Abstract
Technological evolution has allowed that tasks, usually performed by humans, can now be performed accurately by automated systems, often with superior performance. The healthcare area has been paradigmatic in the automation of processes, as the need to optimize costs, ensuring the provision of quality care, is crucial for the success of organizations. Diabetes, whose prevalence has increased significantly in the last decade, could be a case of application of several technologies that facilitate diagnosis, tracking and monitoring. Such tasks demand a great effort from health systems, requiring the allocation of material, human and financial resources, under penalty of worsening symptoms and emergence of serious complications. In this chapter the authors will present and explore how different technologies can be integrated to provide better healthcare, ensuring quality and safety standards, with reference to the case of diabetes.

Abstract
This paper presents a model predictive control (MPC) framework for battery energy storage systems (BESS) management considering models for battery degradation, system efficiency and V-I characteristics. The optimization framework has been tested for microgrids with different renewable generation and load mix considering several operation strategies. A comparison for one-year simulations between the proposed model and a naïve BESS model, show an increase in computation times that still allows the application of the framework for real-time control. Furthermore, a trade-off between financial revenue and reduced BESS degradation was evaluated for the yearly simulation, considering the degradation model proposed. Results show that a conservative BESS usage strategy can have a high impact on the asset's lifetime and on the expected system revenues, depending on factors such as the objective function and the degradation threshold considered.

Abstract
Switched reluctance machines (SRM) are simple, robust and fault tolerant machines, usually operating under strong nonlinear characteristics. Hence, SRM modeling is a most demanding task, in particular core losses. Non-sinusoidal flux density waveforms in different stator and rotor core sections, in addition to lamination non-uniform distribution are challenging phenomena to be addressed. This is still an ongoing research field. The purpose of this paper is to develop a comparative analysis between a linear and non-linear simulation model for core loss distribution in a three-phase 6/4 SRM. Five different steady-state operation modes will be addressed.

Abstract
The purpose of this study is to describe the construction process and the evidence of content validity of SCARA, a prototype of a technological system to support language and communication rehabilitation in people with aphasia, providing a tool that serves both patients and health professionals who accompany the respective recovery process. The process followed four stages: internal phase of the program's organization, with research in the literature and analysis of the materials available in the Portuguese market; construction of the SCARA prototype; evaluation by experts; and data analysis. A Content Validity Index was calculated to determine the level of agreement between the experts. The level of agreement between experts showed the validity of SCARA. SCARA has shown to help the work of the speech-language pathologist and persons with aphasia, contributing to a higher therapeutic quality, enhancing linguistic recovery, and compensating for the impossibility of direct support more frequently and/or prolonged intervention. © 2022 ACM.

Abstract
The volume of data is growing exponentially and becoming more valuable to organizations that collect it, from e-commerce data, shipping, audio and video logs, text messages, internet search queries, stock market activity, financial transactions, the Internet of Things, and various other sources. The major challenges are related with the way to extract insights from such a rich data environment and whether Deep Learning can be successful with Big Data. To get some insight on these topics, social network data are employed as a case study on how sentiments can affect decisions in stock market environments. In this paper, we propose a generalized Deep Learning-based classification framework for Stock Market Sentiment Analysis. This work comprises the study, the development, and implementation of an automatic classification system based on Deep Learning and the validation of its adequacy and efficiency in any scenario, particularly Stock Market Sentiment Analysis. Distinct datasets and several Deep Learning approaches with different layers and embedded techniques are used, and their performances are evaluated. These developments show how Deep Learning reacts to distinct contexts. The results also give context on how different techniques with different parameter combinations react to certain types of data. Convolution obtained the best results when dealing with complex data inputs, and long short-term layers kept a memory of data, allowing inputs which are not as common to still be considered for decisions. The models that resulted from Stock Market Sentiment Analysis datasets were applied with some success to real-life problems. The best models reached accuracies of 73% in training and 69% in certain test datasets. In a simulation, a model was able to provide a Return on Investment of 4.4%. The results contribute to understanding how to process Big Data efficiently using Deep Learning and specialized hardware techniques.

Abstract
New challenges arise with the upsurge of a Big Data era. Huge volumes of data, from the most varied natures, gathered from different sources, collected in different timings, often with high associated uncertainty, make the decision-making process a harsher task. Current methods are not ready to deal with characteristics of the new problems. This paper proposes a novel data selection methodology that filters big volumes of data, so that only the most correlated information is used in the decision-making process in each given context. The proposed methodology uses a clustering algorithm, which creates sub-groups of data according to their correlation. These groups are then used to feed a forecasting process that uses the relevant data for each situation, while discarding data that is not expected to contribute to improving the forecasting results. In this way, a faster, less computationally demanding, and effective forecasting is enabled. A case study is presented, considering the application of the proposed methodology to the filtering of electricity market data used by forecasting approaches. Results show that the data selection increases the forecasting effectiveness of forecasting methods, as well as the computational efficiency of the forecasts, by using less yet more adequate data. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.