Abstract
The increasing use of sensor networks has led to an ever larger number of available spatiotemporal datasets. Forecasting applications using this type of data are frequently motivated by important domains such as environmental monitoring. Being able to properly assess the performance of different forecasting approaches is fundamental to achieve progress. However, traditional performance estimation procedures, such as cross-validation, face challenges due to the implicit dependence between observations in spatiotemporal datasets. In this paper, we empirically compare several variants of cross-validation (CV) and out-of-sample (OOS) performance estimation procedures, using both artificially generated and real-world spatiotemporal datasets. Our results show both CV and OOS reporting useful estimates, but they suggest that blocking data in space and/or in time may be useful in mitigating CV's bias to underestimate error. Overall, our study shows the importance of considering data dependencies when estimating the performance of spatiotemporal forecasting models.

Abstract
Introduction: Disease-related undernutrition is highly prevalent and requires timely intervention. However, identifying undernutrition often relies on physician judgment. As Internal Medicine wards are the backbone of the hospital setting, insight into the prevalence of nutritional risk in this population is essential. We aimed to determine the prevalence of nutritional risk in Internal Medicine wards, to identify its correlates, and to assess the agreement between the physicians' impression of nutritional risk and evaluation by Nutritional Risk Screening 2002. Material and Methods: A cross-sectional multicentre study was performed in Internal Medicine wards of 24 Portuguese hospitals during 2017. Data on demographics, previous hospital admissions, primary diagnosis, and Charlson comorbidity index score were collected. Nutritional risk at admission was assessed using Nutritional Risk Screening 2002. Agreement between physicians' impression of nutritional risk and Nutritional Risk Screening 2002 was tested by Cohen's kappa. Results: The study included 729 participants (mean age 74 +/- 14.6 years, 51% male). The main reason for admission was respiratory disease. Mean Charlson comorbidity index score was 5.8 +/- 2.8. Prevalence of nutritional risk was 51%. Nutritional risk was associated with admission during the previous year (odds ratio = 1.65, 95% confidence interval: 1.22 - 2.24), solid tumour with metastasis (odds ratio = 4.73, 95% confidence interval: 2.06 - 10.87), any tumour without metastasis (odds ratio = 2.04, 95% confidence interval:1.24 - 3.34), kidney disease (odds ratio = 1.83, 95% confidence interval: 1.21 - 2.75), peptic ulcer (odds ratio = 2.17, 95% confidence interval: 1.10 - 4.25), heart failure (odds ratio = 1.51, 95% confidence interval: 1.11 - 2.04), dementia (odds ratio = 3.02, 95% confidence interval: 1.96 - 4.64), and cerebrovascular disease (odds ratio = 1.62, 95% confidence interval: 1.12 - 2.35). Agreement between physicians' evaluation of nutritional status and Nutritional Risk Screening 2002 was weak (Cohen's kappa = 0.415, p < 0.001). Discussion: Prevalence of nutritional risk in the Internal Medicine population is very high. Admission during the previous year and multiple comorbidities increase the odds of being at-risk. Subjective physician evaluation is not appropriate for nutritional screening. Conclusion: The high prevalence of at-risk patients and poor subjective physician evaluation suggest the need to implement mandatory nutritional screening.

Abstract
The algebraic-group model (AGM), which lies between the generic group model and the standard model of computation, provides a means by which to analyze the security of cryptosystems against so-called algebraic adversaries. We formalize the AGM within the framework of universal composability, providing formal definitions for this setting and proving an appropriate composition theorem. This extends the applicability of the AGM to more-complex protocols, and lays the foundations for analyzing algebraic adversaries in a composable fashion. Our results also clarify the meaning of composing proofs in the AGM with other proofs and they highlight a natural form of independence between idealized groups that seems inherent to the AGM and has not been made formal before—these insights also apply to the composition of game-based proofs in the AGM. We show the utility of our model by proving several important protocols universally composable for algebraic adversaries, specifically: (1) the Chou-Orlandi protocol for oblivious transfer, and (2) the SPAKE2 and CPace protocols for password-based authenticated key exchange.

Abstract
The emergency department of a hospital plays an extremely important role in the healthcare of patients. To maintain a high quality service, clinical professionals need information on how patient flow will evolve in the immediate future. With accurate emergency department forecasts it is possible to better manage available human resources by allocating clinical staff before peak periods, thus preventing service congestion, or releasing clinical staff at less busy times. This paper describes a solution developed for the presentation of hourly, four-hour, eight-hour and daily number of admissions to a hospital's emergency department. A 10-year history (2009-2018) of the number of emergency admissions in a Portuguese hospital was used. To create the models several methods were tested, including exponential smoothing, SARIMA, autoregressive and recurrent neural network, XGBoost and ensemble learning. The models that generated the most accurate hourly time predictions were the recurrent neural network with one-layer (sMAPE = 23.26%) and with three layers (sMAPE = 23.12%) and XGBoost (sMAPE = 23.70%). In terms of efficiency, the XGBoost method has by far outperformed all others. The success of the recurrent neuronal network and XGBoost machine learning methods applied to the prediction of the number of emergency department admissions has been demonstrated here, with an accuracy that surpasses the models found in the literature.

Abstract
To gather hydrological measurements is a difficult task for Autonomous Surface Vessels. It is necessary for precise navigation considering underwater obstacles, shallow and fast water flows, and also mitigate misreadings due to disturbs caused by their propulsion system. To deal with those problems, this paper presents a new topology of an Autonomous Surface Vessel (ASV) based on a catamaran boat with an aerial propulsion system with azimuth control. This set generates an over-actuated 3 Degree of Freedom (DoF) ASV, highly maneuverable and able of operating over the above-mentioned situations. To deal with the high computational cost of the over-actuated control allocation (CA) problem, this paper also proposes a Fast CA (FCA) approach. The FCA breaks the initial nonlinear system into partially-dependent linear subsystems. This approach generates smaller connected systems with overlapping solution spaces, generating fast and robust convergence, especially attractive for embedded control devices. Both proposals, i.e., ASV and FCA, are assessed through mathematical simulations and real scenarios.

Abstract
Artificial intelligence (AI)-based solutions have revolutionized our world, using extensive datasets and computational resources to create automatic tools for complex tasks that, until now, have been performed by humans. Massive data is a fundamental aspect of the most powerful AI-based algorithms. However, for AI-based healthcare solutions, there are several socioeconomic, technical/infrastructural, and most importantly, legal restrictions, which limit the large collection and access of biomedical data, especially medical imaging. To overcome this important limitation, several alternative solutions have been suggested, including transfer learning approaches, generation of artificial data, adoption of blockchain technology, and creation of an infrastructure composed of anonymous and abstract data. However, none of these strategies is currently able to completely solve this challenge. The need to build large datasets that can be used to develop healthcare solutions deserves special attention from the scientific community, clinicians, all the healthcare players, engineers, ethicists, legislators, and society in general. This paper offers an overview of the data limitation in medical predictive models; its impact on the development of healthcare solutions; benefits and barriers of sharing data; and finally, suggests future directions to overcome data limitations in the medical field and enable AI to enhance healthcare. This perspective is dedicated to the technical requirements of the learning models, and it explains the limitation that comes from poor and small datasets in the medical domain and the technical options that try or can solve the problem related to the lack of massive healthcare data.