Abstract
Explainable Artificial Intelligence (XAI) seeks to enhance the interpretability of Artificial Intelligence (AI) systems, ensuring that algorithmic decisions and their underlying data are comprehensible to non-technical stakeholders. While advanced Machine Learning (ML) models, such as deep neural networks, have significantly improved AI capabilities, their complexity poses challenges for XAI, particularly in handling large datasets required for training and interpretation. In particular, the application of Shapley Additive Explanations (SHAP), although widely recognized for its effectiveness, often incurs a high computational cost when applied to large-scale data. Addressing this issue, our previous work proposed a novel approach that leverages K-Means clustering to identify representative data instances, applied after the forecasting phase to refine SHAP-based explanations and reduce computational costs while preserving their fidelity. This extended study further optimizes the clustering strategy and evaluates its applicability across broader use cases in sustainable energy systems. We apply our method to forecast photovoltaic (PV) generation in buildings, a critical aspect of energy management in e-mobility and smart grids. The results show that clustering reduces execution time by more than 50 % compared to random sampling while maintaining comparable explanatory stability. These findings highlight the potential of data-driven clustering techniques in enhancing the explainability of ML models in energy forecasting, contributing to more accessible and practical AI solutions for real-world applications.

Abstract
This paper explores the potential of the educational gamification platform known as SCORE as a novel solution to address challenges related to student disengagement and the increasing preference for gaming. Faced with observed disinterest among first-year Computer Engineering students, particularly intensified during the Covid-19 era, the study advocates for integrating the educational gamification platform to create a dynamic and engaging learning environment. SCORE is presented as an innovative alternative to conventional teaching methods, fostering deeper understanding and motivation among students. Positioned to catalyze holistic student development, encompassing critical thinking and problem-solving skills, SCORE emerges as a leading player in the evolving landscape of educational gamification. The document provides a comprehensive overview of the motivating factors for this investigation, laying the groundwork for a detailed analysis of SCORE and the role of educational games in effective teaching methods. Anticipated outcomes encompass enriched pedagogical practices and a solid foundation for future research endeavors. Positioned as one among many alternatives, SCORE contributes to the ongoing discourse on innovative teaching methods, offering valuable insights for educators and researchers exploring ways to enhance the learning experience. With the evolution of technology, SCORE, alongside other educational games, aims to take a significant step forward in academic terms, enabling students to achieve the best possible results while remaining motivated in their academic journey. © 2025 Elsevier B.V., All rights reserved.

Abstract
This study delves into the critical role of third-party applications in enhancing motorcycle interface design, particularly focusing on their potential to revolutionize the rider experience through innovative UI/UX designs. As motorcycles increasingly serve as primary modes of transportation in urban environments, safety concerns escalate, needing effective solutions. The research scrutinizes the main safety challenges faced by motorcycle riders, the influence of thirdparty applications on safety outcomes, and the advantages these applications offer over traditional dashboards. In this context, it is presented a Systematic Literature Review (SLR) methodology. Specifically, articles were selected based on predefined inclusion and exclusion criteria. Results indicate that third-party applications provide customizable solutions that not only offer real-time information about the motorcycle's condition but also mitigate safety risks by minimizing distractions. However, the literature reveals a lack of studies specifically addressing these applications, underscoring their potential as pioneering initiatives to reinforce motorcycle safety.

Abstract
Forest fires represent a significant and growing threat to natural ecosystems and human settlements, with their unpredictable behavior and capacity for rapid expansion over time, creating substantial challenges for effective prevention, control, and mitigation. This paper presents the development of a forest fire simulator designed to model and predict fire spread under varying environmental conditions. Such a simulator must consider how fire spreads in different locations and climate conditions, showing the final shape of the fire in a given period of time. Using the NetLogo agent-based modeling platform, a simulated forest environment was created in which trees function as autonomous agents interacting with one another and the environment. Identifying and understanding the risk factors that increase the likelihood of a fire occurring, as well as those that contribute to its spread and intensity, is essential for the development of an accurate forest fire simulator. Such a simulator can integrate the complex interactions among these variables to produce dynamic visualizations of fire progression, allowing users to evaluate different scenarios and make informed decisions for preventing, controlling and fighting forest fires. By incorporating key factors—such as vegetation density, temperature, humidity, topography, and wind direction—the system calculates the probability of fire propagation and generates visual representations of fire behavior over time. This tool allows users to forecast fire behavior and assess response strategies proactively, thereby improving the accuracy and efficiency of firefighting efforts. In addition, the simulator yields significant social benefits, especially for older adults residing in fire-prone areas, by supporting early warning systems, enabling prompt evacuations, and mitigating their susceptibility to fire-related risks through enhanced preparedness and coordinated response measures.

Abstract
Digital twins are increasingly used, as they allow the creation of detailed virtual representations of physical products and systems. They face, however, significant challenges such as heterogeneous data integration and high costs. This article presents an innovative methodology that uses Large Language Models to unify information and automate the generation of Digital Twin models. The proposal comprises several modules, covering the stages of data collection, semantic processing, modular construction and validation of the Digital Twin. In this way, the proposed model guarantees interoperability, efficiency and scalability for various domains.

Abstract
The rapid evolution of Artificial Intelligence (AI) is reshaping Human Resource Management (HRM), with growing interest in its role in talent identification. While AI has demonstrated effectiveness in analysing structured data, its limitations in assessing qualitative attributes such as creativity, adaptability, and emotional intelligence remain underexplored. This study addresses these gaps through an exploratory mixed-methods design, combining a global survey (n = 240) with semi-structured interviews of HR professionals. Quantitative analysis highlights patterns of association between key competencies, while qualitative findings provide contextual insights into perceptions of fairness, bias, and cultural resistance. The results suggest that AI can complement, but not replace, human judgement, supporting a Hybrid Evaluative Model that integrates algorithmic efficiency with human interpretation. The study contributes rare empirical evidence to a nascent field, highlights the ethical imperatives of bias mitigation and transparency, and underscores the importance of cultural context (collectivist versus individualist orientations) in shaping the acceptance and effectiveness of AI-enabled HR practices. These findings offer practical guidance for organisations and advance theory-building at the intersection of AI and HRM.