Search Results (48,311)

Falls are a leading cause of paediatric injuries, yet school-based prevention relies heavily on subjective observation rather than objective biomechanical assessment. This paper introduces the Safe Fall framework, integrating a judo-inspired educational programme with an occlusion-robust computer vision pipeline to quantify safe falling strategies. We analysed video recordings of 285 schoolchildren using a multi-stage architecture combining YOLOv8 for detection, SAM 2 for segmentation, and MMPose for skeletal tracking. The intervention yielded significant improvements in 60% of kinematic metrics ($p<0.05$), most notably a $+61.4\%$ increase in descent rate and expanded rolling ranges, indicating a shift from hazardous “freezing” behaviours to controlled energy dissipation. Unsupervised clustering confirmed a migration of students towards safe motor profiles, while a Random Forest classifier achieved an accuracy of 98.3% and an AUC of 0.998 in distinguishing fall quality. These findings demonstrate that integrating pedagogical training with automated vision modelling provides a scalable and evidence-based approach for reducing injury risk in real-world school environments. Full article

Same-level falls are the most frequent occupational accidents, yet traditional manual analysis of accident reports is labor-intensive and limits large-scale prevention strategies. In this pilot study, we aimed to evaluate the accuracy of using large language models (LLMs) to automate the classification of occupational accident text data without task-specific pretraining. We analyzed data from 2619 same-level-fall-related injury cases, using expert manual classification as the reference standard. Four models—GPT-4o mini, GPT-4.1 mini, GPT-4.1, and o4-mini—were compared using accuracy and Cohen’s kappa. The o4-mini model demonstrated the highest performance, showing statistical superiority in the complex “causal agent” category with 72.8% accuracy. For other classification tasks, the top models achieved accuracies of 82–92%, with Cohen’s kappa coefficients > 0.7, indicating substantial agreement with expert judgments. These findings suggest that LLMs can classify occupational accident text with substantial agreement with the expert-derived reference standard in this dataset. This automated approach enables efficient, high-frequency analysis of large datasets, offering a promising tool for large-scale occupational accident surveillance and screening. Full article

This paper presents a practical implementation of relative primary radiation thermometry (RPRT) together with MultiFixRadSoft, an open-source software package developed in accordance with the Mise-en-Pratique for the kelvin (MeP-K) for realization of the thermodynamic temperature scale and uncertainty evaluation under the new definition of the kelvin. The software enables realization of temperature scales using ITS-90 metal fixed points as well as metal–carbon and metal–carbide–carbon eutectic high-temperature fixed points (HTFPs) for both radiation thermometers and radiometers. It incorporates automated routines for melting plateau analysis, including determination of the point of inflection, liquidus point, and melting range, together with correction modules for size-of-source effect, detector nonlinearity, emissivity, and temperature drop. Validation is demonstrated through experimental realization using six fixed points (Cu, Fe–C, Co–C, Pd–C, Ru–C, and WC–C) and a linear radiation thermometer. The software also supports ITS-90 extrapolation procedures and flexible calibration schemes (n = 1 to n ≥ 3), with automated Sakuma–Hattori fitting and full uncertainty propagation compliant with MeP-K requirements. The results show excellent agreement with manual analyses and published data, confirming the correctness of the implemented algorithms. By integrating data processing, scale realization, and uncertainty analysis within a unified and transparent framework, MultiFixRadSoft provides a robust and accessible tool for traceable radiometric thermometry, supporting emerging NMIs and industrial laboratories while promoting the wider adoption of primary thermodynamic temperature realization methods. Full article

Manual survey data entry remains a bottleneck in large-scale research, marketing, and public policy, where survey sheets are still widely used due to accessibility and high response rates. Despite the progress in Optical Character Recognition (OCR) and Optical Mark Recognition (OMR), existing systems treat these tasks separately and are typically tailored to clean, standardized forms, making them unreliable for real-world survey sheets with diverse markings and handwritten inputs. These limitations hinder automation and introduce significant error rates in data transcription. To address this, we propose SurveyNet, a unified deep learning framework that combines OCR and OMR capabilities to automatically digitize complex survey responses within a single model. SurveyNet processes both handwritten digits and a wide variety of mark types including ticks, circles, and crosses across multiple question formats. We also introduce SurveySet, a novel dataset comprising 135 real-world survey forms annotated across four key response types. Experimental results demonstrate that SurveyNet achieves between 50% and 97% classification accuracy across tasks, with strong performance even on small and imbalanced datasets. This framework offers a scalable solution for streamlining survey digitization workflows, reducing manual errors, and enabling timely analysis in domains ranging from consumer research to public health and education. Full article

Water surface object detection in shipborne remote sensing is challenged by unstable wave-induced backgrounds, illumination variations, extreme scale changes with tiny objects, and limited annotations. Multimodal RGB–infrared (RGB–IR) sensing leverages complementary visible and infrared cues to enhance robustness. However, most existing RGB–IR methods rely on backbones pretrained on limited-scale data, which constrain their performance for complex water surface scenes. In this work, we propose the WS-R-IR Adapter, a parameter-efficient vision foundation model (VFM)-based framework for shipborne RGB–IR object detection. Instead of full fine-tuning, it adapts frozen VFM representations via lightweight task-specific designs. the WS-R-IR Adapter includes (1) a water scene domain-aware modal adapter that progressively guides frozen backbone features with evolving semantic cues, (2) a parallel multi-scale structural perception module for fine-grained, scale-sensitive modeling, (3) an adaptive RGB–IR feature modulation fusion strategy, and (4) a resolution-aligned context semantic and structural detail fusion module. Moreover, we introduce an object-guided global-to-local registration framework to address dynamic cross-modal misalignment, and construct modality-aligned PoLaRIS-DET and ASV-RI-DET datasets that cover diverse water surface scenes. On the two datasets, the proposed method achieves mAP@0.5:0.95 scores of 74.2% and 50.2%, respectively, significantly outperforming existing methods with only 11.9M additional parameters. These results demonstrate the effectiveness of parameter-efficient VFM adaptation for multimodal water surface remote sensing. Full article

Addressing the lack of high-fidelity test cycles for fuel cell light-duty trucks, this paper proposes an automated driving cycle construction method that integrates unsupervised clustering and reinforcement learning. Firstly, based on large-sample real-world driving data, four libraries of typical driving pattern segments are extracted through dimensionality reduction via Principal Component Analysis (PCA) and K-means clustering. Subsequently, the cycle construction process is formulated as a sequential decision-making problem, and a framework based on the Proximal Policy Optimization (PPO) algorithm, incorporating an action masking mechanism, is designed. This framework innovatively injects macro-level time budget allocation as a hard constraint into the agent’s policy space via action masking, while utilizing micro-level Markov transition probabilities as a soft guide. This dual approach drives the agent to learn an optimal segment concatenation strategy, thereby simultaneously ensuring both the macro-level statistical representativeness and the micro-level driving logic coherence of the synthesized cycle. Validation results demonstrate that the cycle constructed by the proposed method achieves an average relative error of only 7.53% in key characteristic parameters, and its joint speed-acceleration distribution exhibits a similarity as high as 0.9886 with the original data, significantly outperforming traditional methods such as the clustering method, the Markov chain method, and standard driving cycles. This study provides an effective tool for generating high-fidelity driving cycles and testing energy management strategies for fuel cell commercial vehicles. Full article

The proliferation of sensor networks in critical infrastructure, healthcare monitoring, and smart city applications demands robust privacy-preserving mechanisms for data verification. Zero-knowledge succinct non-interactive arguments of knowledge (zk-SNARKs) offer a promising cryptographic primitive that enables data integrity verification without revealing sensitive sensor readings. However, the practical feasibility of deploying zk-SNARKs in resource-constrained sensor network environments remains insufficiently characterized. This paper presents a systematic benchmarking study of the Groth16 zk-SNARK protocol across eight representative circuit types spanning six orders of magnitude in computational complexity, from basic arithmetic operations (1 constraint) to ECDSA signature verification (1,510,185 constraints). Using an automated open-source benchmarking framework built on the Circom-snarkjs toolchain, we conducted 160 statistically controlled measurements (20 iterations per circuit) with cold/warm separation, collecting proof generation time, verification time, proof size, memory consumption, and witness generation overhead. Our results demonstrate that Groth16 proofs maintain a constant size of $804.7\pm 1.7$ bytes and near-constant verification time of $0.662\pm 0.032$ s regardless of circuit complexity, with coefficients of variation below 5% across all circuit types. Proof generation time exhibits sub-linear scaling ($\alpha =0.256$, $R^2=0.608$), with statistically significant differences between circuit categories confirmed by one-way ANOVA ($F=355.0$, $p<{10}^{-79}$, ${\eta }^2=0.94$). We identify three operational deployment tiers for sensor network architectures and estimate energy budgets for battery-powered devices. These findings provide actionable guidance for the design of privacy-preserving data verification systems in next-generation sensor networks. Full article

The integration of Generative Artificial Intelligence (GAI) into software design tools has transformed the early stages of mobile application development, particularly prototype creation from natural-language prompts. This study evaluates the usability and effectiveness of GAI-assisted prototyping tools for generating high-fidelity mobile application prototypes. A controlled laboratory usability study was conducted in which undergraduate Information Technology Engineering students used and evaluated four widely adopted prototyping platforms: Figma, Uizard, Visily, and Stitch. Participants employed these tools to recreate mobile interfaces corresponding to the interaction model of the Duolingo application. The System Usability Scale (SUS) was used to assess perceived usability and effectiveness from the users’ perspective. The results indicate that all evaluated tools enabled rapid prototype generation; however, significant differences emerged in usability, structural fidelity, and perceived control. Figma and Stitch achieved the highest usability scores and demonstrated greater alignment with the reference prototype (82.86 and 80.36, respectively). Visily achieved a favorable usability score (78.57), while Uizard obtained a moderate score (67.14). Although Uizard and Visily exhibited strong automation capabilities and faster initial generation, their outputs required additional manual refinement to achieve higher fidelity and customization. Participant feedback emphasized the importance of output quality, responsiveness, and foundational design knowledge in achieving satisfactory results. Overall, the findings suggest that current GAI-based prototyping tools are effective and valuable in real-world software development contexts. However, their effectiveness appears closely related to the degree of user control, responsiveness, and the ability to iteratively refine AI-generated interface components. Full article

To address the instability risk of grid-forming inverters under large power dispatch in low-inertia and low-damping power grids caused by renewable energy integration, based on the grid-forming inverter connected to an infinite bus system model, transient stability under power dispatch is conducted. The power dispatch boundaries constrained by transient stability are analyzed by the inverter’s output power-angle characteristics and the equal area criterion. To enable on-demand power dispatch for the grid-forming inverter, a power ramp scheduling strategy constrained by transient stability is proposed. Furthermore, to overcome the limitations of variable-step ramp scheduling, such as a prolonged transient duration, significant output waveform overshoot, and the need for real-time computation, an improved scheme employing virtual inertia emulation is presented, along with its parameter design methodology for the inertia emulation block. The response time and overshoot can be effectively reduced. Finally, simulations and experiments validate the effectiveness of the proposed equivalent-inertia ramp control scheme in improving system transient stability under power dispatch. Full article

Addressing high dynamics, stringent non-holonomic constraints, and limited onboard computation in cooperative online trajectory planning for multiple fixed-wing UAVs in complex 3D obstacle environments, this paper proposes a Cooperative-3D-Quick-Dubins-RRT*. First, an offline motion-primitive database is engineered to align with RRT* mechanics: an unconstrained expansion mode facilitates rapid space exploration, while a constrained rewiring mode ensures kinodynamic continuity. This architecture, synergized with four targeted acceleration strategies (dimensionality reduction, elliptical sampling, tree pruning, and pre-discretized collision checking), significantly accelerates convergence. Second, a Dubins-detour-based time-coordination mechanism is designed to map cooperative timing constraints into controllable path-length adjustments, and the feasible adjustment range is analyzed to ensure realizability. Finally, simulations and hardware-in-the-loop experiments across a variety of representative scenarios are conducted for validation. The results show that, compared with the classical Dubins-RRT*, the proposed method achieves clear advantages in planning time and path length, demonstrating its suitability for online cooperative obstacle-avoidance planning of multiple UAVs. Full article

Coastal ecosystems are increasingly threatened by climate change, especially the rising frequency of marine heatwaves (MHWs), which often co-occur with emerging nanomaterials such as graphene oxide (GO), whose ecological risks are still being evaluated. While the effects of GO have been studied in isolation, little is known about its interaction with thermal stress events. This research studied the combined effects of temperature (18 °C and 23 °C, simulating control and MHW conditions) and GO nanosheets exposure (0.01 mg/L) on two key estuarine bivalves: the clam Scrobicularia plana and the mussel Mytilus galloprovincialis. After 7 days of exposure (duration of many MHWs), energy metabolism, antioxidant defenses, oxidative damage, and neurotransmission were assessed. The results revealed that clams exhibited lower ETS and SOD activity when exposed to MHWs and lower SOD and AChE activities at MHW + GO, compared to the control treatment. Mussels relied primarily on SOD activity across treatments but showed increased susceptibility to GO nanosheets, with higher LPO levels and a significant reduction in AChE activity when exposed to GO at both temperatures. Overall, our findings suggest that S. plana shows a stronger response to the environmental alterations tested than M. galloprovincialis. Combined exposure to GO + MHW triggers species-specific biochemical responses in estuarine bivalves, highlighting how physiological traits shape the assessment of ecological risks posed by nanomaterial pollution under climate change. Full article

Flexible factories and adaptive fabrication lines offer a testbed for advanced multimodal interaction concepts that can support the inclusion of disabled workers in Industry 5.0 manufacturing systems. The study synthesizes interdisciplinary data from ergonomics, industrial automation, and EU regulatory frameworks to establish a conceptual model for human-machine interaction. Building on conceptual modeling and a structured literature analysis, the study proposes a six-step integration framework that links task demands, worker capabilities, and interaction modalities within human-in-the-loop manufacturing environments. Although no empirical case study was conducted in this phase, an exemplary application is presented for a semi-automated bike wheel manufacturing process. Detailed machine-based assembly line flows and simulated process data were utilized for illustrative purposes to depict the process and validate the proposed Capability–Task Matching Matrix. The results operationalize the human-centric vision of Industry 5.0 by providing a structured methodology for the inclusion of disabled workers within fabrication environments. The findings are organized into two primary components: the conceptual development of the Integration Approach and its practical application to a semi-automated industrial use-case. Finally, a particular focus is placed on Brain–Computer Interfaces (BCIs) as an emerging interaction channel that enables non-muscular control, attention monitoring, and neuroadaptive feedback, complementing conventional interfaces rather than replacing them. The framework is illustrated through application to the same semi-automated bicycle wheel assembly line, where BCI-supported interaction, augmented interfaces, and robotic assistance are mapped to specific production tasks and assessed in terms of feasibility and technological maturity. Drawing on the paper’s results, an explanatory 10-year roadmap outlines the feasibility and phased deployment of BCI solutions. It aligns technological advances with European regulations and a vision for a fully inclusive manufacturing enterprise. Full article

This study aims to identify and synthesize the major global trends that shaped 2025 by applying the DeflyCompass methodology to a curated corpus of strategic foresight reports. The study synthesizes insights from 23 strategic reports published by leading international organizations, including the World Economic Forum, Accenture, Euromonitor, and major technology firms. Methodologically, DeflyCompass operationalizes a structured hybrid human–AI pipeline comprising the deployment of multi-agent AI systems, automated knowledge graph construction, semantic clustering, and hybrid human–AI validation processes, reducing an initial set of 816 preliminary signals to a validated catalog of 50 high-priority trends across six PESTEL domains: Political, Economic, Social, Technological, Environmental, and Legal/Governance. Key findings indicate that artificial intelligence functions as a systemic enabling technology across all domains, climate and sustainability imperatives permeate multiple domains, geopolitical fragmentation introduces systemic tension, and trust deficits emerge as a critical vulnerability. The study contributes a replicable and scalable framework for global-level strategic foresight that operationalizes human–AI integration within a rigorous expert-driven validation process, complementing existing hybrid analytical approaches in the literature. Implications extend to decision-making in technology governance, sustainability strategy, social adaptation, and scenario planning, highlighting the necessity of integrating AI augmentation with human expertise for effective future-oriented planning. Full article

Lung nodule detection remains a critical challenge in clinical diagnostics due to the small size, weak contrast, and high background interference of nodules in CT scans. To address these issues, a novel deep neural network architecture, termed Daisy-Net, is proposed. This model incorporates dual attention mechanisms and inter-scale feature perception, consisting of two primary components: the Parallelized Patch and Spatial Context Aware (PPSCA) module and the Omni-domain Multistage Fusion (OMF) module. The PPSCA module enhances the extraction of fine-grained textures and boundary information through multi-branch patch perception and spatial attention. The OMF module employs omni-domain feature fusion and progressive stage-wise supervision to improve robustness and discrimination under complex conditions. The lung nodule detection task is formulated as a two-dimensional segmentation problem and evaluated on the LUNA16 dataset. In the post-binarization comparative evaluation, Daisy-Net achieves the best overall performance among all compared methods, with an Intersection over Union (IoU) of 81.41, a Dice coefficient of 89.75, a precision of 95.34, a sensitivity of 84.78, and a specificity of 99.9974. These findings indicate the model’s strong capability in detecting small pulmonary nodules accurately and reliably. Full article

Seasonal snow cover in mountainous regions represents a critical natural freshwater reserve for arid and semi-arid areas of Central Asia. This study evaluates the long-term (2000–2024) spatiotemporal dynamics of snow cover in the Arys River basin, located within the Western Tien Shan. The research utilizes daily satellite data from MODIS Terra and Aqua, along with data from the MODSNOW automated processing system. Terra-Aqua composite imagery was employed to minimize cloud cover effects. Satellite-derived estimates were validated against observational data from five meteorological stations of the Republican State Enterprise (RSE) “Kazhydromet”. The results indicate significant interannual variability in snow cover extent: the snow-covered area during the cold season ranged from 16.2% to 54.1%, with a mean value of 34.4%. Trend analysis revealed a weak negative trend, while Sen’s slope estimator showed an average annual reduction in snow cover area of 0.37% per year. The most pronounced decline in snow accumulation was observed in mid-elevation mountain zones. These findings suggest potential increased risks to seasonal water availability in the Arys River basin and, more broadly, across the Syr Darya basin under ongoing climate change conditions. The results provide a scientific basis for quantifying climate impacts and developing adaptation strategies for integrated water resources management in Central Asia. Full article