Now showing items 1-20 of 89

    • A comparison study of U-Net based methods for brain tumor segmentation 

      Ferrando Garrido, Albert (Universitat Politècnica de Catalunya, 2023-10-19)
      Master thesis
      Open Access
      Covenantee:   Universitat de Barcelona
      The brain tumor segmentation (BraTS) Challenge is an international competition that focuses on the task of automated segmentation of the different parts of brain tumors in magnetic resonance imaging (MRI) scans. U-Net ...
    • A confusion matrix for evaluating feature attribution methods 

      Arias Duart, Anna; Mariotti, Ettore; Garcia Gasulla, Dario; Alonso Moral, Jose Maria (Institute of Electrical and Electronics Engineers (IEEE), 2023)
      Conference lecture
      Open Access
      The increasing use of deep learning models in critical areas of computer vision and the consequent need for insights into model behaviour have led to the development of numerous feature attribution methods. However, these ...
    • A Deep Learning Based Tool For Ear Training 

      Nogales Pérez, David (Universitat Politècnica de Catalunya, 2023-05-16)
      Bachelor thesis
      Open Access
      L'objectiu principal d'aquest projecte és utilitzar tècniques d'aprenentatge profund per desenvolupar una eina capaç de generar exercicis de dictat melòdic significatius perquè els professors de música i els seus estudiants ...
    • Acoustic classification of marine mammals by deep learning 

      Cavero Carreras, Pol (Universitat Politècnica de Catalunya, 2023-09-14)
      Master thesis
      Open Access
      The classification of marine mammals has been an important topic for monitoring their population numbers. Many species of whales are considered endangered, making this task even more imperative. In this thesis two species ...
    • Acoustic detection of marine mammals by deep learning 

      Casals I Salvador, Marc (Universitat Politècnica de Catalunya, 2023-10-18)
      Master thesis
      Open Access
      In oceanography, specifically in the study of whales, the classification of the different species is an essential task for passive acoustic observation. It is fundamental for the tracking of some species that have become ...
    • Age & Gender Recognition in The Wild 

      Bonet Cervera, Emili (Universitat Politècnica de Catalunya, 2022-06-28)
      Bachelor thesis
      Open Access
      L'estimació de grups demogràfics a partir d'imatges, i en particular pel que fa a l'estimació d'edat i sexe, és un sector amb un ampli ventall d'aplicacions. Tanmateix, l'estat de l'art actual està poc encarat a escenaris ...
    • Analysis of Visually-aware recommender systems 

      Vicol, Valeriu (Universitat Politècnica de Catalunya, 2023-01-23)
      Master thesis
      Open Access
      Covenantee:   Universitat de Barcelona / Universitat Rovira i Virgili
      Modern recommender systems had their roots in the early 1990s when they were primarily used experimentally for information filtering and personal email. Person- alized recommendations are commonplace today, 30 years later, ...
    • Analysis the use of large language model for automated program repair 

      Torrens Punsola, Marc (Universitat Politècnica de Catalunya, 2023-06-29)
      Bachelor thesis
      Restricted access - confidentiality agreement
      Automated program repair (APR) is a research field that develops multiple techniques to fix software bugs automatically. For a long time, the proposed solutions were based on heuristics and patterns, but since the appearance ...
    • Análisis y diseño de Dataset para el reconocimiento de COVID-19 en señales de tos con Redes Neuronales Profundas 

      Sánchez Bergés, Marc (Universitat Politècnica de Catalunya, 2022-05-23)
      Bachelor thesis
      Open Access
      This project will try to improve the detection results of the COVID-19 disease as much as possible from acoustic signals of coughing through a convolutional neural network. To accomplish these objectives, we started with ...
    • Applying artificial intelligence models for the automatic forest fire detection 

      El Madafri, Ismail; Peña Carrera, Marta; Olmedo Torre, Noelia (OmniaScience, 2023-03)
      Conference lecture
      Open Access
      Throughout the past decade, the development of Artificial Intelligence-based devices for the automatic detection of early stage forest fires has been a growing focus. Computer Vision techniques are well-suited for this ...
    • Automatic deep learning-based pipeline for automatic delineation and measurement of fetal brain structures in routine mid-trimester ultrasound images 

      Coronado Gutiérrez, David; Eixarch Roca, Elisenda; Monterde, Elena; Matas Barceló, Isabel; Traversi, Paola; Gratacós Solsona, Eduard; Bonet Carné, Elisenda; Burgos Artizzu, Xavier Paolo (Karger, 2023-08-11)
      Article
      Open Access
      Introduction: The aim of this study was to develop a pipeline using state-of-the-art deep learning methods to automatically delineate and measure several of the most important brain structures in fetal brain ultrasound ...
    • Autonomous flow routing for near real-time quality of service assurance 

      Barzegar, Sima; Ruiz Ramírez, Marc; Velasco Esteban, Luis Domingo (2024/04)
      Article
      Open Access
      The deployment of beyond 5G and 6G network infrastructures will enable highly dynamic services requiring stringent Quality of Service (QoS). Supporting such combinations in today’s transport networks will require high ...
    • Brain Age Prediction from Structural Magnetic Resonance Imaging using Deep Learning 

      Garriga Artieda, Daniel (Universitat Politècnica de Catalunya, 2023-07-07)
      Master thesis
      Open Access
      Brain-age delta, a biomarker based on the brain-age prediction from neuroimaging data, has garnered significant attention in recent years. In this project, a deep learning model for brain age prediction is going to be ...
    • Building a CT Image Analysis Database for Postoperative Endometrial Carcinoma to Enhance Radiotherapy Treatment Planning 

      Orío Tejada, Sara (Universitat Politècnica de Catalunya, 2023-05-30)
      Master thesis
      Restricted access - confidentiality agreement
      Covenantee:   Universitat de Barcelona. Facultat de Medicina i Ciències de la Salut
      Endometrial cancer is a prevalent type of gynecological tumor in women that arises in the uterus, specifically in the endometrium, the inner lining of the uterus. Treatment often involves surgical removal of the uterus ...
    • Clustering for unsupervised image segmentation 

      Bercowsky Rama, Andrés Eduardo (Universitat Politècnica de Catalunya, 2023-09-01)
      Bachelor thesis
      Open Access
      Covenantee:   Eidgenössische Technische Hochschule Zürich
      Unsupervised and self-supervised semantic segmentation has made significant advances in recent years in identifying and labeling regions of an image based on their appearance and context without the need for manual annotations ...
    • Computer vision tools for the automatic evaluation of collagen VI deficiencies 

      Ramírez i Márquez, Alex (Universitat Politècnica de Catalunya, 2022-01-24)
      Master thesis
      Open Access
      Deficiencies in the structure of collagen VI are a common cause of neuromuscular diseases. Such diseases typically require assisted ventilation and result in a severely reduced life expectancy. Collagen VI structural defects ...
    • Control de producción en invernadero mediante aprendizaje por refuerzo 

      Yin, Wenjie (Universitat Politècnica de Catalunya, 2022-07-13)
      Master thesis
      Open Access
      En este proyecto, se estudia, diseña y simula agentes de aprendizaje profundo por refuerzo para controlar el clima interior de un invernadero en un modelo de invernadero de lechugas que tiene incertidumbre en la predicción ...
    • Deep learning based computer vision for aerial-view street object detection and classification 

      Coll Josifov, Richard (Universitat Politècnica de Catalunya, 2022-07-14)
      Bachelor thesis
      Open Access
      This project consists of the training of a convolutional neural network based on the YOLO approach for the systematic detection and classification of objects in a street as seen from a drone flying over them, to then be ...
    • Deep Learning for Demographic Classification by Speech 

      Navarrete Jiménez, Daniel (Universitat Politècnica de Catalunya, 2022-10-26)
      Master thesis
      Open Access
      Speech characterization is a challenging task and one of the most relevant challenges in AI. Moreover, it is a field of study with minimal scope in the Catalan language. In this work, we try to perform a demographic ...
    • Deep learning for image super resolution 

      Rojas Sedó, Pablo (Universitat Politècnica de Catalunya, 2022-01-31)
      Bachelor thesis
      Open Access
      Covenantee:   Infaimon
      Super-resolution is a popular computer vision task that aims to enhance an image by increasing its resolution. The countless possibilities for applications with this technology and the recent success of deep learning in ...