Abstract
Regression testing is of paramount importance to ensure that the quality of software does not suffer when code changes are implemented. However, having a large set of tests is mostly done by hand and is time-consuming. Regression tests are written to test functionality that is already implemented and thus are a prime target for automatic test generation. Mutation testing is a technique that evaluates the quality of tests by applying simple changes to source code and checking if any test detects those changes. This paper presents an approach focused on GUI Testing that takes the idea behind mutation testing and applies it, not to the source code, but the actual tests. Generated tests are then analyzed, and those that generate different outcomes are chosen. The set of initial test cases is obtained from the interactions of the actual users of the service under analysis. In the end, an evaluation of the approach is presented. © Springer Nature Switzerland AG 2019.

Abstract
Numerous sophisticated machine learning tools (e.g. ensembles or deep networks) have shown outstanding performance in terms of accuracy on different numeric forecasting tasks. In many real world application domains the numeric predictions of the models drive important and costly decisions. Frequently, decision makers require more than a black box model to be able to “trust” the predictions up to the point that they base their decisions on them. In this context, understanding these black boxes has become one of the hot topics in Machine Learning and Data Mining research. This paper proposes a series of visualisation tools that help in understanding the predictive performance of non-interpretable regression models. More specifically, these tools allow the user to relate the expected error of any model to the values of the predictor variables. This type of information allows end-users to correctly assess the risks associated with the use of the models, by showing how concrete values of the predictors may affect the performance of the models. Our illustrations with different real world data sets and learning algorithms provide insights on the type of usage and information these tools bring to both the data analyst and the end-user. © 2019, Springer Nature Switzerland AG.

Abstract
This work aims to present and summarize the identified main research fields about player engagement enhancement with video games. The expansion of video game diversity, complexity and applicability increased development costs. New approaches aim to automatize the design process by developing algorithms that can understand players requirements and redesign games on the fly. Multiplayer games have the added benefit of socially engage all involved parties through game-play. But balancing becomes more important as feeling overwhelmed by a stronger opponent may be demotivating, as feeling underwhelmed by a weaker adversary that cannot provide enough challenge and stimulation. Our research concludes that there is still lack of research effort in the identified fields. This may be due to the lack of academy incentive on the subject. The entertainment industry depends on game quality to increase their revenue, but lack interest on sharing their knowledge. We identify potential application on Serious Games. © Springer Nature Switzerland AG 2019.

Abstract
O presente estudo tem o objetivo de demonstrar a aplicação dos indicadores de Desenvolvimento Sustentável sugeridos pela OCDE (Organização para Cooperação e Desenvolvimento Econômico) para Museus. Esta aplicação tem o intuito de demonstrar como é possível reconhecer o nível de sustentabilidade dos Museus. Para isso foram realizadas pesquisas bibliográficas que evidenciam a importância de se organizar tais parâmetros, com base nas características do País em que o Museu está instalado e que demonstram a efetiva contribuição destas organizações no que se refere aos objetivos do Desenvolvimento Sustentável. Neste estudo preliminar, foram realizadas recolha de dados em dois museus da Região Centro de Portugal. A recolha de dados teve como referência Indicadores de Sustentabilidade sugeridos e publicados pela OCDE  em 2018. Estes parâmetros foram a base da recolha de dados, que resultou em uma análise do nível de sustentabilidade desses dois museus, seguindo as referências OCDE. O resultado demonstrou uma efetiva possibilidade de medição dos níveis de sustentabilidade dos museus e mostra também, a potencialidade dos museus para cooperação nos objetivos delineados pela Agenda 2030 do Desenvolvimento Sustentável, elaborado pela Organização das Nações Unidas.

Abstract
This paper proposes a reinforcement learning model for intelligent energy management in buildings, using a UCB1 based approach. Energy management in buildings has become a critical task in recent years, due to the incentives to the increase of energy efficiency and renewable energy sources penetration. Managing the energy consumption, generation and storage in this domain, becomes, however, an arduous task, due to the large uncertainty of the different resources, adjacent to the dynamic characteristics of this environment. In this scope, reinforcement learning is a promising solution to provide adaptiveness to the energy management methods, by learning with the on-going changes in the environment. The model proposed in this paper aims at supporting decisions on the best actions to take in each moment, regarding buildings energy management. A UCB1 based algorithm is applied, and the results are compared to those of an EXP3 approach and a simple reinforcement learning algorithm. Results show that the proposed approach is able to achieve a higher quality of results, by reaching a higher rate of successful actions identification, when compared to the other considered reference approaches.

Abstract
A new first-order integer-valued moving average, INMA(1), model based on the negative binomial thinning operation defined by Ristic et al. [21] is proposed and characterized. It is shown that this model has negative binomial (NB) marginal distribution when the innovations follow an NB distribution and therefore it can be used in situations where the data present overdispersion. Additionally, this model is extended to the bivariate context. The Generalized Method of Moments (GMM) is used to estimate the unknown parameters of the proposed models and the results of a simulation study that intends to investigate the performance of the method show that, in general, the estimates are consistent and symmetric. Finally, the proposed model is fitted to a real dataset and the quality of the adjustment is evaluated. © 2019, Springer Nature Switzerland AG.