Ara es mostren els items 1-20 de 67

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

      Perez Granero, Pol (Universitat Politècnica de Catalunya, 2020-06)
      Treball Final de Grau
      Accés obert
      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 ...
    • A machine learning based recommendation system for furniture selection 

      Manresa Román, Maria Isabel (Universitat Politècnica de Catalunya, 2022-07-04)
      Treball Final de Grau
      Accés obert
      Artificial Intelligence (AI) is one of today's fastest growing technologies, and has been evolving for decades. It allows machines to have the ability to "learn", and self-correct. This technology is used in many fields, ...
    • A new deep reinforcement learning architecture for autonomous UAVs 

      Muñoz Ferran, Guillem (Universitat Politècnica de Catalunya, 2018-09-07)
      Treball Final de Grau
      Accés obert
      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 ...
    • AI based cover image generation for music albums : the study of AI techniques for generating images 

      Campobadal Forés, Kiriam (Universitat Politècnica de Catalunya, 2023-07-20)
      Treball Final de Grau
      Accés obert
      Introdueix els principals conceptes de xarxes neuronals, Stable Diffusion i NLP per tal de desenvolupar un sistema amb una arquitectura de disseny que combini tots aquests conceptes. Aquest sistema consisteix en una ...
    • An advanced AI chess engine based on ML 

      Montore Ramírez, Marc (Universitat Politècnica de Catalunya, 2021-10-27)
      Treball Final de Grau
      Accés obert
      Chess is one of the most loved and at the same time difficult board games in history. During these last decades, a variety of chess engines have achieved levels of play humans could never reach, and using various methods ...
    • An autoencoder-based Solution for IQ constellation analysis 

      Morales López, Javier Roman (Universitat Politècnica de Catalunya, 2021-09-09)
      Treball Final de Grau
      Accés obert
      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 ...
    • Applicability and Limitations of the SWASH model to predict wave overtopping 

      Martínez Pés, Víctor (Universitat Politècnica de Catalunya / Technische Universiteit Delft, 2013-11-25)
      Tesina
      Accés obert
      The main aim of this minor thesis is to evaluate if we can accurately predict the mean wave overtopping discharge in rubble mound breakwaters with the tools we currently have. In first place, the available methods (Eurotop ...
    • Application of classification methods in business intelligence 

      Hashemi, Seyedpedram (Universitat Politècnica de Catalunya / Universitat de Barcelona, 2017-10)
      Projecte Final de Màster Oficial
      Accés restringit per decisió de l'autor
      In past few years, many start-ups have started working. The few that survive make very important decisions by exploiting available data. This has amplified the importance of Business Intelligence and their tools, which ...
    • Artificial Inteligence applications in 5G networks 

      Lladós Gómez, Guillem (Universitat Politècnica de Catalunya, 2020-10-19)
      Projecte Final de Màster Oficial
      Accés obert
      This project presents an analysis on one application of Artificial Intelligent in 5G networks. It analyzes how slicing can be improved using Deep Learning through the creation of two different systems. The first system is ...
    • Artificial intelligence for aircraft predictive maintenance 

      Garreta Piñol, Bernat (Universitat Politècnica de Catalunya, 2022-10-20)
      Projecte Final de Màster Oficial
      Accés obert
      Realitzat a/amb:   DMD Aeronautics Engineering SL
      At first, the goal of this project was threefold: create the first version of a working interface, obtain more data to train the algorithm, and improve the performance of the deep learning classifier. Basically, to build ...
    • Artificial Intelligence for obstacles detection using IR camera images 

      Mercade Laborda, Sergi (Universitat Politècnica de Catalunya, 2019-06)
      Treball Final de Grau
      Accés restringit per decisió de l'autor
    • Clustering and visualization of Lithium-Ion battery data for second life applications 

      Domínguez Piernas, Gabriel (Universitat Politècnica de Catalunya, 2023-06-27)
      Treball Final de Grau
      Accés obert
      L'ús de bateries de segona vida és una de les estratègies més prometedores per a resoldre el problema del reciclatge de piles en el futur. L'objectiu d'aquesta recerca és aportar solucions pràctiques de garbellat, reagrupació ...
    • Clustering of images using Generative Adversarial Networks 

      Marín Ciudad, Eloy (Universitat Politècnica de Catalunya, 2020-07)
      Treball Final de Grau
      Accés obert
      Realitzat a/amb:   Universitetet i Linköping
      Recently, a variation of GANs, called ClusterGAN, has shown the ability to perform unsupervised classification of images according to content thanks to the use of a discrete-continuous latent space and a clustering-specific ...
    • Comparación de la explicación obtenida con modelos de explicabilidad para diferentes métodos de Reinforcement Learning 

      Rivera Hernández, Javier (Universitat Politècnica de Catalunya, 2022-06-28)
      Treball Final de Grau
      Accés obert
      El creciente uso de las tecnologías de Inteligencia Artificial para proveer productos y servicios destinados a humanos ha aumentado el interes en como estas tecnologías toman decisiones que pueden tener un grave impacto ...
    • Computational-efficient flora and fauna recognition 

      Solergibert i Llaquet, Antoni-Joan (Universitat Politècnica de Catalunya, 2022-07-04)
      Treball Final de Grau
      Accés obert
      One of the main characteristics of Neural Networks is that they are data-hungry, which means that in order to simply learn the difference between a lemon and a tennis ball require thousands of examples. If it is already ...
    • Connections between kernel methods and deep neural networks 

      Mulet Arabí, Pau (Universitat Politècnica de Catalunya, 2021-07)
      Treball Final de Grau
      Accés obert
      This thesis aims to study recent theoretical work in machine learning research that seeks to better understand neural networks by finding connections with kernels. The main goal is to describe the predictor s space of ...
    • Data analysis of socio-economic and financial factors from a public world-wide source 

      Calvo Fantova, Santiago (Universitat Politécnica de Catalunya / Universitat Politècnica de Catalunya, 2020-01-27)
      Projecte Final de Màster Oficial
      Accés obert
      Many socio-economic studies are nowadays trying to accomplish a complete description of how the different elements of our society and world are connected. This work is an attempt to build an architecture that provides an ...
    • Data-driven analysis of the thermal behavior of a logistic warehouse 

      Calvo De La Iglesia, Àngel (Universitat Politècnica de Catalunya, 2022-07-07)
      Projecte Final de Màster Oficial
      Accés obert
      El present Treball de Final de Màster té com objectiu millorar el coneixement previ sobre el comportament tèrmic d'un gran magatzem per a reduir el seu consum energètic i millorar el confort tèrmic dels seus ocupants. ...
    • Decyphering the Geheimschreiber, a machine learning approach 

      Closa Márquez, Oriol (Universitat Politècnica de Catalunya, 2019-06-28)
      Treball Final de Grau
      Accés restringit per decisió de l'autor
      Realitzat a/amb:   Kungliga Tekniska högskolan
      A Suècia, la Siemens and Halske T52 va ser utilitzada pels alemanys durant la Segona Guerra Mundial. Una recreació de la màquina s'ha construït virtualment i diversos texts alemanys han estat xifrats. Les tècniques ...
    • Deep learning and domain adaptation for autism spectrum disorder youth aggressive episode prediction 

      Antona i Pizà, Héctor (Universitat Politècnica de Catalunya, 2022-07)
      Treball Final de Grau
      Accés restringit per acord de confidencialitat
      Realitzat a/amb:   Northeastern University
      Els joves amb Trastorn de l'Espectre Autista (TEA) sovint presenten un comportament impredictible i agressiu cap a altres persones o fins i tot cap a ells mateixos, aïllant-los de les activitats socials i educatives del ...