Abstract
Emerging wearable technology able to monitor electrocardiogram (ECG) continuously for long periods of time without disrupting the patient's daily life represents a great opportunity to improve suboptimal current diagnosis of paroxysmal atrial fibrillation (AF). However, its integration into clinical practice is still limited because the acquired ECG recording is often strongly contaminated by transient noise, thus leading to numerous false alarms of AF and requiring manual interpretation of extensive amounts of ECG data. To improve this situation, automated selection of ECG segments with sufficient quality for precise diagnosis has been widely proposed, and numerous algorithms for such ECG quality assessment can be found. Although most have reported successful performance on ECG signals acquired from healthy subjects, only a recent algorithm based on a well-known pre-trained convolutional neural network (CNN), such as AlexNet, has maintained a similar efficiency in the context of paroxysmal AF. Hence, having in mind the latest major advances in the development of neural networks, the main goal of this work was to compare the most recent pre-trained CNN models in terms of classification performance between high- and low-quality ECG excerpts and computational time. In global values, all reported a similar classification performance, which was significantly superior than the one provided by previous methods based on combining hand-crafted ECG features with conventional machine learning classifiers. Nonetheless, shallow networks (such as AlexNet) trended to detect better high-quality ECG excerpts and deep CNN models to identify better noisy ECG segments. The networks with a moderate depth of about 20 layers presented the best balanced performance on both groups of ECG excerpts. Indeed, GoogLeNet (with a depth of 22 layers) obtained very close values of sensitivity and specificity about 87%. It also maintained a misclassification rate of AF episodes similar to AlexNet and an acceptable computation time, thus constituting the best alternative for quality assessment of wearable, long-term ECG recordings acquired from patients with paroxysmal AF.

Abstract
Distributed Machine Learning, in which data and learning tasks are scattered across a cluster of computers, is one of the answers of the field to the challenges posed by Big Data. Still, in an era in which data abounds, decisions must still be made regarding which specific data to use on the training of the model, either because the amount of available data is simply too large, or because the training time or complexity of the model must be kept low. Typical approaches include, for example, selection based on data freshness. However, old data are not necessarily outdated and might still contain relevant patterns. Likewise, relying only on recent data may significantly decrease data diversity and representativity, and decrease model quality. The goal of this paper is to compare different heuristics for selecting data in a distributed Machine Learning scenario. Specifically, we ascertain whether selecting data based on their characteristics (meta-features), and optimizing for maximum diversity, improves model quality while, eventually, allowing to reduce model complexity. This will allow to develop more informed data selection strategies in distributed settings, in which the criteria are not only the location of the data or the state of each node in the cluster, but also include intrinsic and relevant characteristics of the data.

Abstract
Artificial intelligence and machine learning have been widely applied in several areas with the twofold goal of improving people’s well-being and accelerating computational processes. This may be seen in medical assistance (e.g., automatic verification of MRI images) and in personal assistants that adapt the content to the user based on his/her preferences, to optimize query response times in relational databases and accelerate the information retrieval process. Most of machine learning algorithms used need a dataset to train on, so that the resulting models can be used, for example, to predict a value or enable user-specific results. Considering predictive methods, when new data arrives, a new training of the model may be needed. Speculative computation is a machine learning subfield that seeks to enable computation to be one step ahead of the user by speculating the value that will be received to be computed. A change in the environment may affect the execution, but the adjustments are rapidly performed. This paper intends to provide an overview of the field of speculative computation, describing its main characteristics and advantages, and different scenarios of the medical field in which it is applied. It also provides a critical and comparative analysis with other machine learning methods and a description of how to apply different algorithms to create better systems.

Abstract
In order to address one of the most challenging problems in hospital management - patients' absenteeism without prior notice - this study analyses the risk factors associated with this event. To this end, through real data from a hospital located in the North of Portugal, a prediction model previously validated in the literature is used to infer absenteeism risk factors, and an explainable model is proposed, based on a modified CART algorithm. The latter intends to generate a human-interpretable explanation for patient absenteeism, and its implementation is described in detail. Furthermore, given the significant impact, the COVID-19 pandemic had on hospital management, a comparison between patients' profiles upon absenteeism before and during the COVID-19 pandemic situation is performed. Results obtained differ between hospital specialities and time periods meaning that patient profiles on absenteeism change during pandemic periods and within specialities.

Abstract
Despite major advances in recent years, the field of Machine Learning continues to face research and technical challenges. Mostly, these stem from big data and streaming data, which require models to be frequently updated or re-trained, at the expense of significant computational resources. One solution is the use of distributed learning algorithms, which can learn in a distributed manner, from distributed datasets. In this paper, we describe CEDEs-a distributed learning system in which models are heterogeneous distributed Ensembles, i.e., complex models constituted by different base models, trained with different and distributed subsets of data. Specifically, we address the issue of predicting the training time of a given model, given its characteristics and the characteristics of the data. Given that the creation of an Ensemble may imply the training of hundreds of base models, information about the predicted duration of each of these individual tasks is paramount for an efficient management of the cluster's computational resources and for minimizing makespan, i.e., the time it takes to train the whole Ensemble. Results show that the proposed approach is able to predict the training time of Decision Trees with an average error of 0.103 s, and the training time of Neural Networks with an average error of 21.263 s. We also show how results depend significantly on the hyperparameters of the model and on the characteristics of the input data.

Abstract
Computer Science degrees are often seen as challenging by students, especially in what concerns subjects such as programming, data structures or algorithms. Many reasons can be pointed out for this, some of which related to the abstract nature of these subjects and the lack of previous related knowledge by the students. In this paper we tackle this challenge using gamification in the teaching/learning process, with two main goals in mind. The first is to increase the intrinsic motivation of students to learn, by making the whole process more fun, enjoyable and competitive. The second is to facilitate the learning process by providing intuitive tools for the visualization of data structures and algorithmic output, together with a tool for automated assessment that decreases the dependence on the teacher and allows them to work more autonomously. We validated this approach over the course of three academic years in a Computer Science degree of the Polytechnic of Porto, Portugal, through the use of a questionnaire. Results show that the effects of using games and game elements have a generally positive effect on motivation and on the overall learning process.