Browsing Universitat de Barcelona by Subject "004"

Adapting by copying. Towards a sustainable machine learning

Unceta, Irene (Date of defense: 2021-03-01)

Despite the rapid growth of machine learning in the past decades, deploying automated decision making systems in practice remains a challenge for most companies. On an average day, data scientists face substantial barriers ...

Boosting the Artificial Intelligence solutions training phase by means of process simulation methods

Abió Rojo, Albert (Date of defense: 2025-05-13)

[eng] Despite the emergence of Industry 4.0 and the rise of a data-driven manufacturing paradigm, the acquisition of valuable data in a cost-efficient and sustainable manner for manufacturing processes remains a challenge ...

Bridging Natural Language and Hierarchical Multivariate Data Visualisation to Support Data Analysis

Kavaz, Ecem (Date of defense: 2025-04-23)

[eng] Tracking and analysing the vast amounts of data generated from social networks and digital platforms presents important challenges, not only due to the overwhelming volume but also the complex relationships embedded ...

Deep Learning and Uncertainty Modeling in Visual Food Analysis

Aguilar, Eduardo (Date of defense: 2020-09-23)

Several computer vision approaches have been proposed for tackling food analysis problems, due to the challenging problem it poses, the ease collection of food images, and its numerous applications to health and leisure. ...

Deep Learning Approaches for Human Activity Understanding

Zhang, Zejian (Date of defense: 2025-06-12)

[eng] Understanding human activities is crucial for developing practical applications that benefit society. Temporal action localization (TAL) in untrimmed videos is one of the most challenging tasks in this field. While ...

Deep Learning-based Solutions to Improve Diagnosis in Wireless Capsule Endoscopy

Laiz Treceño, Pablo (Date of defense: 2023-12-12)

[eng] Deep Learning (DL) models have gained extensive attention due to their remarkable performance in a wide range of real-world applications, particularly in computer vision. This achievement, combined with the increase ...

End-to-End AI Solutions for Capsule Endoscopy: Enhancing Efficiency and Accuracy in Gastrointestinal Diagnostics

Gilabert Roca, Pere (Date of defense: 2025-01-22)

[eng] Artificial Intelligence (AI) models are fundamentally transforming the way clinicians carry out their daily tasks. By streamlining various processes, AI offers a more robust and consistent method for reviewing ...

Estudio del estado actual, proyecto de formación y perspectivas del futuro de la informática farmacéutica

Gratacòs-Roig, Jordi (Date of defense: 1990-01-01)

Presentar una tesis doctoral sobre informática, sea el campo de conocimiento que sea, tiene un elevado riesgo debido a los imparables avances que se producen a diario, y lo que se dice hoy mañana está anticuado. El ámbito ...

From pixels to gestures: learning visual representations for human analysis in color and depth data sequences

Hernández-Vela, Antonio (Date of defense: 2015-03-09)

The visual analysis of humans from images is an important topic of interest due to its relevance to many computer vision applications like pedestrian detection, monitoring and surveillance, human-computer interaction, ...

Generalizability in multi-centre cardiac image analysis with machine learning

Campello Román, Víctor Manuel (Date of defense: 2023-12-15)

[eng] The field of Artificial Intelligence (AI) has undergone a revolution in recent years with the advent of more efficient computing hardware and well-documented software for model development. Many fields are being ...

Modelling Uncertainty in Black-box Classification Systems

Mena Roldán, José (Date of defense: 2020-12-15)

Currently, thanks to the Big Data boom, the excellent results obtained by deep learning models and the strong digital transformation experienced over the last years, many companies have decided to incorporate machine ...

Optimization of neural networks for deep learning and applications to CT image segmentation

Pezzano, Giuseppe (Date of defense: 2023-07-27)

[eng] During the last few years, AI development in deep learning has been going so fast that even important researchers, politicians, and entrepreneurs are signing petitions to try to slow it down. The newest methods for ...

Paper d'Internet en la cultura emergent del món actual (1945-2003), El. Instal·lacions interactives, Net.Art i hipertextos en línia com a estudis de cas

Campàs Montaner, Joan (Date of defense: 2005-04-28)

Es tracta d'una recerca d'història que s'aplica al camp de la producció artística i literària en xarxa i que pretén explicar com apareix, es desenvolupa, es consolida i es legitima un nou camp cultural, com el mode de ...