Abstract

Abstract
Data exchange between multiple renewable energy power plant owners can lead to an improvement in forecast skill thanks to the spatio-temporal dependencies in time series data. However, owing to business competitive factors, these different owners might be unwilling to share their data. In order to tackle this privacy issue, this paper formulates a novel privacy-preserving framework that combines data transformation techniques with the alternating direction method of multipliers. This approach allows not only to estimate the model in a distributed fashion but also to protect data privacy, coefficients and covariance matrix. Besides, asynchronous communication between peers is addressed in the model fitting, and two different collaborative schemes are considered: centralized and peer-to-peer. The results for a solar energy dataset show that the proposed method is robust to privacy breaches and communication failures, and delivers a forecast skill comparable to a model without privacy protection.

Abstract
Software engineering education requires students to develop technical knowledge and advanced cognitive and behavioral skills, particularly in the transition from novice to proficient. In distance learning, the hurdles are greater because students require greater autonomy, adopting strategies of self and co-regulation of learning. Facing these challenges, the SimProgramming approach has been transposed into the context of DL: e-SimProgramming. In the second iteration of e-SimProgramming implementation (2019/2020), one adaptation was inclusion of metacognitive challenges (MC) to promote students' self-reflection on their learning process. We explain the design of the two types of implemented MCs. We provide qualitative and quantitative analysis of: 1) evolution of MCs submission throughout the semester, identifying regularity and completion within deadlines and their relationship to student success; 2) students' perceptions of MCs. Results show a positive correlation between high MC submission and student success, greater interest and involvement of students in type 2 MCs and positive perceptions of students about MCs.

Abstract
Predictive maintenance methods assist early detection of failures and errors in machinery before they reach critical stages. This study proposes a data-driven predictive maintenance framework for the air production unit (APU) system of a train of Metro do Porto by deep learning based on a sparse autoencoder (SAE) network that efficiently detects abnormal data and considerably reduces the false alarm rate. Several analog and digital sensors installed on the APU system allow the detection of behavioral changes and deviations from the normal pattern by analyzing the collected data. We implemented two versions of the SAE network in which we inputted analog sensors data and digital sensors data, and the experimental results show that the failures due to air leakage problems are predicted by analog sensors data while other types of failures are identified by digital sensors data. A low pass filter is applied to the output of the SAE network, and a sequence of abnormal data is used as an alarm for the APU system failure. Performance indicators of the SAE network with digital sensors data, in terms of F1 Score, Recall, and Precision, are respectively, about 33.6%, 42%, and 28% better than those of the SAE network with analog sensors data. For comparison purposes, we also implemented a variational autoencoder (VAE). The results show that SAE performance is better than that of VAE by 14%, 77%, and 37% respectively, for Recall, Precision and F1 Score.

Abstract
Retirees have been growing in importance as a consumer segment targeted by the tourism industry, namely because they can minimize the typical seasonality of tourism and increase its sustainability. This study aims to contribute to a more in-depth knowledge of retirees' behaviour and has two objectives: (i) describe tourist behaviour of seniors prior to and after retirement; (ii) identify and analyse retired consumers' current motivations and constraints towards tourism. Qualitative research was conducted comprising interviews with 40 Portuguese retirees. The results indicate a diversity of experiences regarding tourism activities both before and after retirement, evidencing that past experience stands out as a determinant of retirees' tourism behaviour. Moreover, three distinct segments of tourists emerge: the experts, the new tourists, and the non-tourists.

Abstract
Imbalanced learning is one of the most relevant problems in machine learning. However, it faces two crucial challenges. First, the amount of methods proposed to deal with such problem has grown immensely, making the validation of a large set of methods impractical. Second, it requires specialised knowledge, hindering its use by those without such level of experience. In this paper, we propose the Automated Imbalanced Classification method, ATOMIC. Such a method is the first automated machine learning approach for imbalanced classification tasks. It provides a ranking of solutions most likely to ensure an optimal approximation to a new domain, drastically reducing associated computational complexity and energy consumption. We carry this out by anticipating the loss of a large set of predictive solutions in new imbalanced learning tasks. We compare the predictive performance of ATOMIC against state-of-the-art methods using 101 imbalanced data sets. Results demonstrate that the proposed method provides a relevant approach to imbalanced learning while reducing learning and testing efforts of candidate solutions by approximately 95%.