Abstract
Forgetting is often considered a malfunction of intelligent agents; however, in a changing world forgetting has an essential advantage. It provides means of adaptation to changes by removing effects of obsolete (not necessarily old) information from models. This also applies to intelligent systems, such as recommender systems, which learn users' preferences and predict future items of interest. In this work, we present unsupervised forgetting techniques that make recommender systems adapt to changes of users' preferences over time. We propose eleven techniques that select obsolete information and three algorithms that enforce the forgetting in different ways. In our evaluation on real-world datasets, we show that forgetting obsolete information significantly improves predictive power of recommender systems.

Abstract
The classification of retinal vessels into arteries and veins in eye fundus images is a relevant task for the automatic assessment of vascular changes. This paper presents a new approach to solve this problem by means of a Fully-Connected Convolutional Neural Network that is specifically adapted for artery/vein classification. For this, a loss function that focuses only on pixels belonging to the retinal vessel tree is built. The relevance of providing the model with different chromatic components of the source images is also analyzed. The performance of the proposed method is evaluated on the RITE dataset of retinal images, achieving promising results, with an accuracy of 96 % on large caliber vessels, and an overall accuracy of 84 %. © 2018, Springer International Publishing AG, part of Springer Nature.

Abstract
As in many other combinatorial optimisation problems, research on nesting problems (aka irregular packing problems) has evolved around the dichotomy between continuous (time consuming) and discrete (memory consuming) representations of the solution space. Recent research has been devoting increasing attention to discrete representations for the geometric layer of nesting problems, namely in mathematical programming-based approaches. These approaches employ conventional regular meshes, and an increase in their precision has a high computational cost. In this paper, we propose a data structure to represent non-regular meshes, based on the geometry of each piece. It supports non-regular discrete geometric representations of the shapes, and by means of the proposed data structure, the discretisation can be easily adapted to the instances, thus overcoming the precision loss associated with discrete representations and consequently allowing for a more efficient implementation of search methods for the nesting problem. Experiments are conducted with the dotted-board model - a recently published mesh-based binary programming model for nesting problems. In the light of both the scale of the instances, which are now solvable, and the quality of the solutions obtained, the results are very promising.

Abstract
Apresenta o Modelo de Gestão do Sistema de Informação Ativa e Permanente (MGSI-AP), resultado de uma investigação que discutiu conceitos e perspetivas em torno da Gestão da Informação, posicionou-a como área transversal e aplicada em Ciência da Informação, com foco no(s) fluxo(s) infocomunicacional(ais), atendendo de forma particular aos que ocorrem em meio digital, no contexto de uma instituição complexa – a universidade pública portuguesa – e respetivos serviços de informação. Aborda um dos eixos da operacionalização da investigação realizada e do modelo desenvolvido. Nele se destaca a estreita ligação da Gestão da Informação à área de estudo da Produção Informacional. A universidade, foco do estudo, é abordada numa dupla faceta sistémica e, consequentemente, complexa, isto é, entre o sistema organizado formal e o sistema combinatório de feição loosely coupled. A formulação de uma proposta teórico-metodológica e de modelação operacional convergiram para uma definição de Gestão da Informação.

Abstract

Abstract
Over the last years, Deep Learning has become one of the most popular research fields of Artificial Intelligence. Several approaches have been developed to address conventional challenges of AI. In computer vision, these methods provide the means to solve tasks like image classification, object identification and extraction of features. In this paper, some approaches to face detection and recognition are presented and analyzed, in order to identify the one with the best performance. The main objective is to automate the annotation of a large dataset and to avoid the costy and time-consuming process of content annotation. The approach follows the concept of incremental learning and a R-CNN model was implemented. Tests were conducted with the objective of detecting and recognizing one personality within image and video content. Results coming from this initial automatic process are then made available to an auxiliary tool that enables further validation of the annotations prior to uploading them to the archive. Tests show that, even with a small size dataset, the results obtained are satisfactory. © 2020, Springer Nature Switzerland AG.