Abstract
Usually, Machine Learning systems are seen as something fully automatic. Recently, however, interactive systems in which human experts actively contribute towards the learning process have shown improved performance when compared to fully automated ones. This may be so in scenarios of Big Data, scenarios in which the input is a data stream, or when there is concept drift. In this paper, we present a system for supporting auditors in the task of financial fraud detection. The system is interactive in the sense that the auditors can provide feedback regarding the instances of the data they use, or even suggest new variables. This feedback is incorporated into newly trained Machine Learning models which improve over time.

Abstract
The frequency security problem becomes a critical concern in power systems when the system inertia is lowered due to the high penetration of renewable energy sources (RESs). A wind-storage system (WSS) controlled by power electronics can provide the virtual inertia to guarantee the fast frequency response after a disturbance. However, the provision of virtual inertia might be affected by the variability of wind power generation. To address this concern, we propose a two-stage chance-constrained stochastic optimization (TSCCSO) model to find the optimal thermal unit commitment (i.e., economic operation) and the optimal placement of virtual inertia (i.e., frequency stability) in a power grid using representative power system operation scenarios. An enhanced bilinear Benders decomposition method is employed with strong valid cuts to effectively solve the proposed optimization model. Numerical results on a practical power system show the effectiveness of the proposed model and solution method.

Abstract
Innovative teaching-learning methodologies in the fields of Control, Automation and Robotics are of great interest to researchers, educators and students. Nowadays there is a wide range of technological options available that can be used to improve learning and motivate students in their knowledge acquisition and skills development. Concepts such as Pocket-Sized Labs, Virtual and Remote Labs, as well as Web-Based Learning, are increasingly included in the teaching-learning processes, where students are expected to acquire their knowledge as active and central elements in the entire process. This article focuses on the review of various teaching-learning methodologies in the fields of Control, Automation and Robotics, taking several aspects into account: the portability and low cost of devices and applications, the possibility of autonomous and distance learning and centering of the learning process in the student. The conclusions drawn allow us to state that it is possible to apply innovative, effective and motivating methodologies with tools, devices and applications that are both low-cost and easy to access. It can also be inferred that the future of teaching demands a radical departure from the traditional methodologies, as well as taking advantage of technologies and students' skills to use and put them into practice.

Abstract
Lung cancer treatments that are accurate and effective are urgently needed. The diagnosis of advanced-stage patients accounts for the majority of the cases, being essential to provide a specialized course of treatment. One emerging course of treatment relies on target therapy through the testing of biomarkers, such as the Epidermal Growth Factor Receptor (EGFR) gene. Such testing can be obtained from invasive methods, namely through biopsy, which may be avoided by applying machine learning techniques to the imaging phenotypes extracted from Computerized Tomography (CT). This study aims to explore the contribution of ensemble methods when applied to the prediction of EGFR mutation status. The obtained results translate in a direct correlation between the semantic predictive model and the outcome of the combined ensemble methods, showing that the utilized features do not have a positive contribution to the predictive developed models.

Abstract
Machine Learning problems are significantly growing in complexity, either due to an increase in the volume of data, to new forms of data, or due to the change of data over time. This poses new challenges that are both technical and scientific. In this paper we propose a Distributed Learning System that runs on top of a Hadoop cluster, leveraging its native functionalities. It is guided by the principle of data locality. Data are distributed across the cluster, so models are also distributed and trained in parallel. Models are thus seen as Ensembles of base models, and predictions are made by combining the predictions of the base models. Moreover, models are replicated and distributed across the cluster, so that multiple nodes can answer requests. This results in a system that is both resilient and with high availability. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Regional income inequality is a topic of increasing relevance worldwide that has received considerable scientific attention. However, a clear-cut, comprehensive view has yet to be put forward of the main determinants of regional income inequality. Indeed, the extant empirical literature on the topic has reported differing results. Thus, this study develops a comprehensive meta-analysis using 33 comparable empirical studies spanning 29 years of research, involving 28 main determinants of which the most frequently mentioned were regional development, human capital, manufacturing/industry share, unemployment, financial development, and trade openness. After adjusting for publication bias and heterogeneity in the results reported by the primary studies, we conclude that the not very frequently addressed institutional related determinants (financial development, fiscal policies and public sector size), substantially contribute to reduce within-region income inequality, particularly in lower-income settings. In a smaller extent, human capital and trade openness also mitigate within-region income inequality. Region level of development, urbanization and, in a lesser extent, technological intensity aggravate within-region income inequality. © 2021, Springer-Verlag GmbH Germany, part of Springer Nature.