Abstract
We propose a multi-task learning approach for simultaneous tempo estimation and beat tracking of musical audio. The system shows state-of-the-art performance for both tasks on a wide range of data, but has another fundamental advantage: due to its multi-task nature, it is not only able to exploit the mutual information of both tasks by learning a common, shared representation, but can also improve one by learning only from the other. The multi-task learning is achieved by globally aggregating the skip connections of a beat tracking system built around temporal convolutional networks, and feeding them into a tempo classification layer. The benefit of this approach is investigated by the inclusion of training data for which tempo-only annotations are available, and which is shown to provide improvements in beat tracking accuracy.

Abstract
Low performance of nontechnical engineering students in programming courses is a problem that remains unsolved. Over the years, many authors have tried to identify the multiple causes for that failure, but there is unanimity on the fact that motivation is a key factor for the acquisition of knowledge by students. To better understand motivation, a new evaluation strategy has been adopted in a second programming course of a nontechnical degree, consisting of 91 students. The goals of the study were to identify if those students felt more motivated to answer multiple-choice questions in comparison to development questions, and what type of question better allows for testing student knowledge acquisition. Possibilities around the motivational qualities of multiple-choice questions in programming courses will be discussed in light of the results. In conclusion, it seems clear that student performance varies according to the type of question. Our study points out that multiple-choice questions can be seen as a motivational factor for engineering students and it might also be a good way to test acquired programming concepts. Therefore, this type of question could be further explored in the evaluation points.

Abstract
This paper proposes a novel case-based reasoning (CBR) recommender system for intelligent energy management in buildings. The proposed approach recommends the amount of energy reduction that should be applied in a building in each moment, by learning from previous similar cases. The k-nearest neighbor clustering algorithm is applied to identify the most similar past cases, and an approach based on support vector machines is used to optimize the weight of different parameters that characterize each case. An expert system composed by a set of ad hoc rules guarantees that the solution is adequate and applicable to the new case scenario. The proposed CBR methodology is modeled through a dedicated software agent, thus enabling its integration in a multi-agent systems society for the study of energy systems. Results show that the proposed approach is able to provide suitable recommendations on energy reduction, by comparing its results with a previous approach based on particle swarm optimization and with the real reduction in past cases. The applicability of the proposed approach in real scenarios is also assessed through the application of the results provided by the proposed approach on a house energy resources management system.

Abstract
NaSSIE - Navigation and Sensoring Skills in Engineering is a platform developed with the intent of facilitating the acquisition of some skills by Engineering Students, which is a core part of the process of controlling a mobile robot. In this paper, the chosen hardware and consequent physical construction of the prototype as well as vehicle’s associated software will be presented. As a use case, this platform was tested during the Robotic Day 2017 in Czech Republic. Preliminary results will also be presented of this year’s preparation for the Micromouse competition. © 2019, Springer Nature Switzerland AG.

Abstract
In view of the growing importance of nanotechnologies, the detection of nanoparticles type in several contexts has been considered a relevant topic. Several organisms, including the National Institutes of Health, have been highlighting the urge of developing nanoparticles exposure risk assessment assays, since very little is known about their physiological responses. Although the identi fi cation/characterization of synthetically produced nanoparticles is considered a priority, there are many examples of \ naturally" generated nanostructures that provide useful information about food components or human physiology. In fact, several nanoscale extracellular vesicles are present in physiological fluids with high potential as cancer biomarkers. However, scientists have struggled to fi nd a simple and rapid method to accurately detect/identify nanoparticles, since their majority have diameters between 100-150 nm -far below the di ff raction limit. Currently, there is a lack of instruments for nanoparticles detection and the few instrumentation that is commonly used is costly, bulky, complex and time consuming. Thus, considering our recent studies on particles identi fi cation through back-scattering, we examined if the time/frequency-domain features of the back-scattered signal provided from a 100 nm polystyrene nanoparticles suspension are able to detect their presence only by dipping a polymeric lensed optical fi ber in the solution. This novel technique allowed the detection of synthetic nanoparticles in distilled water versus \ blank solutions" (only distilled water) through Multivariate Statistics and Arti fi cial Intelligence (AI)-based techniques. While the state-of-the-art methods do not o ff er a ff ordable and simple approaches for nanoparticles detection, our technique can contribute for the development of a device with innovative characteristics.

Abstract
Machine learning systems are becoming increasingly ubiquitous. These systems's adoption has been expanding, accelerating the shift towards a more algorithmic society, meaning that algorithmically informed decisions have greater potential for significant social impact. However, most of these accurate decision support systems remain complex black boxes, meaning their internal logic and inner workings are hidden to the user and even experts cannot fully understand the rationale behind their predictions. Moreover, new regulations and highly regulated domains have made the audit and verifiability of decisions mandatory, increasing the demand for the ability to question, understand, and trust machine learning systems, for which interpretability is indispensable. The research community has recognized this interpretability problem and focused on developing both interpretable models and explanation methods over the past few years. However, the emergence of these methods shows there is no consensus on how to assess the explanation quality. Which are the most suitable metrics to assess the quality of an explanation? The aim of this article is to provide a review of the current state of the research field on machine learning interpretability while focusing on the societal impact and on the developed methods and metrics. Furthermore, a complete literature review is presented in order to identify future directions of work on this field.