Ortega Redondo, Juan Antonio; Romero Troncoso, Rene De Jesus (Institute of Electrical and Electronics Engineers (IEEE), 2016-10-19)
    Article
    Open Access
    This paper presents a condition-based monitoring methodology based on novelty detection applied to industrial machinery. The proposed approach includes both, the classical classification of multiple a priori known scenarios, ...
  • Estudio del algoritmo NEAT aplicado a los videojuegos 

    Fernandez Villalba, Mario (Universitat Politècnica de Catalunya, 2018-10-23)
    Bachelor thesis
    Open Access
    És possible fer que un ordinador aprengui pel seu compte a jugar a un videojoc? En aquest projecte s'intenta respondre a aquesta pregunta al conegut joc Tetris mitjançant l'algoritme NEAT, un algoritme genètic que evoluciona ...
  • Exploring the Vision Processing Unit as Co-Processor for Inference 

    Rivas-Gomez, Sergio; Peña, Antonio J.; Moloney, David; Laure, Erwin; Markidis, Stefano (IEEE, 2018-08-06)
    Conference lecture
    Open Access
    The success of the exascale supercomputer is largely debated to remain dependent on novel breakthroughs in technology that effectively reduce the power consumption and thermal dissipation requirements. In this work, we ...
  • Face recognition using Deep Learning 

    Serra Alza, Xavier (Universitat Politècnica de Catalunya, 2017-01-20)
    Master thesis
    Restricted access - confidentiality agreement
  • Facial Expression Detection using Convolutional Neural Networks 

    Vilagran Solsona, Albert (Universitat Politècnica de Catalunya, 2018-10-24)
    Bachelor thesis
    Open Access
    The world of artificial intelligence advances at great speed. The greatest example of this is neural networks, which are revolutionizing the system of automation and data extraction. Neural networks can be trained to perform ...
  • Fast Video Object Segmentation by Pixel-Wise Feature Comparison 

    Palliser Sans, Rafel (Universitat Politècnica de Catalunya, 2019-05-29)
    Bachelor thesis
    Open Access
    Covenantee:  University of Toronto. Vector Institute
    This final degree thesis tackles the task of One-Shot Video Object Segmentation, where multiple objects have to be separated from the background only having the ground truth masks for them in the very first frame. Their ...
  • Heart Failure Factors: a database approach 

    Gállego Olsina, Gerard Ion (Universitat Politècnica de Catalunya, 2019-03)
    Bachelor thesis
    Open Access
    This project aims to find relationships between psychological stress factors and heart attacks that took place in Catalunya between 2010 and 2016. We have measured these factors through the news that were published in La ...
  • Hierarchical classification scheme based on identification, isolation and analysis of conflictive regions 

    Cariño Corrales, Jesús Adolfo; Zurita Millán, Daniel; Delgado Prieto, Miquel; Ortega Redondo, Juan Antonio; Romero Troncoso, Rene De Jesus (Institute of Electrical and Electronics Engineers (IEEE), 2014)
    Conference report
    Restricted access - publisher's policy
    Abstract: A great deal of effort is being made to increase accuracy and reliability of Condition Based Maintenance systems; for instance, by improved feature selection strategies or optimization approaches of classifier ...
  • Implementació d'un sistema portable multimodal basat en Deep Learning 

    Abella Gassol, Adrià (Universitat Politècnica de Catalunya, 2016)
    Bachelor thesis
    Open Access
  • Implementació i estudi d'una deep/wide kernel machine 

    Serra Alza, Xavier (Universitat Politècnica de Catalunya, 2015-06-23)
    Bachelor thesis
    Open Access
    Aquest projecte busca implementar i provar un tipus particular de Deep Kernel Machine. Aquest tipus de programa pertany al camp del Machine Learning i, per tant, s'usa per a fer predicions basades en un procés previ ...