Now showing items 1-20 of 187

    • 2D to 3D body pose estimation for sign language with Deep Learning 

      Perez Granero, Pol (Universitat Politècnica de Catalunya, 2020-06)
      Bachelor thesis
      Open Access
      This project aims at leveraging the challenge of using 3D poses for Sign Language translation or animation by transforming 2D pose datasets into 3D ones. The goal is, using a 3D dataset of American Sign Language, to train ...
    • 3D Reconstruction of vegetation from orthophotos 

      Comino Trinidad, Marc (Universitat Politècnica de Catalunya, 2013-06-21)
      Bachelor thesis
      Open Access
      [CATALÀ] Mitjançant tècniques de Visió per Computador som capaços de detectar i classificar la flora present en una ortofoto. A partir d'aquesta informació, i d'un conjunt de models de plantes en 3D que generem, elaborem ...
    • A machine learning based wall model for LES of turbulent flows 

      Radhakrishnan, Sarath; Lehmkuhl Barba, Oriol (Barcelona Supercomputing Center, 2021-05)
      Conference report
      Open Access
      The trubulent flow of fluids is still an enigma for mathematicians and engineers alike. The partial differential equation that reperesents the flow of fluids does not have an analytical solution for turbulent regimes. ...
    • A machine learning research template for binary classification problems and shapley values integration 

      Smith, Matthew; Alvarez, Francisco (Elsevier, 2021-05)
      Article
      Open Access
      This paper documents published code which can help facilitate researchers with binary classification problems and interpret the results from a number of Machine Learning models. The original paper was published in Expert ...
    • A machine learning workflow for hurricane prediction 

      Kahira, Albert; Bautista Gomez, Leonardo; Badia Sala, Rosa Maria (Barcelona Supercomputing Center, 2018-04-24)
      Conference report
      Open Access
    • A new deep reinforcement learning architecture for autonomous UAVs 

      Muñoz Ferran, Guillem (Universitat Politècnica de Catalunya, 2018-09-07)
      Bachelor thesis
      Open Access
      Recent improvements in computation and algorithmic research, together with the rising era of Big Data, have allowed Artificial Intelligence increase its popularity within masses. The recent publication of the Deep Q-Network ...
    • A Quick View on Current Techniques and Machine Learning Algorithms for Big Data Analytics 

      Berral García, Josep Lluís (Institute of Electrical and Electronics Engineers (IEEE), 2016)
      Conference report
      Open Access
      Big-data is an excellent source of knowledge and information from our systems and clients, but dealing with such amount of data requires automation, and this brings us to data mining and machine leaming techniques. In ...
    • A stochastic approach for automatic layout synthesis in interior design, using a learningbased scoring function 

      Racec, Emil (Universitat Politècnica de Catalunya, 2016-07-06)
      Master thesis
      Open Access
      Covenantee:   Interiorvista
      Despite the increasing capabilities of computers to master sophisticated human-like tasks and the recent explosive new wave of Machine Learning-based methods, the interior design field still remains a hard-to-master area, ...
    • A Survey on multimodal data stream mining for e-learner’s emotion recognition 

      Arijit, Nandi; Xhafa Xhafa, Fatos; Subirats, Laia; Fort, Santi (Institute of Electrical and Electronics Engineers (IEEE), 2020)
      Conference report
      Restricted access - publisher's policy
      Emotions play a crucial role in learning. To improve and optimize electronic learning (e-Learning) outcomes, many researchers have investigated the role of emotions. Also, researchers have come up with many approaches to ...
    • A workflow for the analysis and modelling of high-dimensional omics data 

      Otero Martín, Gerard (Universitat Politècnica de Catalunya, 2019-09)
      Bachelor thesis
      Open Access
      En los últimos años, los avances en el campo de la computación han convertido al Machine Learning en un método viable para obtener información muy precisa y hacer grandes predicciones relacionadas con todo el campo de la ...
    • Abstraction capabilities of deep neural networks while learning chess 

      Mitjans Coma, Carles (Universitat Politècnica de Catalunya / Universitat de Barcelona, 2018-10)
      Master thesis
      Open Access
      En aquest treball es fa un estudi detallat de les Xarxes Neuronals, especialment de les xarxes neuronals profundes. En la part pràctica, s'utilitzen xarxes neuronals convolucionals per crear programes capaços d'apendre a ...
    • Adaptive distributed mechanism againts flooding network attacks based on machine learning 

      Berral García, Josep Lluís; Poggi Mastrokalo, Nicolas; Alonso López, Javier; Gavaldà Mestre, Ricard; Torres Viñals, Jordi; Parashar, Manish (ACM Press, NY, 2008)
      Conference report
      Restricted access - publisher's policy
      Adaptive techniques based on machine learning and data mining are gaining relevance in self-management and self- defense for networks and distributed systems. In this paper, we focus on early detection and stopping of ...
    • Adaptive optics control with reinforcement learning: first steps 

      Pou Mulet, Bartomeu; Quiñones, Eduardo; Martín Muñoz, Mario (Barcelona Supercomputing Center, 2021-05)
      Conference report
      Open Access
      When planar wavefronts from distant stars traverse the atmosphere, they become distorted due to the atmosphere’s inhomogeneous temperature distribution. Adaptive Optics (AO) is the field in charge of correcting those ...
    • Advanced segmentation of the HORECA sector via artificial intelligence and machine learning 

      Canal Prat, Sergi (Universitat Politècnica de Catalunya, 2020-02-13)
      Bachelor thesis
      Restricted access - author's decision
      Covenantee:   UVE Solutions
      UVE Solutions, located in Manresa and Sant Cugat del Vallès, is a company that has been helping for more than a decade, Fast Moving Consumer Goods companies (FMGC) to improve the route that their products do from their ...
    • Advancements of vibration based damage detection techniques for small to medium span bridges 

      Moughty, John James; Casas Rius, Joan Ramon (2016)
      Conference report
      Restricted access - publisher's policy
      Overtime, the structural condition of bridges tends to decline due to a number of degradation processes, such as; creep, corrosion and cyclic loading, among others. Considerable research has been conducted over the years ...
    • An application of explainability methods in reinforcement learning 

      Climent Muñoz, Antoni (Universitat Politècnica de Catalunya, 2020-07-02)
      Bachelor thesis
      Open Access
      La popularidad de los métodos explicativos está aumentando en el contexto de la Inteligencia Artificial y consiste en dar explicaciones inteligibles a modelos complejos. Recientemente, en el contexto del Aprendizaje Reforzado ...
    • An autoencoder-based Solution for IQ constellation analysis 

      Morales López, Javier Roman (Universitat Politècnica de Catalunya, 2021-09-09)
      Bachelor thesis
      Open Access
      The continuous advances in technology and globalisation of humanity has made the use of communications an essential part of human lives. Nowadays, the advances in this field and the huge amount of data, structured and ...
    • Analysis and evaluation of No-Reference video quality assesment using neural networks 

      Arnoso Pérez, Roberto (Universitat Politècnica de Catalunya, 2021-07-14)
      Bachelor thesis
      Open Access
      The main goal of our project is: Analyze the performance of some networks, in order to see if it is capable of classifying, in terms of quality, different types of images. In a very generalized and simplified way, in this ...
    • Analysis and prediction of the Overall Equipment Effectiveness of manufacturing processes 

      Sánchez López, Sara (Universitat Politècnica de Catalunya, 2021-07-01)
      Bachelor thesis
      Open Access
      Covenantee:   Enginyeria Mapex
      Un dels majors objectius en la industria de la manufactura és disminuir els costos associats a la falta d'efectivitat de les màquines durant el procés de producció. Per poder realitzar un seguiment del progrés, la mètrica ...
    • Analysis of state-of-the-art deep generative models for images 

      Salvia Punsoda, Víctor (Universitat Politècnica de Catalunya, 2020-07)
      Bachelor thesis
      Open Access
      In this work we will try to break down the fundamentals of deep generative models for image generation. For the sake of simplicity and understanding we will be using the MNIST dataset, which can be easily trained and ...