Abstract

Abstract
New opportunities for lifelong learning, alternative curricula in pre-university education and fairly "open" policies on access to Higher Education (HE) have boosted, in recent decades, the problem of the lack of homogenization of knowledge and skills of "freshmen" students in Higher Education Institutions (HEI). This problem becomes overwhelming when it comes to "constructive" basic curricular units, such as Mathematics or Statistics, in non-mathematical degrees, in areas as Administration, Accounting or Management. This is a daily "struggle" faced by teachers of these curricular units as they try to talk about more advanced subjects to a very heterogeneous audience, with significant differences in Math background, promoting the participation of all students and avoiding the early drop out of some. In this sense, other didactic strategies, which include a set of activities that combine higher order thinking skills with math subjects and technology, for students of HE, appear as remedial but important, proactive and innovative measures in order to face and try to level up Math competences without risking the "repetition process", that unfortunately promotes other kind dropout behaviors. In this paper some of these strategies, developed in the Polytechnic of Porto (P.PORTO) and based on the creation and usefulness of the interactive teaching and learning materials, will be presented. The actual need for innovating in the teaching-learning process was felt and the search for a good support software, that enables to develop all the materials and implement real interactions, culminated with the choice of iSpring Suite 9. This software is a powerful eLearning toolkit for PowerPoint that allows to develop quality courses, video lectures, and assessments that will work on any desktop, laptop and mobile platform. Therefore, the use of the iSpring Suite 9 will be described, with a special focus on core objective when teaching statistics to students from the Management and Business degree in a HEI and facing the abovementioned issues - to improve students' basic statistics skills and enhance their motivation in learning Statistics.

Abstract
Lung cancer is considered one of the deadliest diseases in the world. An early and accurate diagnosis aims to promote the detection and characterization of pulmonary nodules, which is of vital importance to increase the patients' survival rates. The mentioned characterization is done through a segmentation process, facing several challenges due to the diversity in nodular shape, size, and texture, as well as the presence of adjacent structures. This paper tackles pulmonary nodule segmentation in computed tomography scans proposing three distinct methodologies. First, a conventional approach which applies the Sliding Band Filter (SBF) to estimate the filter's support points, matching the border coordinates. The remaining approaches are Deep Learning based, using the U-Net and a novel network called SegU-Net to achieve the same goal. Their performance is compared, as this work aims to identify the most promising tool to improve nodule characterization. All methodologies used 2653 nodules from the LIDC database, achieving a Dice score of 0.663, 0.830, and 0.823 for the SBF, U-Net and SegU-Net respectively. This way, the U-Net based models yield more identical results to the ground truth reference annotated by specialists, thus being a more reliable approach for the proposed exercise. The novel network revealed similar scores to the U-Net, while at the same time reducing computational cost and improving memory efficiency. Consequently, such study may contribute to the possible implementation of this model in a decision support system, assisting the physicians in establishing a reliable diagnosis of lung pathologies based on this segmentation task.

Abstract
Reactive programming (RP) languages and Synchronous Coordination (SC) languages share the goal of orchestrating the execution of computational tasks, by imposing dependencies on their execution order and controlling how they share data. RP is often implemented as libraries for existing programming languages, lifting operations over values to operations over streams of values, and providing efficient solutions to manage how updates to such streams trigger reactions, i.e., the execution of dependent tasks. SC is often implemented as a standalone formalism to specify existing component-based architectures, used to analyse, verify, transform, or generate code. These two approaches target different audiences, and it is non-trivial to combine the programming style of RP with the expressive power of synchronous languages. This paper proposes a lightweight programming language to describe component-based Architectures for Reactive systems, dubbed ARx, which blends concepts from RP and SC, mainly inspired to the Reo coordination language and its composition operation, and with tailored constructs for reactive programs such as the ones found in ReScala. ARx is enriched with a type system and with algebraic data types, and has a reactive semantics inspired in RP. We provide typical examples from both the RP and SC literature, illustrate how these can be captured by the proposed language, and describe a web-based prototype tool to edit, parse, and type check programs, and to animate their semantics. © IFIP International Federation for Information Processing 2020.

Abstract
Currently, lung cancer is the most lethal in the world. In order to make screening and follow-up a little more systematic, guidelines have been proposed. Therefore, this study aimed to create a diagnostic support approach by providing a patient label based on the LUNG-RADSTM guidelines. The only input required by the system is the nodule centroid to take the region of interest for the input of the classification system. With this in mind, two deep learning networks were evaluated: a Wide Residual Network and a DenseNet. Taking into account the annotation uncertainty we proposed to use sample weights that are introduced in the loss function, allowing nodules with a high agreement in the annotation process to take a greater impact on the training error than its counterpart. The best result was achieved with the Wide Residual Network with sample weights achieving a nodule-wise LUNG-RADSTM labelling accuracy of 0.735 +/- 0.003.

Abstract
For many reasons, including sports being one of the main forms of entertainment in the world, online gambling is growing. And in growing markets, opportunities to explore it arise. In this paper, neural network ensemble approaches, such as bagging, random subspace sampling, negative correlation learning and the simple averaging of predictions, are compared. For each one of these methods, several combinations of input parameters are evaluated. We used only the expected goals metric as predictors since it is able to have good predictive power while keeping the computational demands low. These models are compared in the soccer (also known as association football) betting context where we have access to metrics, such as rentability, to analyze the results in multiple perspectives. The results show that the optimal solution is goal-dependent, with the ensemble methods being able to increase the accuracy up to +3 % over the best single model. The biggest improvement over the single model was obtained by averaging dropout networks. © 2020, Springer Nature Switzerland AG.