Abstract
[No abstract available]

Abstract
Breast cancer is the most common type of cancer in women worldwide. Because of high survival rates, there has been an increased interest in patient Quality of Life after treatment. Aesthetic results play an important role in this aspect, as these treatments can leave a mark on a patient's self-image. Despite that, there are no standard ways of assessing aesthetic outcomes. Commonly used software such as BCCT.core or BAT require the manual annotation of keypoints, which makes them time-consuming for clinical use and can lead to result variability depending on the user. Recently, there have been attempts to leverage both traditional and Deep Learning algorithms to detect keypoints automatically. In this paper, we compare several methods for the detection of Breast Endpoints across two datasets. Furthermore, we present an extended evaluation of using these models as input for full contour prediction and aesthetic evaluation using the BCCT.core software. Overall, the YOLOv9 model, fine-tuned for this task, presents the best results considering both accuracy and usability, making this architecture the best choice for this application. The main contribution of this paper is the development of a pipeline for full breast contour prediction, which reduces clinician workload and user variability for automatic aesthetic assessment.

Abstract
Since the public unveiling of ChatGPT-3 in November 2022, its impact and consequences for society have been significant. This generative artificial intelligence has now become a disruptive technology. Education in general, and Engineering Education in particular, are feeling the effects of the widespread adoption of artificial intelligence tools by students. However, teachers and universities are still struggling with how to deal with these technologies. The current increase in digitalisation makes detecting unauthorised use of ChatGPT and similar tools a major challenge. This paper therefore explores several issues regarding the use of ChatGPT in the context of Engineering Education. Copyright (c) 2025 The Authors. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract
A investigação sobre o feedback e a autorregulação da aprendizagem tem granjeado interesse com a explosão da Inteligência Artificial e os desafios que coloca à educação e, em particular, à avaliação dos estudantes. Contudo, há mais de 30 anos que se estudam esses processos para compreender como os estudantes regulam a sua própria aprendizagem ao nível motivacional, cognitivo e metacognitivo. Ao assumirem um papel proativo na geração e utilização do feedback estão a avaliar o seu próprio trabalho, o que tem implicações na forma como os professores organizam a avaliação e o apoio na aprendizagem.  Este artigo elabora sobre os desafios múltiplos que se colocam à IA na avaliação digital da aprendizagem, no que respeita ao feedback e a autorregulação bem como na investigação sobre a avaliação digital. Após a discussão desses conceitos e de modelos enquadradores bem como a sua conexão com a avaliação digital conclui-se que é crucial considerar equipas multidisciplinares na investigação com IA e minimizar ou eliminar situações que podem introduzir enviesamentos em termos de género, etnias, culturas e estatutos económico ou social.

Abstract
Electric vehicles (EVs) allow a significant reduction in harmful gas emissions, thus improving urban air quality. However, the widespread adoption of this technology is limited by several factors, resulting in heterogeneous deployment in urban areas. This raises challenges regarding the planning of public electric vehicle charging infrastructure (EVCI), requiring adaptive strategies to ensure comprehensive and efficient coverage. This study introduces an innovative method that leverages geographic information systems to pinpoint appropriate sizes and suitable locations for public EVCI within urban environments. Initially, a Bass diffusion model is employed to estimate EV adoption rates by regions, enabling the determination of the appropriate sizes of EVCI necessary for each of them. Subsequently, a multi-criteria decision-making approach is applied to identify the suitable locations for EV charger installation within each region. In this way, EVCI locations are selected using spatial criteria, which ensure they are near common areas of interest and easily accessible through the road network. To validate the effectiveness and applicability of the proposed method, tests using geospatial data from a city in Brazil were carried out. The findings suggest that EVCI planning without proper spatial analysis may result in inefficient locations and inadequate sizes, which may discourage potential EV adopters and hinder widespread adoption of this technology.

Abstract
Electric vehicles (EVs) are crucial in achieving a low-carbon transportation sector and can inherently offer demand-side flexibility by responding to price signals and incentives, yet real-world strategies to influence charging behavior remain limited. This paper combines bilevel optimization and causal machine learning as complementary tools to design and evaluate dynamic incentive schemes as part of a pilot project using a supermarket's EV charging station network. The bilevel model determines discount levels, while double machine learning quantifies the causal impact of these incentives on charging demand. The results indicate a marginal increase of 1.16 kW in charging demand for each one-percentage-point increase in discount. User response varies by hour and weekday, revealing treatment effect heterogeneity, insights that can inform business decision-making. While the two methods are applied independently, their combined use provides a framework for connecting optimization-based incentive design with data-driven causal evaluation. By isolating the impact of incentives from other drivers, the study sheds light on the potential of incentives to enhance demand-side flexibility in the electric mobility ecosystem.