Search Results (834)

Semantic segmentation in remote sensing images, which is the task of classifying each pixel of the image in a specific category, is widely used in areas such as disaster management, environmental monitoring, precision agriculture, and many others. However, traditional semantic segmentation methods face a major challenge: they require large amounts of annotated data to train effectively. To tackle this challenge, few-shot semantic segmentation has been introduced, where the models can learn and adapt quickly to new classes from just a few annotated samples. This paper presents a comprehensive review of recent advances in few-shot semantic segmentation (FSSS) for remote sensing, covering datasets, methods, and emerging research directions. We first outline the fundamental principles of few-shot learning and summarize commonly used remote-sensing benchmarks, emphasizing their scale, geographic diversity, and relevance to episodic evaluation. Next, we categorize FSSS methods into major families (meta-learning, conditioning-based, and foundation-assisted approaches) and analyze how architectural choices, pretraining strategies, and inference protocols influence performance. The discussion highlights empirical trends across datasets, the behavior of different conditioning mechanisms, the impact of self-supervised and multimodal pretraining, and the role of reproducibility and evaluation design. Finally, we identify key challenges and future trends, including benchmark standardization, integration with foundation and multimodal models, efficiency at scale, and uncertainty-aware adaptation. Collectively, they signal a shift toward unified, adaptive models capable of segmenting novel classes across sensors, regions, and temporal domains with minimal supervision. Full article

We investigate how symmetries present in datasets affect the structure of the latent space learned by Variational Autoencoders (VAEs). Understanding symmetries in data is essential because symmetries determine the true degrees of freedom, constrain generalization, and provide physically interpretable coordinates. We therefore study whether a standard, non-equivariant VAE can reveal symmetry-induced dimensional reduction directly from data, without imposing the symmetry in the architecture. By training VAEs on data originating from simple mechanical systems and particle collisions, we analyze the organization of the latent space through a relevance measure that identifies the most meaningful latent directions. We show that when symmetries or approximate symmetries are present, the VAE self-organizes its latent space, effectively compressing the data along a reduced number of latent variables. This behavior captures the intrinsic dimensionality determined by the symmetry constraints and reveals hidden relations among the features. Furthermore, we provide a theoretical analysis of a simple toy model, demonstrating how, under idealized conditions, the latent space aligns with the symmetry directions of the data manifold. We illustrate these findings with examples ranging from two-dimensional datasets with $O\left(2\right)$ symmetry to realistic datasets from electron–positron and proton–proton collisions. Our results highlight the potential of unsupervised generative models to expose underlying structures in data and offer a novel approach to symmetry discovery without explicit supervision. Full article

Artificial Intelligence (AI) holds transformative potential to revolutionize teaching and learning, yet its rapid integration poses significant challenges for teacher preparation. While AI competencies—encompassing knowledge, skills, and attitudes—are critical for effective integration, limited research has holistically addressed these three interconnected domains. To bridge this gap, this quasi-experimental study (N = 259) evaluated a triadic instructional design synergizing the intelligent technological, pedagogical, and content knowledge (Intelligent-TPACK) framework, Synthesis of Qualitative Data model, and curated AI tools. Pre-service English as a foreign language (EFL) teachers were assigned to an experimental group (n = 137) receiving the structured intervention or a control group (n = 122) engaging in self-directed AI exploration. Results reveal that the experimental group achieved greater gains across all Intelligent-TPACK dimensions and demonstrated higher-order AI applications in lesson planning. Furthermore, the experimental group experienced a significant reduction in perceived pressure and reported higher perceived usefulness regarding AI integration. Qualitative data revealed that hands-on AI tasks enhanced participants’ confidence, yet challenges with prompts and critical adaptation persisted. The findings demonstrate that systematic training is essential for transforming pre-service teachers’ passive awareness into competent AI integration. Finally, this paper proposes practical implications for integrating this triadic framework into teacher education curricula to facilitate sustainable AI adoption. Full article

In the digital era, industries increasingly demand innovation and problem-solving capabilities, making cross-disciplinary integration and creative thinking essential competencies for information management professionals. Although previous studies have shown that Problem-Based Learning (PBL) enhances students’ problem-solving abilities and proactive learning behaviors, its effectiveness in supporting creative extension and conceptual deepening remains limited without structured thinking frameworks. To address this issue, this study integrated PBL with a Two-Tier Mandala Thinking approach based on a nine-grid structure. The proposed method combines first-tier divergent thinking with second-tier spiral convergence to guide students in establishing conceptual foundations, differentiating ideas, and refining design directions. A quasi-experimental study was conducted in a course in which students completed a game design task using either the Two-Tier Mandala Thinking Method or conventional brainstorming strategies. Quantitative results indicate that students in the Mandala Thinking group significantly outperformed those in the brainstorming group across three learning performance metrics. Qualitative findings further revealed that students using the proposed approach exhibited enhanced creative self-efficacy and greater confidence in their creative outcomes. Overall, integrating Two-Tier Mandala Thinking into PBL effectively supported the experimental group in structuring and developing in-depth creative thinking processes, providing empirical evidence for its application in innovation-oriented information education. Full article

While fostering an informed understanding of science is a key educational aim, students often hold simplified, fact-based views of science due to limitations in traditional pedagogy, materials, and resources. Out-of-school learning environments, such as natural history museums (NHMs) and citizen science projects, offer opportunities to deepen scientific understanding by providing authentic insights into scientific work. This study examines how participation in a short-term citizen science project on micrometeorites, conducted in collaboration with a NHM, contributes to students’ understanding of science. Two cohorts of 10th-grade students in an elective STEM course combined classroom learning with museum-based lab experiences to identify and analyze real micrometeorites. Qualitative interviews with students and their teacher revealed that participants gained insight into real scientific work, viewed science as a participatory process, and benefited from self-directed, hands-on learning, including innovative remote access to research instruments. The teacher also emphasized access to lab equipment and authentic research as key benefits, but noted organizational and structural challenges to its implementation, as well as format-specific considerations. The findings highlight the value of school–museum collaboration for promoting citizen science approaches for young people and call for greater institutional support to enable such initiatives more frequently and at a larger scale. Full article

The informal learning spaces (ILSs), as the core carrier supporting students’ autonomous learning and social interaction, have become an indispensable component of modern campuses. However, existing research still has limitations, including the ambiguous definition of ILSs and the lack of analysis of the synergy between social and physical dimension factors and students’ performance. To further explore the above problems, this review conducted a systematic review, in which all included literature was analysed following the PRISMA guidelines. This review retrieved 33 empirical studies from multiple databases in the fields of education, architecture and library science published from 2000 to 2025. The results of this review show that ILSs can be defined as dynamic ecosystems primarily designed to support self-directed and collaborative learning. The ecosystem integrates technological infrastructure, flexible layouts and social interaction to accommodate diverse learning needs. Meanwhile, ILSs’ design needs to coordinate and balance the multiple influencing factors across the social and physical dimensions. Although synthesising findings inevitably involves subjective judgement, this review can provide design guidelines for educators, architects, and policymakers that account for both students’ needs and adaptive functional configurations, thereby offering a practical path to achieving inclusive learning environments and sustainable campus development. Full article

Emotional stress plays a critical role in mental health conditions such as anxiety, depression, and cognitive decline, yet its assessment remains challenging due to the subjective and episodic nature of conventional self-report methods. Multimodal physiological approaches, integrating signals such as electrocardiogram (ECG), electrodermal activity (EDA), and electromyography (EMG), offer a promising alternative by enabling objective, continuous, and complementary characterization of autonomic stress responses. Recent advances in machine learning and artificial intelligence (ML/AI) have become central to this paradigm, as they provide the capacity to model nonlinear dynamics, inter-modality dependencies, and individual variability that cannot be effectively captured by rule-based or single-modality methods. This paper reviews multimodal physiological stress recognition with an emphasis on ECG-centered systems and their integration with EDA and EMG. We summarize stress-related physiological mechanisms, catalog public and self-collected databases, and analyze their ecological validity, synchronization, and annotation practices. We then examine preprocessing pipelines, feature extraction methods, and multimodal fusion strategies across different stages of model design, highlighting how ML/AI techniques address modality heterogeneity and temporal misalignment. Comparative analysis shows that while deep learning models often improve within-dataset performance, their generalization across subjects and datasets remains limited. Finally, we discuss open challenges and future directions, including self-supervised learning, domain adaptation, and standardized evaluation protocols. This review provides practical insights for developing robust, generalizable, and scalable multimodal stress recognition systems for mental health monitoring. Full article

The emerging scope of the Industrial Internet of Services (IIoS) requires a robust intrusion detection system to detect malicious attacks. The increasing frequency of sophisticated and high-impact cyber attacks has resulted in financial losses and catastrophes in IIoS-based manufacturing industries. However, existing solutions often struggle to adapt and generalize to new cyber attacks. This study proposes a unique approach designed for known and zero-day network attack detection in IIoS environments, called Denoising Adaptive Multi-Branch Architecture (DA-MBA). The proposed approach is a smart, conformal, and self-adjusting cyber attack detection framework featuring denoising representation learning, hybrid neural inference, and open-set uncertainty calibration. The model merges a denoising autoencoder (DAE) to generate noise-tolerant latent representations, which are processed using a hybrid multi-branch classifier combining dense and bidirectional recurrent layers to capture both static and temporal attack signatures. Moreover, it addresses challenges such as adaptability and generalizability by hybridizing a Multilayer Perceptron (MLP) and bidirectional LSTM (BiLSTM). The proposed hybrid model was designed to fuse feed-forward transformations with sequence-aware modeling, which can capture direct feature interactions and any underlying temporal and order-dependent patterns. Multiple approaches have been applied to strengthen the dual-branch architecture, such as class weighting and comprehensive hyperparameter optimization via Optuna, which collectively address imbalanced data, overfitting, and dynamically shifting threat vectors. The proposed DA-MBA is evaluated on two widely recognized IIoT-based datasets, Edge-IIoT set and WUSTL-IIoT-2021 and achieves over 99% accuracy and a near 0.02 loss, underscoring its effectiveness in detecting the most sophisticated attacks and outperforming recent deep learning IDS baselines. The solution offers a scalable and flexible architecture for enhancing cybersecurity within evolving IIoS environments by coupling feature denoising, multi-branch classification, and automated hyperparameter tuning. The results confirm that coupling robust feature denoising with sequence-aware classification can provide a scalable and flexible framework for improving cybersecurity within the IIoS. The proposed architecture offers a scalable, interpretable, and risk sensitive defense mechanism for IIoS, advancing secure, adaptive, and trustworthy industrial cyber-resilience. Full article

Microfluidic chip technologies, also known as lab-on-a-chip systems, have profoundly transformed laboratory medicine by enabling the miniaturization, automation, and rapid processing of complex diagnostic assays using minimal sample volumes. Recent advances in chip design, fabrication methods—including 3D printing, modular and flexible substrates—and biosensor integration have significantly enhanced the performance, sensitivity, and clinical applicability of these devices. Integration of advanced biosensors allows for real-time detection of circulating tumor cells, nucleic acids, and exosomes, supporting innovative applications in cancer diagnostics, infectious disease detection, point-of-care testing (POCT), personalized medicine, and therapeutic monitoring. Notably, the convergence of microfluidics with artificial intelligence (AI) and machine learning has amplified device automation, reliability, and analytical power, resulting in “smart” diagnostic platforms capable of self-optimization, automated analysis, and clinical decision support. Emerging applications in fields such as neuroscience diagnostics and microbiome profiling further highlight the broad potential of microfluidic technology. Here, we present findings from a comprehensive review of recent innovations in microfluidic chip design and fabrication, advances in biosensor and AI integration, and their clinical applications in laboratory medicine. We also discuss current challenges in manufacturing, clinical validation, and system integration, as well as future directions for translating next-generation microfluidic technologies into routine clinical and public health practice. Full article

Drawing on digital agency theory, expectancy–value frameworks, and self-regulated learning perspectives, this study proposes and tests a moderated mediation model explaining students’ intentions to use AI. Using data from 673 university students, we examined whether sense of positive agency (SOPA) predicts intention to use AI indirectly through perceived value and perceived benefits of AI, and whether these pathways are conditionally shaped by sense of negative agency (SONA). Conditional process analysis (PROCESS Model 59) showed that SOPA had no direct effect on intention to use AI (b = 0.013, p = 0.882). Instead, its influence was fully indirect and conditional. SOPA predicted perceived value and perceived benefits of AI only at moderate to high levels of SONA, with significant SOPA × SONA interactions for both mediators (p = 0.040). Perceived value strongly predicted intention to use AI (b = 0.385, p < 0.001), and this relationship was amplified at higher levels of negative agency (b = 0.138, p = 0.002). In contrast, the effect of perceived benefits on intention weakened as SONA increased (b = −0.125, p = 0.005), becoming non-significant at higher levels of negative agency (Johnson–Neyman point ≈ 2.99). The final model explained 50.4% of the variance in intention to use AI. Overall, the findings indicate a conditional appraisal mechanism: as negative agency increases, perceived value becomes a stronger predictor of intention, whereas the motivational contribution of perceived benefits weakens and becomes non-significant beyond the Johnson–Neyman threshold. These results support an agency-aware account of AI adoption focused on how cognitive appraisals relate to intention under different perceived agency orientations, without implying ethical reasoning or moral deliberation processes not measured in this study. Full article

Condition monitoring has come to the forefront of intelligent manufacturing and is particularly important in Computer Numerical Control (CNC) machining processes, where reliability, precision, and productivity are crucial. The traditional methods of monitoring, which are mostly premised on single sensors, the localized capture of data, and offline interpretation, are proving too small to handle current machining processes. Being limited in their scale, having limited computational power, and not being responsive in real-time, they do not fit well in a dynamic and data-intensive production environment. Recent progress in the Industrial Internet of Things (IIoT), cloud computing, and edge intelligence has led to a push into distributed monitoring architectures capable of obtaining, processing, and interpreting large amounts of heterogeneous machining data. Such innovations have facilitated more adaptive decision-making approaches, which have helped in supporting predictive maintenance, enhancing machining stability, tool lifespan, and data-driven optimization in manufacturing businesses. A structured literature search was conducted across major scientific databases, and eligible studies were synthesized qualitatively. This systematic review synthesizes over 180 peer-reviewed studies found in major scientific databases, using specific inclusion criteria and a PRISMA-guided screening process. It provides a comprehensive look at sensor technologies, data acquisition systems, cloud–edge–IoT frameworks, and digital twin implementations from an architectural perspective. At the same time, it identifies ongoing challenges related to industrial scalability, standardization, and the maturity of deployment. The combination of cloud platforms and edge intelligence is of particular interest, with emphasis placed on how the two ensure a balance in the computational load and latency, and improve system reliability. The review is a synthesis of the major advances associated with sensor technologies, data collection approaches, machine operations, machine learning, deep learning methods, and digital twins. The paper concludes with what can and cannot be performed to date by providing a comparative analysis of what is known about this topic and the reported industrial case applications. The main issues, such as the inconsistency of data, the lack of standardization, cyber threats, and old system integration, are critically analyzed. Lastly, new research directions are touched upon, including hybrid cloud–edge intelligence, advanced AI models, and adaptive multisensory fusion, which is oriented to autonomous and self-evolving CNC monitoring systems in line with the Industry 4.0 and Industry 5.0 paradigms. The review process was made transparent and repeatable by using a PRISMA-guided approach to qualitative synthesis and literature screening. Full article

With the implementation of the 2022 revised curriculum in South Korea, significant changes are taking place in education as of 2025. This curriculum emphasizes self-directed learning and a proactive attitude toward life, which are essential in the era of digital transformation. Accordingly, there is a growing need to establish systematic environments that support self-directed learning. The number of instructional hours for information education has been doubled to 34 h in elementary school and 68 h in middle school, highlighting the increased importance of the subject. In addition, 2025 marked the official introduction of AI-based digital textbooks. However, their diversity and functionality as effective learning resources remain limited. In programming education, most studies on learning difficulty have focused on basic concepts, while research on more advanced topics, such as object-oriented programming, has been insufficient. Therefore, this research aims to develop a digital learning tool that supports high school students in engaging in self-directed learning. Specifically, it focuses on the “Implementing Classes for Objects” unit from the MiraeN textbook and provides customized support within a tablet-based learning environment. The tool also includes chatbot-based problem generation and feedback functions. To analyze the accuracy and level of the problems generated by the chatbot, both the researcher and ChatGPT were used simultaneously. Full article

Medical artificial intelligence (AI) systems depend heavily on high-quality data representations to support accurate prediction, diagnosis, and clinical decision-making. However, the availability of large, well-annotated medical datasets is often constrained by cost, privacy concerns, and the need for expert labeling, motivating growing interest in self-supervised representation learning. Among these approaches, contrastive learning has emerged as one of the most influential paradigms, driving major advances in representation learning across computer vision and natural language processing. This paper presents a comprehensive review of contrastive learning in medical AI, highlighting its theoretical foundations, methodological developments, and practical applications in medical imaging, electronic health records, physiological signal analysis, and genomics. Furthermore, we identify recurring challenges, including pair construction, sensitivity to data augmentations, and inconsistencies in evaluation protocols, while discussing emerging trends such as multimodal alignment, federated learning, and privacy-preserving frameworks. Through a synthesis of current developments and open research directions, this review provides insights to advance data-efficient, reliable, and generalizable medical AI systems. Full article

Localization and mapping remain critical challenges for Unmanned Ground Vehicles (UGVs) operating in unstructured natural environments, such as forests and agricultural fields. While Visual SLAM (VSLAM) and Visual–Inertial SLAM (VI-SLAM) have matured significantly in structured and urban scenarios, their extension to outdoor natural domains introduces severe challenges, including dynamic vegetation, illumination variations, a lack of distinctive features, and degraded GNSS availability. Recent advances in Deep Learning have brought promising developments to VSLAM- and VI-SLAM-based pipelines, ranging from learned feature extraction and matching to self-supervised monocular depth prediction and differentiable end-to-end SLAM frameworks. Furthermore, emerging methods for adaptive sensor fusion, leveraging attention mechanisms and reinforcement learning, open new opportunities to improve robustness by dynamically weighting the contributions of camera and IMU measurements. This review provides a comprehensive overview of Visual and Visual–Inertial SLAM for UGVs in unstructured environments, highlighting the challenges posed by natural contexts and the limitations of current pipelines. Classic VI-SLAM frameworks and recent Deep-Learning-based approaches were systematically reviewed. Special attention is given to field robotics applications in agriculture and forestry, where low-cost sensors and robustness against environmental variability are essential. Finally, open research directions are discussed, including self-supervised representation learning, adaptive sensor confidence models, and scalable low-cost alternatives. By identifying key gaps and opportunities, this work aims to guide future research toward resilient, adaptive, and economically viable VSLAM and VI-SLAM pipelines, tailored for UGV navigation in unstructured natural environments. Full article

Wireless Sensor Networks (WSNs) are widely deployed for long-term monitoring in environments characterized by nonstationary sensing dynamics, intermittent connectivity and continuously evolving network topologies, while reliable, fine-grained labeled data capturing faults and adversarial behaviors remain scarce. This survey systematically reviews and synthesizes recent research that integrates autoencoder-based representation learning with self-supervised learning (SSL) objectives to enhance anomaly detection under these practical constraints. We structure the existing literature through a unified taxonomy encompassing autoencoder variants, self-supervised pretext tasks, spatio-temporal encoding mechanisms and the increasing use of graph-structured autoencoders for topology-aware modeling. Across distinct methodological categories, SSL-augmented frameworks consistently demonstrate improved robustness and stability compared to purely reconstruction-driven baselines, particularly in heterogeneous, dynamic and temporally drifting WSN environments. Nevertheless, this review also highlights several unresolved challenges that hinder real-world adoption, including uncertain scalability to large-scale networks, limited model interpretability, nontrivial energy and memory overheads on resource-constrained sensor nodes and a lack of standardized evaluation protocols and reporting practices. By consolidating publicly available datasets, experimental configurations and comparative performance trends, we derive concrete design requirements for robust and resource-aware anomaly detection in operational WSNs and outline promising future research directions, emphasizing lightweight model architectures, explainable learning mechanisms and federated AE–SSL paradigms to enable adaptive, privacy-preserving monitoring in next-generation IoT sensing systems. Full article