Search Results (517)

The rapid emergence of generative artificial intelligence (GenAI) has sparked growing interest across educational disciplines, reshaping how knowledge is produced, represented, and assessed. While recent research has increasingly explored the implications of text-based tools such as ChatGPT in education, far less attention has been paid to image-based GenAI tools—despite their particular relevance to fields grounded in visual communication and creative exploration, such as architecture and design. These disciplines raise distinct pedagogical and ethical questions, given their reliance on iteration, authorship, and visual representation as core elements of learning and practice. This exploratory study investigates how architecture and interior architecture students perceive the use of AI-generated images, focusing on ethical responsibility, educational relevance, and career implications. To ensure participants had sufficient exposure to visual GenAI tools, we conducted a series of workshops before surveying 42 students familiar with image generation processes. Findings indicate strong enthusiasm for GenAI image tools, which students viewed as supportive during early-stage design processes and beneficial to their creativity and potential future professional competitiveness. Participants regarded AI use as ethically acceptable when accompanied by transparent acknowledgment. However, acceptance declined in later design stages, where originality and critical judgment were perceived as more central. While limited in scope, this exploratory study foregrounds student voices to offer preliminary insights into evolving conversations about AI in creative education and to inform future reflection on developing ethically and pedagogically responsive curricula across the design disciplines. Full article

Accurate detection of student behavior in the classroom helps analyze students’ learning states and contributes to improving teaching effectiveness. We propose the PLA-YOLO11n classroom behavior detection model. We design a novel C3K2_PConv module that integrates partial convolution with modules from the YOLO11 network and apply it to the backbone and neck feature fusion layers. To enhance small-target feature representation, we incorporate a large-kernel self-attention (LSKA) mechanism and replace the SPPF at the end of the backbone with the attention feature integration module (AIFI). We also add a high-resolution detection head. Experimental results on the SCB2 dataset demonstrate that the improved model outperforms the original YOLO11, achieving an increase of 3.8% in mean average precision (mAP@0.5). Full article

Background: This systematic review examines the lived experiences of Black students in UK higher education (HE), focusing on their encounters with racism and racial disadvantage, and how institutional and social factors contribute to these experiences. Methods: We conducted a systematic search across seven databases (Academic Search Complete, Education Abstracts, PsycINFO, Race Relations Abstracts, Scopus, Web of Science, and SocINDEX) in April 2023, with periodic updates. The grey literature, which refers to research and information produced outside of traditional academic publishing and distribution channels, was reviewed. This includes reports, policy briefs, theses, conference proceedings, government documents, and materials from organisations, think tanks, or professional bodies that are not commercially published or peer-reviewed but can still offer valuable insights relevant to the topic. Hand searches were also included. Studies were included if they were peer-reviewed, published between 2012 and 2024, written in English, and focused on the experiences of Black students in UK higher education. Both qualitative and quantitative studies with a clear research design were eligible. Studies were excluded if they lacked methodological rigour, did not focus on the UK HE context, or did not disaggregate Black student experiences. Risk of bias was assessed using standard qualitative appraisal tools. Thematic analysis was used to synthesise findings. Results: Nineteen studies were included in the review. Two main themes emerged: (1) diverse challenges including academic barriers and difficulties with social integration, and (2) the impact of racism and institutional factors, such as microaggressions and biased assessments. These issues contributed to mental fatigue and reduced academic performance. Support systems and a sense of belonging helped mitigate some of the negative effects. Discussion: The evidence was limited by potential bias in reporting and variability in study quality. Findings reveal persistent racial inequalities in UK HE that affect Black students’ well-being and outcomes. Institutional reforms, increased representation, and equity-focused policies are needed. Future research should explore effective interventions to reduce the awarding gap and support Black student success Full article

Knowledge tracing, the computational modeling of student learning progression through sequential educational interactions, represents a critical component for adaptive learning systems and personalized education platforms. However, existing approaches face a fundamental trade-off between predictive accuracy and interpretability: deep sequence models excel at capturing complex temporal dependencies in student interaction data but lack transparency in their decision-making processes, while probabilistic graphical models provide interpretable causal relationships but struggle with the complexity of real-world educational sequences. We propose a hybrid architecture that integrates transformer-based sequence modeling with structured Bayesian causal networks to overcome this limitation. Our dual-pathway design employs a transformer encoder to capture complex temporal patterns in student interaction sequences, while a differentiable Bayesian network explicitly models prerequisite relationships between knowledge components. These pathways are unified through a cross-attention mechanism that enables bidirectional information flow between temporal representations and causal structures. We introduce a joint training objective that simultaneously optimizes sequence prediction accuracy and causal graph consistency, ensuring learned temporal patterns align with interpretable domain knowledge. The model undergoes pre-training on 3.2 million student–problem interactions from diverse MOOCs to establish foundational representations, followed by domain-specific fine-tuning. Comprehensive experiments across mathematics, computer science, and language learning demonstrate substantial improvements: 8.7% increase in AUC over state-of-the-art knowledge tracing models (0.847 vs. 0.779), 12.3% reduction in RMSE for performance prediction, and 89.2% accuracy in discovering expert-validated prerequisite relationships. The model achieves a 0.763 F1-score for early at-risk student identification, outperforming baselines by 15.4%. This work demonstrates that sophisticated temporal modeling and interpretable causal reasoning can be effectively unified for educational applications. Full article

Edge detection of space targets is vital in aerospace applications, such as satellite monitoring and analysis, yet it faces challenges due to diverse target shapes and complex backgrounds. While deep learning-based edge detection methods dominate due to their powerful feature representation capabilities, they often suffer from large parameter sizes and lack explicit geometric prior constraints for space targets. This paper proposes a novel edge detection method for satellite targets based on knowledge distillation, namely STED-KD. Firstly, a multi-stage distillation strategy is proposed to guide a lightweight, fully convolutional network with fewer parameters to learn key features and decision boundaries from a complex teacher model, achieving model efficiency. Next, a shape prior guidance module is integrated into the student branch, incorporating geometric shape information through shape prior model construction, similarity metric calculation, and feature reconstruction, enhancing adaptability to space targets and improving detection accuracy. Additionally, a curvature-guided edge loss function is designed to ensure continuous and complete edges, minimizing local discontinuities. Experimental results on the UESD space target dataset demonstrate superior performance, with ODS, OIS, and AP scores of 0.659, 0.715, and 0.596, respectively. On the BSDS500, STED-KD achieves ODS, OIS, and AP scores of 0.818, 0.829, and 0.850, respectively, demonstrating strong competitiveness and further confirming its stability. Full article

In this paper, we report how digital resources support engineering students in the early stages of mathematical modelling within a Challenge-Based Education (CBE) course. The study was conducted in a second-year engineering course involving mathematics, physics, and ethics. Through a case study of two student teams, we analyze how a digital curriculum resource—specifically, a dashboard designed for feedback and progress monitoring—helped students identify, define, and begin modelling a real-world problem related to crowd flow on train platforms. Using the instrumental approach, we examined the dual processes of instrumentation (integration of resources) and instrumentalization (adaptation and repurposing of tools). Results show that the Dashboard played a central role in fostering self-regulated learning, interdisciplinary collaboration, and the iterative refinement of guiding questions. Students used data analysis, simulations, and modelling techniques to build and validate mathematical representations in answer to the guiding questions. Our findings contribute to ongoing discussions on how mathematics education in engineering can be enhanced through activity-based learning and targeted use of digital tools. We argue that digital feedback systems like dashboards can bridge the gap between abstract mathematical content and its meaningful application in engineering contexts, thus fostering engagement, autonomy, and authentic learning. Full article

The influence of large language models (LLMs) has permeated education, too. We explored the opportunities and challenges of LLMs in mathematics teaching. In mathematics education, the generative nature of LLMs is appropriate for teachers as it enables an understanding of mathematical knowledge rather than students who lack discernment. Additionally, we combined programming languages with LLMs, using the example of geometric models, to integrate mathematics and visual representation in a new way. Through a comparison of problem-solving between ChatGPT and MathGPT and an analysis of their logical reasoning, teachers can exercise with large models as auxiliary tools to enhance the quality of mathematics teaching. Full article

This article presents the results of a participatory urban diagnosis conducted in District 2 of La Paz, Bolivia, as part of an educational cooperation project aimed at exploring the spatial and symbolic dimensions of urban insecurity. Drawing on feminist and intersectional frameworks, this research combined participatory action methods, digital surveys, and collective mapping to identify patterns of fear and exclusion in public space. The analysis revealed significant disparities in how insecurity is perceived and experienced by different social groups—especially women, Indigenous peoples, and LGTBQ+ individuals—highlighting the importance of spatial configuration, social presence, and care infrastructure in shaping everyday urban life. The project also served as a pedagogical innovation, integrating architecture students into a process of civic engagement and co-production of knowledge. The resulting ‘Map of Gender Insecurity’ contributed to local planning efforts through the “Seguras, No Valientes” initiative. While the limited representation of some groups restricts statistical generalization, the approach offers a replicable model for linking research, education, and public action in pursuit of more inclusive and safer cities. Full article

With the rapid expansion of multi-platform remote sensing applications, cloud contamination significantly impedes cross-platform data utilization. Current cloud detection methods face critical technical challenges in cross-platform settings, including neglect of atmospheric radiative transfer mechanisms, inadequate multi-scale structural decoupling, high intra-class variability coupled with inter-class similarity, cloud boundary ambiguity, cross-modal feature inconsistency, and noise propagation in pseudo-labels within semi-supervised frameworks. To address these issues, we introduce a Physics-Guided Multi-Representation Network (PGMRN) that adopts a student–teacher architecture and fuses tri-modal representations—Pseudo-NDVI, structural, and textural features—via atmospheric priors and intrinsic image decomposition. Specifically, PGMRN first incorporates an InfoNCE contrastive loss to enhance intra-class compactness and inter-class discrimination while preserving physical consistency; subsequently, a boundary-aware regional adaptive weighted cross-entropy loss integrates PA-CAM confidence with distance transforms to refine edge accuracy; furthermore, an Uncertainty-Aware Quadruple Consistency Propagation (UAQCP) enforces alignment across structural, textural, RGB, and physical modalities; and finally, a dynamic confidence-screening mechanism that couples PA-CAM with information entropy and percentile-based thresholding robustly refines pseudo-labels. Extensive experiments on four benchmark datasets demonstrate that PGMRN achieves state-of-the-art performance, with Mean IoU values of 70.8% on TCDD, 79.0% on HRC_WHU, and 83.8% on SWIMSEG, outperforming existing methods. Full article

STEM education is constantly seeking innovative methods to enhance student learning. Virtual Reality technology can represent a critical tool for effectively teaching complex engineering subjects. This study evaluates an original Virtual Reality software application, entitled Submarine Simulator, which is developed specifically to support competencies in hydrodynamics within an Underwater Engineering course at MINES Paris—PSL. Our application uniquely integrates a customized physics engine explicitly designed for realistic underwater simulation, significantly improving user comprehension through accurate real-time representation of hydrodynamic forces. The study involved a homogeneous group of 26 fourth-year engineering students, all specializing in engineering and sharing similar academic backgrounds in robotics, electronics, programming, and computer vision. This uniform cohort, primarily aged 22–28, enrolled in the same 3-month course, was intentionally chosen to minimize variations in skills, prior knowledge, and learning pace. Through a combination of quantitative assessments and Confirmatory Factor Analysis, we find that Virtual Reality affordances significantly predict user flow state (path coefficient: 0.811) which then predicts user engagement and satisfaction (path coefficient: 0.765). These findings show the substantial educational potential of tailored Virtual Reality experiences in STEM, particularly in engineering, and highlight directions for further methodological refinement. Full article

Exploring learning trajectories based on student thinking is needed to develop the teaching curricula, practices and educational support materials in mathematics for students with visual impairments. Hence, this study aims to reveal student thinking through various instructional tasks and tactile materials to explore the sequence of goals in the learning trajectory. A teaching experiment involving introductory information on algebraic and visual representations regarding advanced mathematical concepts was designed for correspondence and relations. The research was carried out with a braille-literate 10th-grade high school student with a congenital visual impairment where colour and light are not perceived in Türkiye. As a result of the teaching experiment, the participant was able to determine the correspondence and relations between two sets using different representations. He even designed graphic representations using the needle page. The learning trajectory goals and instructional tasks can serve as guides for research on curriculum development, practice design and material development. Full article

This paper proposes a novel virtual-fixtures-based shared control concept for eye surgery systems focusing on cataract procedures, one of the most common ophthalmic surgeries. Current research on haptic force feedback aims to enhance manipulation capabilities by integrating teleoperated medical robots. Our proposed concept utilizes teleoperated medical robots to improve the training of young surgeons by providing haptic feedback during cataract operations based on geometrical virtual fixtures. The core novelty of our concept is the active guidance to the incision point generated directly from the geometrical representation of the virtual fixtures, and, therefore, it is computationally efficient. Furthermore, novel virtual fixtures are introduced for the posterior corneal surface of the eye during the cataract operation. The concept is tested in a human-in-the-loop pilot study, where non-medical engineering students participated. The results indicate that the proposed shared control system is helpful for the test subjects. Therefore, the inclusion of the proposed concept can be beneficial for the training of non-experienced surgeons. Full article

Traditional educational assessment systems suffer from inefficient question selection strategies that fail to optimally probe student knowledge while requiring extensive testing time. We present a novel hierarchical probabilistic neural framework that integrates Bayesian inference with symmetric deep neural architectures to enable adaptive, efficient knowledge assessment. Our method models student knowledge as latent representations within a graph-structured concept dependency network, where probabilistic mastery states, updated through variational inference, are encoded by symmetric graph properties and symmetric concept representations that preserve structural equivalences across similar knowledge configurations. The system employs a symmetric dual-network architecture: a concept embedding network that learns scale-invariant hierarchical knowledge representations from assessment data and a question selection network that optimizes symmetric information gain through deep reinforcement learning with symmetric reward structures. We introduce a novel uncertainty-aware objective function that leverages symmetric uncertainty measures to balance exploration of uncertain knowledge regions with exploitation of informative question patterns. The hierarchical structure captures both fine-grained concept mastery and broader domain understanding through multi-scale graph convolutions that preserve local graph symmetries and global structural invariances. Our symmetric information-theoretic method ensures balanced assessment strategies that maintain diagnostic equivalence across isomorphic concept subgraphs. Experimental validation on large-scale educational datasets demonstrates that our method achieves 76.3% diagnostic accuracy while reducing the question count by 35.1% compared to traditional assessments. The learned concept embeddings reveal interpretable knowledge structures with symmetric dependency patterns that align with pedagogical theory. Our work generalizes across domains and student populations through symmetric transfer learning mechanisms, providing a principled framework for intelligent tutoring systems and adaptive testing platforms. The integration of probabilistic reasoning with symmetric neural pattern recognition offers a robust solution to the fundamental trade-off between assessment efficiency and diagnostic precision in educational technology. Full article

Eurocentric portrayals of Africa remain entrenched in European educational systems, perpetuating stereotypes of poverty, primitiveness, and exoticism. This study investigates how such representations are mirrored in German students’ mental conceptions and how they are interpreted by future educators. Using an interpretivist qualitative design, the study analyzes open-ended responses from 41 Grade 5 and 7 pupils at a lower secondary school in Münster, Germany, and written reflections from 17 teacher trainees enrolled in a master’s course in geography education. Thematic analysis reveals five dominant pupil schemas: poverty and deprivation, environmental determinism, racialization and othering, infrastructural deficit, and the wildlife-tourism gaze, rooted in media, textbooks, teachers, and social networks. Teacher trainees’ reflections ranged from emotional discomfort to critical awareness, with many advocating pedagogical pluralism, the normalization of African modernity, and the cultivation of critical consciousness. However, most proposals remained reformist, lacking a deep epistemological critique. The findings highlight the urgency of integrating decolonial theory, postcolonial critique, and epistemic justice into teacher education. Without such structural reorientation, schools will risk reproducing the very global hierarchies they purport to challenge. Full article

The integration of artificial intelligence (AI) in education offers novel opportunities to enhance critical thinking while also posing challenges to independent cognitive development. In particular, Human-Centered Artificial Intelligence (HCAI) in education aims to enhance human experience by providing a supportive and collaborative learning environment. Rather than replacing the educator, HCAI serves as a tool that empowers both students and teachers, fostering critical thinking and autonomy in learning. This study investigates the potential for AI to become a collaborative partner that assists learning and enriches academic engagement. The research was conducted during the 2024–2025 winter semester within the Pedagogical and Teaching Sufficiency Program offered by the Audio and Visual Arts Department, Ionian University, Corfu, Greece. The research employs a hybrid ethnographic methodology that blends digital interactions—where students use AI tools to create artistic representations—with physical classroom engagement. Data was collected through student projects, reflective journals, and questionnaires, revealing that structured dialog with AI not only facilitates deeper critical inquiry and analytical reasoning but also induces a state of flow, characterized by intense focus and heightened creativity. The findings highlight a dialectic between individual agency and collaborative co-agency, demonstrating that while automated AI responses may diminish active cognitive engagement, meaningful interactions can transform AI into an intellectual partner that enriches the learning experience. These insights suggest promising directions for future pedagogical strategies that balance digital innovation with traditional teaching methods, ultimately enhancing the overall quality of education. Furthermore, the study underscores the importance of integrating reflective practices and adaptive frameworks to support evolving student needs, ensuring a sustainable model. Full article