Abstract
The aim of this chapter focuses on featuring firmed IoT architecture paradigms and advocating, knowingly in concrete use cases, the combined use of such architecture categories. It is common knowledge that the growing demand for embedded processing, interconnection, and integration facilities in everyday objects is being driven by a multitude of IoT projects. The smart cities, smart agriculture, manufacturing, and industrial automation areas are some of the most important application grounds. Equally important is the medical sector where specially framed in this publication, the personal home healthcare scenarios gain enormous relevance due to the potential of IoT technology application. It is also becoming clear that the IoT-trending efforts are compelling researchers into the concurrent combination of multiple IoT-computing architecture types or paradigms, to know: wide-range cloud-computing architectures, local-spread fog-computing architectures, and spottily scattered edge-computing architectures. This chapter focuses on identifying the major goals and benefits of each of these architectures classes; describing the relevant state of the art projects, which apply such architecture categories in home healthcare settings; and finally, pinpointing our own experience with home e-health demonstrative use case scenarios, where the benefits of using each of these architecture types become evident, and the concurrent combination of such IoT architectures inevitable. © 2021 Elsevier Inc.

Abstract
Absenteeism is a major problem faced particularly by companies with a large number of employees. Therefore, the existence of absenteeism prediction tools is essential for such companies depending on intensive human-resources. This paper focuses on using machine learning technologies for predicting the absences of employees from work. More precisely, a few prediction models were tuned and tested with 241 features extracted from a population of 13.805 employees. This target population was sampled from the help desk work force of a major Brazilian phone company. The features were extracted from the profile of the help desk agents and then filtered by processes of correlation and feature selection. The selected features were then used to compare absenteeism prediction given by different classification algorithm (cf. Random Forest, Multilayer Perceptron, Support Vector Machine, Naive Bayes, XGBoost and Long Short Term Memory). The parameterization of these ML models was also studied to reach the classifier best suited for the prediction problem. Such parameterizations were tuned through the use of evolutionary algorithms, from which considerable precision was reached, the best being 72% (XGBoost) and 71% (Random Forest). © 2019, Springer Nature Switzerland AG.

Abstract
Forest fires can have devastating consequences if not detected and fought before they spread. This paper presents an automatic fire detection system designed to identify forest fires, preferably, in their early stages. The system pipeline processes images of the forest environment and is able to detect the presence of smoke or flames. Additionally, the system is able to produce an estimation of the area under ignition so that its size can be evaluated. In the process of classification of a fire image, one Deep Convolutional Neural Network was used to extract, from the images, the descriptors which are then applied to a Logistic Regression classifier. At a later stage of the pipeline, image analysis and processing techniques at color level were applied to assess the area under ignition. In order to better understand the influence of specific image features in the classification task, the organized dataset, composed by 882 images, was associated with relevant image metadata (eg presence of flames, smoke, fog, clouds, human elements). In the tests, the system obtained a classification accuracy of 94.1% in 695 images of daytime scenarios and 94.8% in 187 images of nighttime scenarios. It presents good accuracy in estimating the flame area when compared with other approaches in the literature, substantially reducing the number of false positives and nearly keeping the same false negatives stats. © Springer Nature Switzerland AG 2019.

Abstract
The longevity of the population is the result of important scientific breakthroughs in recent years. However, living longer with quality, also brings new challenges to governments, and to the society as a whole. One of the most significant consequences will be the increasing pressure on the healthcare services. Ambient Assisted Living (AAL) systems can greatly improve healthcare scalability and reach while keeping the user in their home environment. The work presented in this paper specifies, implements, and validates a smart environment system that aggregates Automation and Artificial Intelligence (AI). The specification includes a reference architecture, composed by three modules, whose tasks are to automate and standardize the collection of data, to relate and give meaning to that data and to learn from it. The system is able to identify daily living activities with different levels of complexity using a temporal logic. It enables a real time response to emergency situations and also a long term analysis of the user daily routine useful to induce healthier lifestyles. The implementation addresses the applications and techniques used in the development of a functional prototype. To demonstrate the system operation three use cases with increasing levels of complexity are proposed and validated. A discussion on related projects is also included, specifically on automation applications, Knowledge Representation (KR) and Machine Learning (ML). © Springer Nature Switzerland AG 2019.

Abstract