Search Results (3,329)

To address the lack of effective risk-identification methods during the commissioning of new power grid equipment, we propose a knowledge graph construction approach for both scheme generation and risk identification. First, a gated attention mechanism fuses textual semantics with knowledge embeddings to enhance feature representation. Then, by introducing a global memory matrix with a decay-factor update mechanism, long-range dependencies across paragraphs are captured, yielding a domain-knowledge-augmentation universal information-extraction framework (DKA-UIE). Using the DKA-UIE, we learn high-dimensional mappings of commissioning-scheme entities and their labels, linking them according to equipment topology and risk-identification logic to build a commissioning knowledge graph for new equipment. Finally, we present an application that utilizes this knowledge graph for the automated generation of commissioning plans and risk identification. Experimental results show that our model achieves an average precision of 99.19%, recall of 99.47%, and an F₁-score of 99.33%, outperforming existing methods. The resulting knowledge graph effectively supports both commissioning-plan generation and risk identification for new grid equipment. Full article

In this study, we propose an interactive environment-aware dialog and planning system for social robots in early childhood education, aimed at supporting the learning and social interaction of young children. The proposed architecture consists of three core modules. First, semantic simultaneous localization and mapping (SLAM) accurately perceives the environment by constructing a semantic scene representation that includes attributes such as position, size, color, purpose, and material of objects, as well as their positional relationships. Second, the automated planning system enables stable task execution even in changing environments through planning domain definition language (PDDL)-based planning and replanning capabilities. Third, the visual question answering module leverages scene graphs and SPARQL conversion of natural language queries to answer children’s questions and engage in context-based conversations. The experiment conducted in a real kindergarten classroom with children aged 6 to 7 years validated the accuracy of object recognition and attribute extraction for semantic SLAM, the task success rate of the automated planning system, and the natural language question answering performance of the visual question answering (VQA) module.The experimental results confirmed the proposed system’s potential to support natural social interaction with children and its applicability as an educational tool. Full article

Electrical impedance measurements are traditionally macroscopic screening techniques designed to obtain information about the macroscopic internal structure of biological systems. In order to overcome the limitations that the technology detects, mainly with the bulk properties, a miniaturization is employed by developing a complex microfluidic system to achieve cell-scale information. In this work, a microelectrode array was incorporated into a microfluidic chip, allowing localized Electrochemical Impedance Spectroscopy (EIS) measurements, providing impedance data obtained in the spatial and frequency domains simultaneously. The height of the capillary in the microfluidic system was also systematically modified; hence, three types of channels with heights of 10 $\mu$m, 30 $\mu$m, and 50 $\mu$m were developed and studied. The EIS data collection was implemented using two different strategies (two- and four-electrode techniques). Sensitivity analysis was conducted using a microbead solution, where the linear mapping of the number of microbeads along the channel was achieved by EIS. Based on the findings, a complete overview of each measurement implementation was obtained, which is well explained by the physical background presented in the paper. In the case where the capillary height (10 $\mu$m) is comparable to the diameter of the microbeads (6 $\mu$m), the four-electrode technique detected the beads in a wider frequency range (approximately between 500 Hz and 50 kHz), while the two-electrode technique detected the beads in a narrower frequency range (approximately between 30 kHz and 300 kHz) with correlation greater than 0.9. In all other cases, a medium (or weak) correlation was found between the impedance data and the longitudinal bead distribution. Based on the results, the technology is ready for further development and adaptation for cell culture purposes. Full article

Accurate diagnosis of myocardial infarction (MI) holds significant clinical importance for public health systems. Deep learning-based ECG, classification and localization methods can automatically extract features, thereby overcoming the dependence on manual feature extraction in traditional methods. However, these methods still face challenges such as insufficient utilization of dynamic information in cardiac cycles, inadequate ability to capture both global and local features, and data imbalance. To address these issues, this paper proposes a ResNet-Transformer cascaded network (RTCN) to process time frequency features of ECG signals generated by the S-transform. First, the S-transform is applied to adaptively extract global time frequency features from the time frequency domain of ECG signals. Its scalable Gaussian window and high phase resolution can effectively capture the dynamic changes in cardiac cycles that traditional methods often fail to extract. Then, we develop an architecture that combines the Transformer attention mechanism with ResNet to extract multi-scale local features and global temporal dependencies collaboratively. This compensates for the existing deep learning models’ insufficient ability to capture both global and local features simultaneously. To address the data imbalance problem, the Denoising Diffusion Probabilistic Model (DDPM) is applied to synthesize high-quality ECG samples for minority classes, increasing the inter-patient accuracy from 61.66% to 68.39%. Gradient-weighted Class Activation Mapping (Grad-CAM) visualization confirms that the model’s attention areas are highly consistent with pathological features, verifying its clinical interpretability. Full article

Big L days are days when the lunar semidiurnal variation M₂ in the ionosphere is strongly enhanced by a factor of 2 or more. The worldwide network of ground-based receivers for the Global Navigation Satellite System (GNSS) has monitored the ionospheric total electron content (TEC) since 1998. The derived world maps of TEC are provided by the International GNSS Service (IGS) and allow the study of the characteristics of big L days in TEC. In the data analysis, the signal of the lunar semidiurnal variation M₂ in TEC is separated from the solar semidiurnal variation S₂ by means of windowing in the spectral domain. The time series of the M₂ amplitude often shows enhancements of M₂ (big L days) a few days after sudden stratospheric warmings (SSWs). The M₂ amplitude can reach values of 8 TECU. The M₂ composite of all SSWs from 1998 to 2024 shows that the M₂ amplitude is enhanced after the central date of the SSW. Regions in Southern China and South America show stronger effects of big L days. Generally, the effects of big L days on TEC show latitudinal and longitudinal dependencies. Full article

Computation modeling for large thermoplastic deformation of plastic solids is critical for industrial applications like non-invasive assessment of engineering components. While deep learning-based methods have emerged as promising alternatives to traditional numerical simulations, they often suffer from systematic errors caused by geometric mismatches between predicted and ground truth meshes. To overcome this limitation, we propose a novel boundary geometry-constrained neural framework that establishes direct point-wise mappings between spatial coordinates and full-field physical quantities within the deformed domain. The key contributions of this work are as follows: (1) a two-stage strategy that separates geometric prediction from physics-field resolution by constructing direct, point-wise mappings between coordinates and physical quantities, inherently avoiding errors from mesh misalignment; (2) a boundary-condition-aware encoding mechanism that ensures physical consistency under complex loading conditions; and (3) a fully mesh-free approach that operates on point clouds without structured discretization. Experimental results demonstrate that our method achieves a 36–98% improvement in prediction accuracy over deep learning baselines, offering a efficient alternative for high-fidelity simulation of large thermoplastic deformations. Full article

Active transport (AT) offers an effective and sustainable strategy to address physical inactivity, reduce traffic congestion, and mitigate environmental challenges. However, participation in AT among young adults (YA) aged 18–25 remains low, leading to public health issues. This review synthesises evidence on how traffic stress (TS), built environment (BE) features, and socioecological factors interact to shape AT behaviour among YA, a relationship that remains insufficiently understood. We systematically reviewed 173 peer-reviewed studies (2015–2025) from Web of Science (WoS), PubMed, and Scopus, following the PRISMA 2020 guidelines. Thematic analysis, bibliometric mapping, and meta-synthesis informed the impact of TS, the Level of Traffic Stress (LTS), the 5Ds of BE, and the Socioecological Model (SEM) on AT among YA. The findings show that high TS, characterised by unsafe road conditions, high-speed motor traffic, and inadequate walking or cycling facilities, consistently reduces AT participation. In contrast, supportive BE features, including street connectivity, land-use diversity, and destination accessibility, increase AT by reducing TS while enhancing safety and comfort. Socioecological factors, including self-efficacy, social norms, and peer support, further mediate these effects. This review introduces two novel metrics: Daily Traffic Stress (DTS), a time-sensitive measure of cumulative daily TS exposure, and the Stress-to-Step Ratio (SSR), a step-based index that standardises how stress exposures translate into AT behaviour. By integrating environmental and psychosocial domains, it offers a theoretical contribution as well as a practical foundation for targeted, multilevel policies to increase AT among YA and foster healthier, more equitable urban mobility. Full article

Detecting and classifying construction workers’ drowsiness is critical in the construction safety management domain. Research efforts to increase the reliability of drowsiness detection through image augmentation and computer vision approaches face two key challenges: the related size constraints and the number of manual tasks associated with creating input images necessary for training vision algorithms. Although text-to-image (T2I) has emerged as a promising alternative, the dynamic relationship between T2I-driven image characteristics (e.g., contextual relevance), different computer vision algorithms, and the resulting performance remains lacking. To address the gap, this study proposes T2I-centered computer vision approaches for enhanced drowsiness detection by creating four separate image sets (e.g., construction vs. non-construction) labeled using the polygon method, developing two detection models (YOLOv8 and YOLO11), and comparing the performance. The results showed that the use of construction domain-specific images for training both YOLOv8 and YOLO11 led to higher mAP@50 of 68.2% and 56.6%, respectively, compared to those trained using non-construction images (53.4% and 53.5%). Also, increasing the number of T2I-generated training images improved mAP@50 from 68.2% (baseline) to 95.3% for YOLOv8 and 56.6% to 93.3% for YOLO11. The findings demonstrate the effectiveness of leveraging the T2I augmentation approach for improved construction workers’ drowsiness detection. Full article

The accelerating complexity of urban environments has prompted cities to adopt digital technologies that improve efficiency, sustainability, and resilience. Among these, Urban Digital Twins (UDTw) have emerged as transformative tools for real-time representation, simulation, and management of urban systems. This Systematic Literature Review (SLR) examines the integration of Digital Twins (DTw), the Internet of Things (IoT), and Artificial Intelligence (AI) into the Smart City Development (SCD). Following the PSALSAR framework and PRISMA 2020 guidelines, 64 peer-reviewed articles from IEEE Xplore, Association for Computing Machinery (ACM), Scopus, and Web of Science (WoS) digital libraries were analyzed by using bibliometric and thematic methods via the Bibliometrix package in R. The review allowed identifying key technological trends, such as edge–cloud, architectures, 3D immersive visualization, Generative AI (GenAI), and blockchain, and classifies UDTw applications into five domains: traffic management, urban planning, environmental monitoring, energy systems, and public services. Persistent challenges have been also outlined, including semantic interoperability, predictive modeling, data privacy, and impact evaluation. This study synthesizes the current state of the field, by clearly identifying a thematic mapping, and proposes a research agenda to align technical innovation with measurable urban outcomes, offering strategic insights for researchers, policymakers, and planners. Full article

Semantic technologies based on ontologies and knowledge graphs are increasingly recognized for their potential to enhance safety, risk, and emergency management in railway systems. This paper presents a systematic literature review aimed at identifying how ontologies, knowledge graphs, and the technologies based on them are applied within the domain of railway safety and assessing their contributions. A total of 53 relevant papers were analyzed using a structured review process, covering four main areas: risk management, safety management, emergency management, and accident analysis. The results reveal that ontologies and knowledge graphs support proactive hazard identification, formalization of safety knowledge, intelligent emergency response, and detailed accident causation modeling. Moreover, they enable semantic interoperability, reasoning, and automation across complex socio-technical railway systems. Despite their benefits, challenges remain regarding data heterogeneity, scalability, and the lack of semantic standardization. This study identifies the most relevant models and technologies, such as SRAC, SRI-Onto, and transformer-based graph neural networks, highlighting their role in advancing intelligent railway safety solutions. This work contributes a detailed map of the current state of semantic applications in railway safety and offers insight into emerging opportunities for future development. Full article

Tall-pier, long-span continuous rigid-frame bridges are prone to wind-induced vibration due to their large spans and pier heights; during cantilever erection, the maximum double-cantilever stage has reduced stiffness and buffeting becomes more evident. Accordingly, a time-domain framework driven by three-component aerodynamic coefficients and their angle-of-attack derivatives is adopted. Code-based target spectra are used to synthesize multi-point fluctuating wind time histories via harmonic superposition, followed by statistical and spectral consistency checks. Buffeting forces are then computed under the quasi-steady assumption, mapped to finite-element nodes, and integrated in time to obtain global responses (displacement and acceleration). In parallel, static six-component wind tunnel tests provide mean force and moment coefficients and their derivatives for comparison. The results indicate that the three-component time-domain approach captures the buffeting features dominated by vertical and torsional responses. When pronounced along-span sectional variation and high angle-of-attack sensitivity are present, errors associated with the strip assumption increase, whereas the force–moment coupling revealed by the six-component data helps explain discrepancies between simulation and tests. These response patterns and error characteristics delineate the applicability and limits of the three-component time-domain evaluation for variable-depth continuous rigid-frame bridges, offering a reference for wind resistance assessment and construction-stage checking of similar bridges. Full article

Generative steganography (GS) generates stego-media via secret messages, but existing GS only targets single-type multimedia data with poor universality. The generator and extractor sizes are highly coupled with resolution. Message mapping converts secret messages and noise, yet current GS schemes based on it use gridded data, failing to generate diverse multimedia universally. Inspired by implicit neural representation (INR), we propose generative implicit steganography via message mapping (GIS). We designed single-bit and multi-bit message mapping schemes in function domains. The scheme’s function generator eliminates the coupling between model and gridded data sizes, enabling diverse multimedia generation and breaking resolution limits. A dedicated point cloud extractor is trained for adaptability. Through a literature review, this scheme is the first to perform message mapping in the functional domain. During the experiment, taking images as an example, methods such as PSNR, StegExpose, and neural pruning were used to demonstrate that the generated image quality is almost indistinguishable from the real image. At the same time, the generated image is robust. The accuracy of message extraction can reach 96.88% when the embedding capacity is 1 bpp, 89.84% when the embedding capacity is 2 bpp, and 82.21% when the pruning rate is 0.3. Full article

Deep learning has emerged as a powerful tool in computational neuroscience, enabling the modeling of complex neural processes and supporting data-driven insights into brain function. However, the non-transparent nature of many deep learning models limits their interpretability, which is a significant barrier in neuroscience and clinical contexts where trust, transparency, and biological plausibility are essential. This review surveys structured explainable deep learning methods, such as saliency maps, attention mechanisms, and model-agnostic interpretability frameworks, that bridge the gap between performance and interpretability. We then explore explainable deep learning’s role in visual neuroscience and clinical neuroscience. By surveying literature and evaluating strengths and limitations, we highlight explainable models’ contribution to both scientific understanding and ethical deployment. Challenges such as balancing accuracy, complexity and interpretability, absence of standardized metrics, and scalability are assessed. Finally, we propose future directions, which include integrating biological priors, implementing standardized benchmarks, and incorporating human-intervention systems. The research study highlights the position of explainable deep learning, not only as a technical advancement but represents it as a necessary paradigm for transparent, responsible, auditable, and effective computational neuroscience. In total, 177 studies were reviewed as per PRISMA, which provided evidence across both visual and clinical computational neuroscience domains. Full article

This study conducts a comprehensive bibliometric analysis of research applying data envelopment analysis (DEA) to the evaluation of sustainability and performance in complex socioeconomic systems between 2010 and mid-2025. DEA has become an increasingly valuable tool for measuring efficiency, benchmarking practices, and supporting decision-making in contexts where sustainability challenges intersect with economic, environmental, and governance dimensions. To capture global research dynamics, we extracted and merged bibliographic data from Web of Science and Scopus, analyzing publication trends, thematic clusters, co-authorship networks, citation structures, and keyword co-occurrences using bibliometric tools such as VOSviewer and Bibliometrix. Our findings reveal a consistent growth trajectory of the field, with research outputs peaking in 2020 and subsequently diversifying across multiple thematic areas. Conceptual mapping highlights two dominant domains: (i) policy, governance, and planning and (ii) environmental, ecological, and management applications, both linked through the overarching theme of sustainable development. The analysis further underscores the geographic diversity of contributions, the concentration of knowledge in key publication outlets, and the increasing connectivity of international collaboration networks. By identifying thematic gaps and underexplored intersections, this study emphasizes the need for more interdisciplinary approaches that integrate bibliometric insights with practical sustainability outcomes. The results provide a structured overview of the field’s evolution, offering researchers and policymakers a valuable reference point for advancing DEA applications in sustainability research. Full article

This study, based on a 25-year dataset (2000–2025) collected from the Scopus database, provides a comprehensive bibliometric analysis of the intellectual structure of research on emotion recognition, prediction, and skills. Using bibliographic coupling as the primary method, the analysis examines the titles, abstracts, keywords, frameworks, and review literature, presenting the most significant articles in this area, along with the headings of 202 relevant papers. The study investigates the temporal distribution of research outputs, focusing particularly on trends from the last decade. To visualize the scientific landscape, the study uses VOSviewer to map co-authorship, keyword co-occurrence, and citation networks. The analysis highlights the most prolific journals, influential authors, dominant subject areas, and frequently used keywords. Additionally, it identifies the algorithms used for emotion recognition in predicting soft skills, along with the objectives of the studies, as well as the data and results involved. The study also identifies the leading countries and educational institutions contributing to this research domain. The findings offer a detailed overview of the field’s development and intellectual trends, providing insights and recommendations for future research directions. This research also helps to understand how emotion recognition can contribute to human development across various domains, as discussed in this article. Full article