We propose a new unsupervised approach for the discovery of routine from egocentric photostreams. The method integrates Convolutional Neural Networks for image feature extraction with Latent Dirichlet Allocation to find ...

In this work a data pipe-line to manage and extract patterns from time-series is described. The patterns found with a combination of Conditional Restricted Boltzmann Machine (CRBM) and k-Means algorithms are then validated ...

Information diffusion in large-scale networks has been studied to identify the users influence. The influence has been targeted as a key feature either to reach large populations or influencing public opinion. Through the ...

Achieving the equilibrium between scalability, sustainability, and security while keeping decentralization has prevailed as the target solution for decentralized blockchain applications over the last years. Several approaches ...

Network topology is a physical description of the overall resources in the network. Collecting this information using efficient mechanisms becomes a critical task for important network functions such as routing, network ...

The general aim is to promote the use of individual- based models (biological agent-based models) in teaching and learning contexts in life sciences and to make their progressive incorporation into academic curricula ...

Pre-training Reinforcement Learning (RL) agents in a task-agnostic manner has shown promising results. However, previous works still struggle to learn and discover meaningful skills in high-dimensional state-spaces. We ...

Covid-19 urges a deeper understanding of the underlying molecular mechanisms involved in illness progression to provide a prompt therapeutical response with an adequate use of available drugs, including drug repurposing. ...

SARS-CoV-2 is a type of coronavirus responsible for the international outbreak of respiratory illness termed COVID-19 that forced the World Health Organization to declare a pandemic infectious disease situation of international ...

Mutants of Ras are oncogenic drivers of a large number of human tumors. Despite being recognized as an attractive target for the treatment of cancer, the high affinity for its substrate tagged the protein as undruggable ...