Faculdade Engenharia
URI permanente desta comunidade:
Navegar
Percorrer Faculdade Engenharia por Objetivos de Desenvolvimento Sustentável (ODS) "04:Educação de Qualidade"
A mostrar 1 - 6 de 6
Resultados por página
Opções de ordenação
- Investigação em artes e arquitectura: Natureza, metodologias, validade e impactoPublication . Sequeira, João Manuel Barbosa Meneses deA discussão sobre a Investigação nas artes e na arquitectura, enquanto práticas dotadas de metodologias próprias e com potencial para serem consideradas formas válidas de produção de conhecimento, é central em muitos debates contemporâneos nas humanidades e ciências sociais. Para abordar esta hipótese, podemos dividir a discussão em três áreas principais: Da Natureza: Investigação em Artes e Arquitectura Das Metodologias: Regras Próprias Da Validade e Valor do Conhecimento Produzido
- Matrices - Book of Abstracts: II International Congress Architecture and GenderPublication . Pedrosa, Patrícia Santos; Santos, Eliana Sousa; Matos, Maria João Pereira de ; Alvarez Lombardero, NuriaThe Second International Congress on Architecture and Gender will address the theme of Matrices. This concept has several definitions and they are all inclusive by nature. Matrices are environments where things develop, the models or patterns that shape formations, and they can also reinvent an environment. These images are suited to address the current patterns of change regarding architecture and gender.
- A scoping study of reviews on artificial intelligence in educationPublication . Gabriel, Graça; Ferrão, Maria Eugénia; Prata, PaulaThis scoping study synthesizes recent developments in artificial intelligence in education (AIEd), addressing knowledge structures, research priorities, learning theories, ethical considerations, and impact evaluation. A bibliometric analysis of 31 review articles (2019-2023) indexed in Scopus (Social Sciences) was conducted using VOSviewer and complementary statistical methods. The corpus is concentrated in the United Kingdom, Hong Kong, China, Germany, the United States, and Taiwan, with Asian countries accounting for 48.4%. Multidisciplinary journals attract 4.4 times more citations than education-only outlets. Findings indicate a marked rise in AIEd research, primarily led by education-affiliated scholars, yet often lacking robust pedagogical grounding and systematic impact assessment. The prevalence of small samples, limited quantitative rigor, and inconsistent contextual reporting constrain generalizability and inference. To enhance educational relevance and fairness, the field should be anchored in pedagogical frameworks and advanced through collaborative efforts that build stronger theories, methods, and practices responsive to diverse educational needs.
- Self-Explanatory Deep Learning Models with Concept-based Multimodal Explanations for Medical Imaging DiagnosisPublication . Patrício, Cristiano Pires ; Neves, João Carlos Raposo; Teixeira, Luís Filipe Pinto de AlmeidaThe remarkable performance of deep learning models in automated medical imaging diagnosis is achieved at the expense of the low interpretability of their representations. The opaque nature of these methods, which often operate as “black boxes”, remains a major barrier to their adoption in real-world applications, especially in high-stakes scenarios such as healthcare. This lack of interpretability motivated the development of eXplainable Artificial Intelligence (XAI) techniques capable of explaining model decisions so that humans can understand and interpret their decision-making. Early efforts in XAI applied to images relied mainly on post-hoc strategies that generate model-agnostic explanations by assessing the influence of input regions on predictions. However, these explanations are often ambiguous and unreliable. Similarly, textual explanations face challenges as language models are prone to generate inaccurate content, including ambiguous or factually incorrect statements. As an alternative, Concept Bottleneck Models (CBMs) offer an inherently interpretable design, where the final predictions are explicitly derived from intermediate human-understandable concepts. Nevertheless, CBMs face several critical limitations. Their reliance on manual concept annotations, the lack of visual interpretability for the predicted concepts, and the need for model retraining when new concepts are introduced hinders their utility and scalability. This thesis addresses these limitations by introducing methods capable of generating multimodal explanations grounded on human-understandable concepts, thereby enhancing both the transparency and the interpretability of the model output. First, we present a comprehensive survey of state-of-the-art XAI methods, datasets, and evaluation metrics in medical image diagnosis, highlighting existing gaps and open challenges in the XAI literature. Building on these insights, we propose two concept-based approaches for skin lesion diagnosis: one extending the conventional CBMs to produce concept-based visual explanations, and another that leverages a transformer-based architecture with learnable concept tokens, improving the visual coherence of concept explanations through a dedicated architecture and regularization. To reduce reliance on concept annotations, we further explore Vision Language Models (VLMs), proposing strategies that automatically annotate concepts and predict the final diagnosis either through a linear classifier or by prompting Large Language Models (LLMs). To overcome the lack of visual context in disease prediction in these latter approaches, we propose CBVLM, a training-free framework that integrates off-the-shelf Large Vision-Language Models (LVLMs) to jointly generate concept-based explanations and predict disease diagnoses grounded in both semantic concepts and visual demonstration examples. Beyond concept-based explanations, we also demonstrate that interpretability can also be achieved even in constrained scenarios with limited annotations. Specifically, we propose an unsupervised framework for brain Magnetic Resonance Imaging (MRI) tumor detection that learns to reconstruct benign patterns of an input image using solely a dataset of healthy examples. At inference, when presented with brain MRI containing anomaly patterns, the reconstruction error between the input and the reconstructed image highlights potential tumor regions, allowing intuitive and interpretable anomaly localization. The results obtained from the methods proposed in this thesis demonstrate that it is possible to enhance the interpretability of CBMs by integrating visual concept explanations consistent with the learned concepts, while reducing their reliance on manual concept annotations, maintaining the interpretability and performance. Furthermore, extensive experiments across various medical imaging modalities, including dermoscopy, radiology, eye fundus imaging, and brain MRI, demonstrate that the proposed approaches not only improve disease diagnosis, but also provide more transparent and faithful multimodal explanations, paving the way for safer clinical integration and increased trust.
- Teoria critica de apoio pedagógico à unidade curricular de Desenho IPublication . Sequeira, João Manuel Barbosa Meneses deO presente manual insere-se no âmbito da unidade curricular de Desenho I, leccionada no 1.º ano do Mestrado Integrado em Arquitectura da Universidade da Beira Interior. Resulta de uma prática pedagógica continuada que, ao longo dos últimos anos, tem procurado articular a formação técnica do desenho com uma reflexão crítica e sensível sobre o papel da representação na génese do projecto arquitectónico. Embora concebido como instrumento de apoio ao ensino, o seu horizonte ultrapassa o contexto estrito da unidade curricular, visando propor um contributo mais amplo para a pedagogia do desenho em arquitectura.
- The importance of the 11th grade physics and chemistry exam to access electrical and computer engineering degrees in higher educationPublication . Velez, Fernando J.This paper analyzes the importance of the 11th-grade Physics and Chemistry exam as a mandatory requirement for admission to Electrical and Computer Engineering (ECE) courses in higher education, highlighting the impacts of Ordinance No. 17/2025/1, which eliminates this requirement. Electrical Engineering, a crucial area for technological progress, demands solid training in Physics and Chemistry, fundamental subjects for understanding concepts such as mechanics and waves, electromagnetism, electrical circuits, thermodynamics, and material properties. The exclusion of the exam requirement may compromise students' preparation, resulting in poor academic performance, lack of motivation in secondary education, and a decline in the quality of engineering training. The study presents a detailed analysis of the relationship between the secondary education Physics and Chemistry curriculum and the courses in ECE, emphasizing the relevance of these subjects for academic success and professional practice of future engineers. Furthermore, the impacts of Ordinance No. 17/2025/1 are discussed, such as insufficient student preparation and reduced motivation to choose scientific subjects in secondary education, which may harm not only engineering courses but also other fields dependent on solid science training. To mitigate these impacts, the paper proposes measures such as reintroducing the Physics and Chemistry exam as a mandatory requirement, emphasizing these subjects in the 12th grade, adopting tie-breaking criteria that prioritize students with strong science backgrounds, and strengthening the practical component in higher education. It concludes that ensuring a solid foundation in Physics and Chemistry is essential for training highly qualified engineers capable of meeting market demands and contributing to Portugal's technological and economic development.