Abstract
Energy management in buildings can be largely improved by considering adequate forecasting techniques to find load consumption patterns. While these forecasting techniques are relevant, decision making is needed to decide the forecasting technique that suits best each context, thus improving the accuracy of predictions. In this paper, two forecasting methods are used including artificial neural network and k-nearest neighbor. These algorithms are considered to predict the consumption of a building equipped with devices recording consumptions and sensors data. These forecasts are performed from five-to-five minutes and the forecasting technique decision is taken into account as an enhanced factor to improve the accuracy of predictions. This decision making is optimized with the support of the multi-armed bandit, the reinforcement learning algorithm that analyzes the best suitable method in each five minutes. Exploration alternatives are considered in trial and test studies as means to find the best suitable level of unexplored territory that results in higher accumulated rewards. In the case-study, four contexts have been considered to illustrate the application of the proposed methodology.

Abstract
Cancer is one of the diseases with the highest mortality rate in the world. To understand the different origins of the disease, and to facilitate the development of new ways to treat it, laboratories cultivate, in vitro, cancer cells (cell lines), taken from patients with cancer. These cell lines enable researchers to test new approaches and to have an appropriate procedure for comparison of results. The methods used in an initial study at EMBL-EBI Institute (Cambridge, UK) were based on algorithms that construct propositional like models. The results reported were promising but we believe that they can be improved. A relevant limitation of the algorithms used in the original study is the absence or severe lack of comprehensibility of the models constructed. In Life Sciences, the possibility of understanding a model is an asset to help the specialist to understand the phenomenon that produced the data. With our study we have improved the performance of forecasting models and constructed understandable models. To meet these objectives we have used Graph Mining and Inductive Logic Programming algorithms.

Abstract
The timely identification of cohort participants at higher risk for attrition is important to earlier interventions and efficient use of research resources. Machine learning may have advantages over the conventional approaches to improve discrimination by analysing complex interactions among predictors. We developed predictive models of attrition applying a conventional regression model and different machine learning methods. A total of 542 very preterm (< 32 gestational weeks) infants born in Portugal as part of the European Effective Perinatal Intensive Care in Europe (EPICE) cohort were included. We tested a model with a fixed number of predictors (Baseline) and a second with a dynamic number of variables added from each follow-up (Incremental). Eight classification methods were applied: AdaBoost, Artificial Neural Networks, Functional Trees, J48, J48Consolidated, K-Nearest Neighbours, Random Forest and Logistic Regression. Performance was compared using AUC- PR (Area Under the Curve-Precision Recall), Accuracy, Sensitivity and F-measure. Attrition at the four follow-ups were, respectively: 16%, 25%, 13% and 17%. Both models demonstrated good predictive performance, AUC-PR ranging between 69 and 94.1 in Baseline and from 72.5 to 97.1 in Incremental model. Of the whole set of methods, Random Forest presented the best performance at all follow-ups [AUC-PR1: 94.1 (2.0); AUC-PR2: 91.2 (1.2); AUC-PR3: 97.1 (1.0); AUC-PR4: 96.5 (1.7)]. Logistic Regression performed well below Random Forest. The top-ranked predictors were common for both models in all follow-ups: birthweight, gestational age, maternal age, and length of hospital stay. Random Forest presented the highest capacity for prediction and provided interpretable predictors. Researchers involved in cohorts can benefit from our robust models to prepare for and prevent loss to follow-up by directing efforts toward individuals at higher risk.

Abstract
Multi-view ensemble learning exploits the information of data views. To test its efficiency for full text classification, a technique has been implemented where the views correspond to the document sections. For classification and prediction, we use a stacking generalization based on the idea that different learning algorithms provide complementary explanations of the data. The present study implements the stacking approach using support vector machine algorithms as the baseline and a C4.5 implementation as the meta-learner. Views are created with OHSUMED biomedical full text documents. Experimental results lead to the sustained conclusion that the application of multi-view techniques to full texts significantly improves the task of text classification, providing a significant contribution for the biomedical text mining research. We also have evidence to conclude that enriched datasets with text from certain sections are better than using only titles and abstracts.

Abstract
Objective/background: To describe and characterize insomnia symptoms and nightmare profiles in Portugal during the first six weeks of a national lockdown due to COVID-19. Patients/methods: An open cohort study was conducted to collect information of the general population during the first wave of SARS-CoV-2/COVID-19 pandemic in Portugal. We analyzed data from 5011 participants (>= 16 years) who answered a weekly questionnaire about their well-being. Two questions about the frequency of insomnia and nightmares about COVID-19 were consecutively applied during six weeks (March-May 2020). Latent class analysis was conducted and different insomnia and nightmare profiles were identified. Associations between individual characteristics and both profiles were estimated using odds ratios (ORs) and 95% confidence intervals (CI). Results: Five insomnia (No insomnia, Stable-mild, Decreasing-moderate, Stable-severe, Increasing-severe) and three nightmares profiles (Stable-mild, Stable-moderate, Stable-severe) were identified. Being female, younger, perceiving their income as insufficient and feelings of fear towards COVID-19 were associated with higher odds of insomnia (Women: OR = 6.98 95%CI: 4.18-11.64; >= 60 years: OR = 0.30 95%CI: 0.18-0.53; Insufficient income: adjusted OR (aOR) = 8.413 95% CI: 3.93-16.84; Often presenting fear of being infected with SARS-CoV-2 infection: aOR = 9.13 95%CI: 6.36-13.11), and nightmares (Women: OR = 2.60 95%CI: 1.74-3.86; >= 60 years: OR = 0.45 95%CI: 0.28-0.74; Insufficient income: aOR = 2.60 95%CI: 1.20e5.20; Often/almost always presenting fear of being infected with SARS-CoV-2 infection: aOR = 6.62 95%CI: 5.01-8.74). Having a diagnosis of SARS-CoV-2 virus infection was associated with worse patterns of nightmares about the pandemic. Conclusions: Social and psychological individual factors are important characteristics to consider in the developmentof therapeutic strategies to supportpeoplewithsleep problems during the COVID-19 pandemic.

Abstract
Capturing complex spatio-temporal features of thousands of correlated taxi-demand time-series in the city makes the traffic flow prediction problem a challenging task. Hence, several Deep Neural Network (DNN) models have been developed to mimic the latent spatio-temporal behaviour of taxi-demand time-series in a city to improve the prediction results. Despite, good performance of recent DNN based traffic prediction techniques, such models can only identify either adjacent or connected regions with direct or transitive connection; hence they fail to capture spatio-temporal correlation among regions that exhibit implicit or latent connection. Additionally, the dependency of the recent DNN models on recursive components facilitates error propagation during feature aggregation without any counter strategy for it. In view of these existing glitches, we introduce a novel DNN model, graph Multi-Head Convolution for patio-Temporal Aggregation (gMHC-STA) which supports capturing spatio-temporal correlation among regions with explicit and implicit connection both. Moreover, gMHC-STA aggregates both spatial and temporal characteristics using multi-head attention; thus overriding recursive RNN or its variant approach to prevent noise propagation. The experimental results of gMHC-STA on two real-world city taxi-demand datasets report minimum of 6.5-10% improvement over the best state-of-the-art on standard benchmark metric in varying experimental conditions.