Abstract
The automotive industry has an extremely high-quality product standard, not just for the security risks each faulty component can present, but the very brand image it must uphold at all times to stay competitive. In this paper, a prototype model is proposed for smart quality inspection using machine vision. The engine labels are detected using Faster-RCNN and YOLOv3 object detection algorithms. All the experiments were carried out using a custom dataset collected at an automotive assembly plant. Eight engine labels of two brands (Citroën and Peugeot) and more than ten models were detected. The results were evaluated using the metrics Intersection of Union (IoU), mean of Average Precision (mAP), Confusion Matrix, Precision and Recall. The results were validated in three folds. The models were trained using a custom dataset containing images and annotation files collected and prepared manually. Data Augmentation techniques were applied to increase the image diversity. The result without data augmentation was 92.5%, and with it the value was up-to 100%. Faster-RCNN has more accurate results compared to YOLOv3. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

Abstract
Peripheral artery disease (PAD) main symptom is intermittent claudication, causing pain and limiting the walking abilities of patients, forcing individuals to temporarily stop walking. One treatment advised to counteract the effects of this disease is the practice of physical exercise with monitoring. Currently the monitored exercise programs are applied at the hospital, so some patients have to travel long distances three times a week, with high costs and low adherence of the patients. This paper presents the cocreation process of a mobile application for quantified supervised home-based exercise therapy on PAD patients. The study aimed to design a solution adapted to users' needs, which collects the necessary information for the therapy supervision by health professionals. The users' behaviour with the application allowed the assessment to a set of limitations and potential sources of noise in the supervision data that suggest the evolution to a pervasive solution, by minimizing, or even eliminating, the interaction with the users. The developed tool is a first step towards the creation of a technological ecosystem for the prescription of supervised therapeutic physical exercise, which leverages self-care and allows access to this type of therapy to the entire population. Cardiovascular disease represents a considerable economic burden to society, therefore effective preventive measures are necessary.

Abstract
The harsh impacts of extreme weather events like cyclones or precipitation extremes are increasingly being felt with hazardous consequences. These extreme events are exceptions to well-known weather patterns and therefore are not forecasted with current automatic computational methods. In this context, the use of human computation to annotate extreme atmospheric phenomena could provide novel insights for computational forecasting algorithms and a step forward in climate change research by enabling the early detection of abnormal weather conditions. However, existing crowd computing solutions have technological limitations and show several gaps when involving expert crowds. This paper presents a research approach to fulfill some of the technological and knowledge gaps for expert crowds’ participation. A case study on expert annotation of extreme atmospheric phenomena is used as a baseline for an innovative architecture able to support expert crowdsourcing. The full stack service-oriented architecture ensures interoperability and provides an end-to-end approach able to fetch weather data from international databases, generating experts’ visualizations (weather maps), annotating data by expert crowds, and delivering annotated data for processing weather forecasts. An implementation of the architecture suggests that it can deliver an effective mechanism for expert crowd work while solving some of the identified issues with extant platforms. Therefore, we conclude that the proposed architecture has the potential to contribute as an effective annotation solution for extreme weather events. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
The dropout of university students has been a factor of concern for educational institutions, affecting various aspects such as the institution’s reputation and funding and rankings. For this reason, it is essential to identify which students are at risk. In this study, algorithms based on decision trees and random forests are proposed to solve these problems using real data from 331 students from the University of Trásos-Montes and Alto Douro. In this work with these learning algorithms together with the training strategies, we managed to obtain an 89% forecast of students who may abandon their studies based on the evaluations of both semesters related to the first year and personal data. © 2021, Springer Nature Switzerland AG.

Abstract
Visualization can be defined as a technique that allows us to obtain the perception of an object/event in a clear and consistent way. The use of visualization in education is a key factor to explain complex information in a clear way. Therefore, it is essential to have tools capable of visualizing various types of data. An example of a data type is the weather forecast data, which includes various atmospheric data for a given place, and allows the simulation of the atmospheric evolution. It is used for decision making in many areas, such as, agriculture, fishing, tourism, etc. Thus, it is beneficial to demonstrate the usefulness of this type of visualization to better understand the meteorological phenomena, as well as to teach scientific visualization techniques in order to enable access to information that otherwise can only be interpreted by qualified people. In this article it will be discussed the scientific visualization and its benefits to the area of meteorology, and it will be presented a case study of data visualization using the ParaView tools for meteorological data visualization and analysis. ParaView is a multiplatform tool based on the Visualization Toolkit (VTK) that provides features to process, analyze, and visualize various types of data. This study aims to present a tool for scientific visualization and to demonstrate its applications and usefulness for education. © 2021, Springer Nature Switzerland AG.

Abstract