Abstract
This work compares six AC/DC power conversion chain topologies commonly employed by industrial companies for implementing electrolyzers. The main purpose is to help identify the eventual advantages of joining the traditional high-power rectifiers to an additional stage based on DC/DC conversion. The comparison is based on the current ripple, power factor, total harmonic distortion, scalability, and solution complexity. A Simulink model corresponding to each topology was developed to determine comparison criteria. The procedure consists of performing a steady-state analysis of each topology through simulations to obtain the main waveforms and the values of the established criteria and then calculating the scores for each technical solution. The findings indicated that the 24-pulse diode bridge rectifier plus DC-DC without interphase reactor exhibited the best performance. © 2024 IEEE.

Abstract
In various machine learning applications, classification plays an important role in categorizing and predicting data. To improve the classification performance, it is crucial to identify and remove the anomalies. Also, class imbalance in many machine learning applications is a very common problem since most classifiers tend to be biased toward the majority class by ignoring the minority class instances. Thus, in this research, we propose a new under-sampling technique based on anomaly detection and removal to enhance the performance of imbalanced classification problems. To demonstrate the effectiveness of the proposed method, comprehensive experiments are conducted on forty imbalanced data sets and two non-parametric hypothesis tests are employed to show the statistical difference in classification performances between the proposed method and other traditional resampling methods. From the experiment, it is shown that the proposed method improves the classification performance by effectively detecting and eliminating the anomalies among true-majority or pseudo-majority class instances.

Abstract
This study introduces a method to assess the quality of Explainable Artificial Intelligence (XAI) algorithms in dynamic data streams, concentrating on the fidelity and stability of feature-importance and rule-based explanations. We employ XAI metrics, such as fidelity and Lipschitz Stability, to compare explainers between each other and introduce the Comparative Expert Stability Index (CESI) for benchmarking explainers against domain knowledge. We adopted the aforementioned metrics to the streaming data scenario and tested them in an unsupervised classification scenario with simulated distribution shifts as different classes. The necessity for adaptable explainers in complex scenarios, like failure detection is underscored, stressing the importance of continued research into versatile explanation techniques to enhance XAI system robustness and interpretability.

Abstract
Temporal reasoning has been the focus of several studies during the past years, both in linguistics and computational studies. Although advances on this topic are undeniable, there are still improvements to be made and new avenues to pursue. One relevant problem concerns the temporal ordering of the events, particularly asserting and representing how events are temporally related and how the story told in the narrative evolves. This paper aims to analyse the temporal structure of narratives present in news articles with the aid of different visualisations. To this end, we annotated a dataset of 119 news articles in European Portuguese following an annotation scheme that combines different parts of ISO 24617-Language Resource Management - Semantic Annotation Framework (SemAF). The temporal layer of this annotation scheme identifies the events and their main features, as well as the temporal links between the events. The annotation provided us with paramount information about the temporal characteristics of news at two levels: the story and the report levels. The visualisations that we propose facilitate the process of understanding how news are temporally organised, providing a more practical means to observe them. © 2024 Copyright for this paper by its authors.

Abstract
This study explores the contribution of serious game teaching technology, such as FLIGBY, to the development of entrepreneurial learning outcomes in the context of an entrepreneurship course in higher education. The sample is composed of 551 students through the construction of a randomized pretest-posttest control group. A quantitative methodology is adopted through the development of a structured equation model that seeks to assess the effectiveness of FLIGBY in the development of three constructs related to the development of entrepreneurial skills, reduction in the perception of barriers associated with entrepreneurial activity and increase the entrepreneurial intention. The findings reveal that FLIGBY can effectively contribute to the development of the first two constructs. However, we found that it has no effect on the third construct because it was not possible to identify significant differences in the entrepreneurial intention of FLIGBY students with those of the control group. The results of this study are relevant in extending the understanding of the impact of adopting a serious game in the context of entrepreneurship education and also supports their role in the development of more immersive and student-centered training.

Abstract