This thesis proposes a novel active learning framework capable to train effectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of training labeled data. Our approach ...

[ANGLÈS] How can we build a system for traffic classification so that different QoS levels can be identified? How can we analyse different network parameters and identify a specific QoS for every flow? The purp ose of ...

Català: Avui en dia la vigilancia de grans àreas, com ara bancs, aeroports o ciutats es basa principalment en sistemas de video. Les Active Cameras (ACs) juguen un paper important per als sistemes de seguretat, ja que ...

This work considers the learning of algorithmic tasks by mere observation of input-output pairs. Rather than studying this as a black-box discrete regression problem with no assumption whatsoever on the input-output mapping, ...

The goal of the project is to implement, using the Xilinx MicroBlaze microprocessor embedded and a wireless communications module eZ430-RF2500T Texas Instruments system, that allows building a distributed sensor network. ...

Integration of M2M Networks into Companies' Administrative Networks.

[ANGLÈS] In this work we design and implement a modular system for consumption monitoring and control by focusing on the specific case of the electric energy. Both monitoring and remote control can be achieved from any ...

The purpose of this project is to achieve a system capable of analysing video sequences of popular races, detecting all the runners, tracking them in order to know their position at all times and increasing the number of ...