Now showing items 1-13 of 13

    • A randomized algorithm for the exact solution of transductive support vector machines 

      Esposito, Gennaro; Martín Muñoz, Mario (2015-05-13)
      Article
      Open Access
      Random sampling is an efficient method for dealing with constrained optimization problems. In computational geometry, this method has been successfully applied, through Clarkson’s algorithm (Clarkson 1996), to solve a ...
    • Autoencoders for semi-supervised water level modeling in sewer pipes with sparse labeled data 

      Plana Rius, Ferran; Philipsen, Mark P.; Mirats Tur, Josep Maria; Moeslund, Thomas; Angulo Bahón, Cecilio; Casas, Marc (2022-01-24)
      Article
      Open Access
      More frequent and thorough inspection of sewer pipes has the potential to save billions in utilities. However, the amount and quality of inspection are impeded by an imprecise and highly subjective manual process. It ...
    • Development and usability assessment of an attention-based encoder for analysing Type-2 Diabetes primary care from a large population 

      Sallent Bayá, Jan (Universitat Politècnica de Catalunya, 2024-06-27)
      Bachelor thesis
      Open Access
      This study examines the evolution of a time series spanning the years 2019, 2020, and 2021, utilizing multiple routinely collected health care data points for approximately 1.5 million adults in Catalonia. The aim is to ...
    • Efficiently learning the system model for microservice-based applications 

      Macià Coll, Laura (Universitat Politècnica de Catalunya, 2023-09-04)
      Master thesis
      Open Access
      Covenantee:   Kungliga Tekniska högskolan
      Microservice-based applications are increasing in popularity. They offer numerous advantages and qualities (i.e., decentralized architecture, ease of monitoring and deployment, or scalability). However, controlling a ...
    • Improving fitness with data 

      Miquel Blasco, Carla (Universitat Politècnica de Catalunya, 2023-06-29)
      Bachelor thesis
      Open Access
      As an individual who has collected training activity data through Strava and Garmin APIs over the years, a substantial database has been amassed containing valuable information that has the potential to enhance performance ...
    • Multi-agent reinforcement learning in two-player zero-sum games 

      Paulo Molina, Marc (Universitat Politècnica de Catalunya, 2023-06-27)
      Bachelor thesis
      Open Access
      El principal objectiu d'aquest projecte és comparar com diferents algorismes d'Aprenentatge per Reforç aprenen a jugar a jocs de suma-zero. En concret, ens centrem en el joc del Connecta 4 (o Quatre en Ratlla). En primer ...
    • Object Detection and Weakly Supervised Semantic Segmentation for Grape Detection 

      Márquez Julbe, Pau (Universitat Politècnica de Catalunya, 2021-07-01)
      Bachelor thesis
      Open Access
      La recerca en intel·ligència artificial ha experimentat un creixement exponencial durant la última dècada. Degut a la rapidesa d'aquest creixement, moltes indústries no han tingut temps d'adaptar les seves metodologies més ...
    • Online motion recognition using an accelerometer in a mobile device 

      Fuentes, Daniel; González Abril, Luis; Angulo Bahón, Cecilio; Ortega Ramírez, Juan Antonio (2012)
      Article
      Open Access
      This paper introduces a new method to implement a motion recognition process using a mobile phone fitted with an accelerometer. The data collected from the accelerometer are interpreted by means of a statistical study and ...
    • Robot Learning from Demonstration with Gaussian Processes 

      Arduengo García, Miguel (Universitat Politècnica de Catalunya, 2021-06-21)
      Master thesis
      Open Access
      Autonomous systems are no longer confined to factories, but they are progressively spreading to urban, social, and assistive domains. However, in order to become handy co-workers and helpful assistants, robots must be ...
    • Robot Learning from Demonstration with Gaussian Processes 

      Arduengo García, Miguel (Universitat Politècnica de Catalunya, 2021-06-21)
      Master thesis
      Open Access
      Autonomous systems are no longer confined to factories, but they are progressively spreading to urban, social, and assistive domains. However, in order to become handy co-workers and helpful assistants, robots must be ...
    • Search & analysis of new heuristics for solving NP-HARD problems with Deep Reinforcement Learning 

      Osarte Segura, Tomàs (Universitat Politècnica de Catalunya, 2024-06-26)
      Bachelor thesis
      Open Access
      La tesi se centra en l'ús de l'aprenentatge profund per reforç (DRL) per resoldre problemes NP-difícils (NPH), coneguts per la seva complexitat computacional. Aquests problemes són difícils de resoldre amb mètodes tradicionals, ...
    • Semi-supervised learning for disabilities detection on English and Spanish biomedical text 

      Medina Herrera, Salvador; Turmo Borras, Jorge; Loharja, Henry; Padró, Lluís (2018)
      Conference report
      Open Access
      This paper describes the disability detection model approaches presented by UPC’s TALP 3 team for the DIANN 2018 shared task. The best of those approaches was ranked in 3rd place for exact-matching of disability detection. ...
    • User behavioral segmentation based on Math Input 

      Qiu Lo, Henry (Universitat Politècnica de Catalunya, 2020-12-14)
      Master thesis
      Restricted access - confidentiality agreement