University of Vigo

This work introduces CyTRACK (Cyclone TRACKing framework), a new open-source, comprehensive and user-friendly Python toolbox for detecting and tracking cyclones in model and reanalysis datasets. The kernel of CyTRACK is based on detecting ...

• CyTRACK is an open-source and user-friendly toolbox for tracking cyclones.
• It can capture cyclone frequency, lifetime and spatial distribution.
• It is useful for case or climatological studies of cyclone features.

In this paper, a strain gradient thermoelastic problem is studied from the numerical point of view. The heat conduction is modeled by using the type II thermal law and the second gradient of the thermal displacement is also included in the set of ...

We present a novel semi-implicit hybrid finite volume/finite element (FV/FE) method for the equations of viscous and resistive incompressible magnetohydrodynamics (MHD). The scheme preserves the divergence-free property of the magnetic field ...

Federated Learning (FL) has emerged as a revolutionary machine learning setting to enable collaborative training in a privacy-preserving way. However, recent research has showcased significant privacy attacks that pose a serious threat to the ...

Forensic image source attribution aims at deciding whether a query image was taken by a specific camera. While various algorithms leveraging forensic traces have been proposed, the most effective techniques rely on Photo Response Non-Uniformity (PRNU), a ...

Welcome to the 12th ACM Information Hiding and Multimedia Security Workshop - IH&MMSec'24 in Baiona, Galicia, Spain, organized by the Research Group in Signal Processing in Communications (GPSC) at the University of Vigo. GPSC is one of the pioneering ...

Semantic segmentation is one of the most important and studied problems in machine vision, which has been solved with high accuracy by many deep learning models. However, all these models present a significant drawback, they require large and ...

This paper presents a link abstraction model and ns-3 implementation of Successive Interference Cancellation (SIC) decoding for the uplink of a mmwave 5G network supporting Space Division Multiple Access (SDMA). The link abstraction model relies on the ...

Decentralized machine learning has recently been proposed as a potential solution to the security issues of the canonical federated learning approach. In this paper, we propose a decentralized and collaborative machine learning framework ...

• This paper introduces an algorithm for resource-limited devices in IoT deployments.
• Two incremental learning mechanisms are proposed: a full ILVQ and a hybrid approach.
• Two sharing protocols are proposed: a random and a performance-...

Social media platforms enable the rapid dissemination and consumption of information. However, users instantly consume such content regardless of the reliability of the shared data. Consequently, the latter crowdsourcing model is exposed to ...

Image generative models have advanced in many areas to produce synthetic images of high resolution and detail. This success has enabled its use in the biomedical field, paving the way for the generation of videos showing the biological evolution of its ...

In this paper, we study, from both an analytical and a numerical point of view, a poro-thermoelastic problem with microtemperatures. The so-called Moore–Gibson–Thompson equation is used to model the contribution for the temperature and ...

Medical image landmark detection can automatically determine the pre-set position coordinates in medical images, so as to further assist disease diagnosis and treatment planning. Using Convolutional Neural Network (CNN) to estimate the heatmap of ...

• Feature decouple and gated recalibration network improves the medical image landmark detection.
• A new dynamic multi-kernel convolution as decouple module’s basic component to decouple features.
• Gated feature recalibration module ...

A novel staggered semi-implicit finite volume method for the simulation of one-dimensional blood flow in networks of elastic and viscoelastic vessels is proposed. The one-dimensional blood flow model is split into three subsystems: one containing ...

• Novel semi-implicit finite volume method for blood flow in networks of compliant vessels.
• Tube law for arteries and veins accounting also for visco-elastic effects.
• Splitting of the PDE into a convective, a viscous and a pressure ...

Background: We address the problem of determining the controllability and accessibility of nonlinear biosystems. We consider models described by affine-in-inputs ordinary differential equations, which are adequate for a wide array of biological ...

• Clarification of the applicability of several accessibility/controllability tests.
• Method for the analysis of accessibility/controllability of nonlinear biosystems.
• Implementation as an open source Matlab tool.
• Applied to ...

Robots are flexible machines, where the flexibility is achieved, mainly, by the re-programming of the robotic system. To fully exploit the potential of robotic systems, an easy, fast, and intuitive programming methodology is desired. By applying ...

• A novel hierarchical classification of manipulation activities is proposed.
• Sensor fusion to recognize manipulation operations using Markov Models.
• Multiorder Multivariate Markov Models optimization to improve operations ...

• Comprehensive review of collaborative inference on convolutional neural networks under the mobile cloud computing paradigm.
• Thorough analysis and comparison of the most relevant co-inference frameworks, covering the underlying workflow ...

This work analyses the most relevant research conducted under the mobile cloud computing paradigm to bring vision tasks supported by state-of-the-art deep convolutional neural networks closer to the end-user through collaborative intelligence. In ...