Abstract
This paper presents a novel feed-forward neural network for wind speed forecasting. The electricity sector accounts for a quarter of the world CO2 emissions. To reduce these emissions, several national, regional and global agreements have been signed, setting ambitious goals to increase the penetration of renewable energy sources (RES). Although achieving those goals is essential for the sector decarbonization and, therefore, to mitigate the global climate crisis, renewable-based generation can depend on highly variable and uncertain resources, such as the wind. Hence, having access to reliable forecasts of those resources availability is essential for the operation of several actors in the power and energy sector, and for the effectiveness of the whole system. This paper contributes to surpass this problem by introducing a new forecasting model based on a feed-forward neural network to forecast wind speed. The proposed model is applied to real data from a wind farm in the south of South America. Results show that the proposed model can achieve lower forecasting errors than the baseline models, which consist of Numerical Weather Predictions.

Abstract
Multi-temporal InSAR (MT-InSAR) techniques proved to be very effective for deformation monitoring. However, decorrelation and other noise sources, can be limiting factors in MT-InSAR. The obtained observations (PS - Persistent scatterers) are usually very demanding from a computational perspective, as they can reach hundreds of thousands of observations. To simplify and speed up the classification process, in this study we present an approach based on Convolutional Neural Networks (CNN) classification models, for the detection of MT-InSAR outlying observations. For each PS, the corresponding MT-InSAR parameters, its neighbouring scatterers parameters and its relative position are considered. Tests in two independent PS datasets, covering the regions of Bratislava city and the suburbs of Prievidza, Slovakia, were performed. The results showed that such models are robust and reduced computation time method for the evaluation of MT-InSAR outlying observations. However, the applicability of these models is limited by the deformation pattern in which such models were trained. (C) 2021 The Authors. Published by Elsevier B.V.

Abstract
A Fabry-Perot acoustic sensor based on a graphene oxide membrane was developed with the aim to achieve a faster and simpler fabrication procedure when compared to similar graphene-based acoustic sensors. In addition, the proposed sensor was fabricated using methods that reduce chemical hazards and environmental impacts. The developed sensor, with an optical cavity of around 246 mu m, showed a constant reflected signal amplitude of 6.8 +/- 0.1 dB for 100 nm wavelength range. The sensor attained a wideband operation range between 20 and 100 kHz, with a maximum signal-to-noise ratio (SNR) of 32.7 dB at 25 kHz. The stability and sensitivity to temperatures up to 90 degrees C was also studied. Moreover, the proposed sensor offers the possibility to be applied as a wideband microphone or to be applied in more complex systems for structural analysis or imaging.

Abstract
Background: Diabetes mellitus (DM) is one of the most challenging diseases in the 21st century and is the sixth leading cause of death. Telemedicine has increasingly been implemented in the care of patients with DM. Although teleconsultations at home have shown to be more effective for inducing HbA(1c) reduction than other telemedicine options, before the 2019 coronavirus disease crisis, their use had been lagging behind. Studies on physicians' or patients' perceptions about telemedicine have been performed independently of each other, and very few have focused on teleconsultations. In a time of great pressure for health systems and when an important portion of health care has to be assured at a distance, obtaining insights about teleconsultations at home from the stakeholders directly involved in the health care interaction is particularly important. Objective: The perceptions of patients and physicians about their intentions to use home synchronous teleconsultations for DM care are examined to identify drivers and barriers inherent to programs that involve home teleconsultations. Methods: Two identical questionnaires integrating the technology acceptance model and the unified theory of acceptance and use of technology and assessing the confidence in information and communication technology use of patients and physicians were developed. Responses by patients (n=75) and physicians (n=68) were analyzed using canonical correlation analysis. Results: Associations between predictor constructs (performance, effort, social influence, facilitating conditions, and attitude) and intention to use yielded significant functions, with a canonical R-2 of 0.95 (for physicians) and 0.98 (patients). The main identified barriers to patient intention to use were the expected effort to explain the medical problem, and privacy and confidentiality issues. The major drivers were the facilitation of contact with the physician, which is beneficial to patient disease management and treatment, time savings, and reciprocity concerning physicians' willingness to perform teleconsultations. Responses from physicians revealed an association between intention to use and the expected performance of home teleconsultations. The major barrier to intention to use expressed in physicians' answers was doubts concerning the quality of patient examination. The major drivers were time savings, productivity increases, improvements in patient's health and patient management, National Health System costs reduction, and reciprocity relative to patients' willingness to engage in teleconsultations. Conclusions: To promote the use of home teleconsultations for DM, decision makers should improve patients' health literacy so the physician-patient communication is more effective; explore information and communication technology developments to reduce current limitations of non-face-to-face examinations; ensure patient privacy and data confidentiality; and demonstrate the capabilities of home teleconsultations to physicians.

Abstract
Logs are still the primary resource for debugging distributed systems executions. Complexity and heterogeneity of modern distributed systems, however, make log analysis extremely challenging. First, due to the sheer amount of messages, in which the execution paths of distinct system components appear interleaved. Second, due to unsynchronized physical clocks, simply ordering the log messages by timestamp does not suffice to obtain a causal trace of the execution. To address these issues, we present Horus, a system that enables the refinement of distributed system logs in a causally-consistent and scalable fashion. Horus leverages kernel-level probing to capture events for tracking causality between application-level logs from multiple sources. The events are then encoded as a directed acyclic graph and stored in a graph database, thus allowing the use of rich query languages to reason about runtime behavior. Our case study with TrainTicket, a ticket booking application with 40+ microservices, shows that Horus surpasses current widely-adopted log analysis systems in pinpointing the root cause of anomalies in distributed executions. Also, we show that Horus builds a causally-consistent log of a distributed execution with much higher performance (up to 3 orders of magnitude) and scalability than prior state-of-the-art solutions. Finally, we show that Horus' approach to query causality is up to 30 times faster than graph database built-in traversal algorithms.

Abstract
In mobile robotics, since no requirements have been defined regarding accuracy for Battery Management Systems (BMS), standard approaches such as Open Circuit Voltage (OCV) and Coulomb Counting (CC) are usually applied, mostly due to the fact that employing more complicated estimation algorithms requires higher computing power; thus, the most advanced BMS algorithms reported in the literature are developed and verified by laboratory experiments using PC-based software. The objective of this paper is to describe the design of an autonomous and versatile embedded system based on an 8-bit microcontroller, where a Dual Coulomb Counting Extended Kalman Filter (DCC-EKF) algorithm for State of Charge (SOC) estimation is implemented; the developed prototype meets most of the constraints for BMSs reported in the literature, with an energy efficiency of 94% and an error of SOC accuracy that varies between 2% and 8% based on low-cost components.