Enviaments recents

  • Probabilistic methods for furnishing bedrooms in interior design: Bayesian Networks for occurrence modeling and GMMs for furnishing arrangement 

    Budulan, Stefania (Universitat Politècnica de Catalunya, 2016-07-06)
    Projecte Final de Màster Oficial
    Accés obert
    Realitzat a/amb:  University Politehnica of Bucharest
    Tasks in architectural and interior design range from defining the building floor plans and ensuring desired functionality, to deciding furnishing styles and arrangement choices; all to best fit certain pre-established ...
  • A stochastic approach for automatic layout synthesis in interior design, using a learningbased scoring function 

    Racec, Emil (Universitat Politècnica de Catalunya, 2016-07-06)
    Projecte Final de Màster Oficial
    Accés obert
    Realitzat a/amb:  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, ...
  • Convolutional neural networks for style classification 

    Oliver, Philipp (Universitat Politècnica de Catalunya, 2016-06-28)
    Projecte Final de Màster Oficial
    Accés obert
    Realitzat a/amb:  Universitat de Barcelona
    In recent years convolutional neural networks have enjoyed great success. Especially in the field of object recognition great leaps forward have been made. Researchers were able to exploit the object detection features ...
  • Investigating prognostic factors in sepsis using computational intelligence methods 

    Morales Boada, Carles (Universitat Politècnica de Catalunya, 2016-10)
    Projecte Final de Màster Oficial
    Accés obert
    Sepsis is a major challenge in medicine. It is in fact a traversal condition affecting people of all ages and is not respectful of lifestyle choices. There are many diseases in medicine whose definition is uncertain and ...
  • Convolutional neural networks for malware classification 

    Gibert Llauradó, Daniel (Universitat Politècnica de Catalunya, 2016-10-20)
    Projecte Final de Màster Oficial
    Accés obert
    According to AV vendors malicious software has been growing exponentially last years. One of the main reasons for these high volumes is that in order to evade detection, malware authors started using polymorphic and ...
  • Study of possible applications of AI Techniques to SEAT Manufacturing IT 

    Muñoz Mellado, David (Universitat Politècnica de Catalunya, 2016-10-20)
    Projecte Final de Màster Oficial
    Accés restringit per acord de confidencialitat
    Realitzat a/amb:  Seat
    In order to survive in such an extreme competitive market as the car manufacturing industry is, automobile companies have traditionally invest a considerable amount of resources and effort in using innovative solutions ...
  • From training to match performance: an exploratory and predictive analysis on F.C. Barcelona GPS data 

    Fernández, Javier (Universitat Politècnica de Catalunya, 2016-10)
    Projecte Final de Màster Oficial
    Accés obert
    An exploratory and predictive analysis on GPS data is presented. Physical performance variables from professional football players are analysed in a holistic approach that involves data exploration, analysis of adaptation ...
  • AI and Prosthetics 

    Kyriazi, Nefeli Evdokia (Universitat Politècnica de Catalunya, 2016-07-06)
    Projecte Final de Màster Oficial
    Accés obert
    Prosthetics are very important to an amputee.The introduction of technology to prosthetics has allowed bionic limbs to emerge and change the way we were thinking about prosthetic limbs.More and more companies create new ...
  • Human Pose Estimation with CNNs and LSTMs 

    Coskun, Huseyin (Universitat Politècnica de Catalunya, 2016-08-15)
    Projecte Final de Màster Oficial
    Accés obert
    Realitzat a/amb:  Technische Universität München
    In this thesis, we present an end-to-end approach to human pose estimation task that based on a deep hybrid architecture that combines convolutional neural network (CNNs) and recurrent neural networks (RNNs).
  • Efficient recognition approaches for the interaction between humans and aerial robots 

    Hernández Ruiz, Alejandro José (Universitat Politècnica de Catalunya, 2016-04-20)
    Projecte Final de Màster Oficial
    Accés obert
    This project consists in a set of computer vision methods that serve as a baseline to perform HRI experiments. The methods are aimed to perform: visual marker detection, face detection and object recognition. Then we tested ...

Mostra'n més