Abstract

Abstract
Portfolio optimization in stock markets has been investigated by many researchers. It looks for a subset of assets able to maintain a good trade-off control between risk and return. Several algorithms have been proposed to portfolio management. These algorithms use known return and correlation data to build subset of recommended assets. Dynamic stock correlation networks, whose vertices represent stocks and edges represent the correlation between them, can also be used as input by these algorithms. This study proposes the definition of constants of the classical mean-variance analysis using machine learning and weighted link prediction in stock networks (method named as MLink). To assess the performance of MLink, experiments were performed using real data from the Brazilian Stock Exchange. In these experiments, MLink was compared with mean-variance analysis (MVA), a popular method to portfolio optimization. According to the experimental results, using weighted link prediction in stock networks as input considerably increases the performance in portfolio optimization task, resulting in a gross capital increase of 41% in 84 days.

Abstract
Physician emigration can either function as an escape valve to help the health labour market clear from a supply surplus, or aggravate the problem further in case of a shortage. Either way, policy-makers should be particularly aware and devise policies to minimize the occurrence of an imbalance in the physician workforce, which may require physician retention policies if barriers to entry and other market rigidities can not be removed. To this purpose we have developed an agent-based computational economics model to analyse physician emigration, and have used it to study the impact of potential short- and long-term retention policies. As a real case study we have calibrated it with data from Portugal, which features a very particular health system with many rigidities. Results show that all policies are capable of increasing the workforce size, but not all reduce emigration. Also, the effect of return migration is non-negligible, and may substantially offset the impact on the workforce size. Furthermore, the welfare impact of the policies varies considerably. Whether policies to retain physicians should be enacted or whether policy makers should let physicians go will depend on the type of imbalance present in the health system.

Abstract
Capsule endoscopy is becoming the major medical technique for the examination of the gastrointestinal tract, and the detection of small bowel lesions. With the growth of endoscopic capsules and the lack of an appropriate tracking system to allow the localization of lesions, the need to develop software-based techniques for the localisation of the capsule at any given frame is also increasing. With this in mind, and knowing the lack of availability of labelled endoscopic datasets, this work aims to develop a unsupervised method for homography estimation in video capsule endoscopy frames, to later be applied in capsule localisation systems. The pipeline is based on an unsupervised convolutional neural network, with a VGG Net architecture, that estimates the homography between two images. The overall error, using a synthetic dataset, was evaluated through the mean average corner error, which was 34 pixels, showing great promise for the real-life application of this technique, although there is still room for the improvement of its performance. (C) 2019 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the scientific committee of the CENTERIS -International Conference on ENTERprise Information Systems / ProjMAN - International Conference on Project MANagement / HCist - International Conference on Health and Social Care Information Systems and Technologies.

Abstract
In the last decades, the assurance of doctoral education's quality and their respective external quality assurance (QA) systems have been on the agenda of many European countries. Portugal is no exception, with doctoral education being envisaged by the national study programmes' accreditation system. This study aims to discuss both the forms assumed by the QA of doctoral education within the scope of a tightly regulated system, such as the Portuguese one, as well as the effects or impact of such a system in this education level. In trying to explore this impact, particular attention is given to the accreditation results (full accreditation, conditional accreditation and non-accreditation) of the doctoral programmes according to their scientific area and higher education sector (public and private). Overall it is possible to conclude that the Portuguese QA system has been contributing to the reorganisation of doctoral education, both by excluding programmes that do not meet a set of minimum quality criteria and by promoting the enhancement of the remaining programmes, through the enforcement of improvement measures. This reorganisation seems to differently affect doctoral programmes from distinct scientific areas as well as from private and public institutions.

Abstract
Although companies seek to export in order to meet the growing importance of international markets, vis-à-vis domestic markets, this chapter presents a case study of a company founded by two former high school teachers who started a beverage company in 2015 and quickly reached an early internationalization. The company produces alcoholic beverages and has won international awards regarding the quality of its product, which has given it an important status and opened the door to a process of rapid internationalization. This will be used to explore the theory of entrepreneurship and how two potential entrepreneurs, with employment difficulties in teaching, began with a project that gave birth to a born global firm.