Abstract
Higher education institutions (HEIs) make decisions in several domains, namely strategic and internal management, without using systematized data that support these decisions, which may jeopardize the success of their actions or even their efficiency. Thus, HEIs must define and monitor strategies and policies essential for decision making in their various areas and levels, in which business intelligence (BI) plays a leading role. This study presents a systematic literature review (SLR) aimed at identifying and analyzing primary studies that propose a roadmap for the implementation of a BI system in HEIs. The objectives of the SLR are to identify and characterize (i) the strategic objectives that underlie decision making, activities, processes, and information in HEIs; (ii) the BI systems used in HEIs; (iii) the methods and techniques applied in the design of a BI architecture in HEIs. The results showed that there is space for developing research in this area since it was possible to identify several studies on the use of BI in HEIs, although a roadmap for its implementation was not identified, making it necessary to define a roadmap for the implementation of BI systems that can serve as a reference for HEIs.

Abstract
In the context of the R3EA project, funded by the Portuguese Foundation for Science and Technology (FCT), we analyse a set of selected future power system scenarios to assess the impact, on the Iberian electricity market (MIBEL), of installing wind and solar generation capacity in Portugal's Centro Region. We use the long-term MIBEL operation and planning model CEVESA. The scenarios are designed based on the current economic situation and the last National Energy and Climate Plan drafts for Portugal and Spain, by distributing the expected new wind and solar generation capacity differently among Portugal regions, also considering the flexible demand for producing electrolytic hydrogen. Market prices, capture prices and production per technology are analysed to assess this impact. Results show that regional investments have no significant impact on the MIBEL variables analysed.

Abstract
Hospitalization has been identified as stress-inducing event that potentially contributes to depression and anxiety among children, particularly when the duration of hospital stay is prolonged. This scoping review seeks to identify the role of videogames and other interactive technology in reducing stress and promoting well-being, exploring the specific considerations for developing videogames for in- patient children and focusing on understanding various outcomes with different types of interactive technologies. The databases used in this research were ACM, PubMed, Wiley Library, yielding a total of 90 articles. Following the application of exclusion criteria 7 articles were selected for analysis. It is noteworthy that many of the included articles exhibit limitations, such as restricted study durations and a small number of participants. Addressing these limitations is crucial for establishing the long-term efficacy of interactive technology and videogames in promoting the well-being of in-patient children.

Abstract
In man-made marine infrastructures, elements such as pillars, cables or ducts are common, which provide distinctive landmarks for Simultaneous Localization and Mapping purposes. In this work, we concentrate on the application of template matching to acoustic imagery for landmark detection and tracking, building on the modeling of common elements in marine environments. The proposed algorithm extends on the original method by employing a density-based clustering technique for match candidate selection and leveraging vehicle inertial information to identify regions of interest in the acquired images, tackling performance deterioration resulting from motion-induced image deformation and overall acoustic feature ambiguity. Experimental results are provided based on datasets collected in a testing pool environment. © 2024 IEEE.

Abstract
Accurate identification of transportation mode distribution is essential for effective urban planning. Recent advancements in machine learning have spurred research on automated Transportation Mode Detection (TMD). While existing TMD methods predominantly employ standard flat classification methods, this paper introduces HiClass4MD, a novel hierarchical approach. By leveraging the misclassification errors from standard flat classifier, HiClass4MD learns the class hierarchy for transportation modes. Although hierarchical metrics initially indicated performance improvements when applied to real-world GPS trajectories dataset, a subsequent evaluation using conventional metrics revealed inconsistent results. While decision trees benefited marginally, other classifiers exhibited no significant gains or even degraded. This study highlights the complexity of applying hierarchical classification to TMD and underscores the need for further investigation into the factors influencing its effectiveness.

Abstract
Arbitrary, inconsistent, or faulty decision-making raises serious concerns, and preventing unfair models is an increasingly important challenge in Machine Learning. Data often reflect past discriminatory behavior, and models trained on such data may reflect bias on sensitive attributes, such as gender, race, or age. One approach to developing fair models is to preprocess the training data to remove the underlying biases while preserving the relevant information, for example, by correcting biased labels. While multiple label noise correction methods are available, the information about their behavior in identifying discrimination is very limited. In this work, we develop an empirical methodology to systematically evaluate the effectiveness of label noise correction techniques in ensuring the fairness of models trained on biased datasets. Our methodology involves manipulating the amount of label noise and can be used with fairness benchmarks but also with standard ML datasets. We apply the methodology to analyze six label noise correction methods according to several fairness metrics on standard OpenML datasets. Our results suggest that the Hybrid Label Noise Correction [20] method achieves the best trade-off between predictive performance and fairness. Clustering-Based Correction [14] can reduce discrimination the most, however, at the cost of lower predictive performance.