Search Results (1,412)

Deep learning algorithms have significantly reduced the computational time and improved the spatial resolution of particle image velocimetry (PIV). However, the models trained on synthetic datasets might have degraded performances on practical particle images due to domain gaps. As a result, special residual patterns are often observed for the vector fields of deep learning-based estimators. To reduce the special noise step by step, we employ a denoising diffusion model (FlowDiffuser) for PIV analysis. And a data-hungry iterative denoising diffusion model is trained via a transfer learning strategy, resulting in our PIV-FlowDiffuser method. Specifically, we carry out the following: (1) pre-training a FlowDiffuser model with multiple optical flow datasets of the computer vision community, such as Sintel and KITTI; (2) fine-tuning the pre-trained model on synthetic PIV datasets. Note that the PIV images are upsampled by a factor of two to resolve small-scale turbulent flow structures. The visualized results indicate that our PIV-FlowDiffuser effectively suppresses the noise patterns. Therefore, the denoising diffusion model reduces the average endpoint error ($AEE$) by $59.4\%$ over the RAFT256-PIV baseline on the classic Cai’s dataset. In addition, PIV-FlowDiffuser exhibits enhanced generalization performance on unseen particle images due to transfer learning. Overall, this study highlights transfer-learning-based denoising diffusion models for PIV. Full article

Red bricks serve as an important material for load-bearing or enclosing structures in traditional architecture and are widely used in construction projects both domestically and internationally. Fujian red bricks, due to geographical, trade, and immigration-related factors, have spread to Taiwan and various regions in Southeast Asia, giving rise to distinctive red brick architectural complexes. To further investigate the types of damage, such as cracking and missing bricks, that occur in traditional red brick buildings due to multiple factors, including climate and human activities, this study takes Fujian red brick buildings as its research subject. It employs the YOLOv12 rapid detection method to conduct technical support research on structural assessment, type detection, and damage localization of surface damage in red brick building materials. The experimental model was conducted through the following procedures: on-site photo collection, slice marking, creation of an image training set, establishment of an iterative model training, accuracy analysis, and experimental result verification. Based on this, the causes of damage types and corresponding countermeasures were analyzed. The objective of this study is to attempt to utilize computer vision image recognition technology to provide practical, automated detection and efficient identification methods for damage types in red brick building brick structures, particularly those involving physical and mechanical structural damage that severely threaten the overall structural safety of the building. This research model will reduce the complex manual processes typically involved, thereby improving work efficiency. This enables the development of customized intervention strategies with minimal impact and enhanced timeliness for the maintenance, repair, and preservation of red brick buildings, further advancing the practical application of intelligent protection for architectural heritage. Full article

This paper offers content priorities, justifications, and pedagogical approaches for the integration of climate change education into the training of teachers, and thus into public schooling. To meet urgent imperatives presented by the polycrisis of the Anthropocene, climate change education must be inclusive, comprehensive, flexible, and regionally responsive. Climate change education can be achieved by adapting regional programs for teacher education to meet those requirements. An example is the Climate Education in Teacher Education (CETE) project in northern British Columbia, Canada. Using the Education Design-Based Research methodology, the project addresses critical questions for curricular and pedagogical development of teachers to address the following three questions: (a) what content and outcomes to prioritize, (b) why these elements matter, and (c) how to implement them effectively. Over two years, CETE engaged pre-service and in-service teachers through workshops, reflective practices, and consultations with Indigenous communities. Our tentative answers emphasize the importance of adapting curriculum and pedagogy to foster community resilience, address climate anxiety, and promote an ethical renewal toward sustainability. The iterative development of objectives as “High-Level Conjectures” provides flexibility and reflexivity in the design process in the face of rapid contextual change. CETE developed practical pedagogical tools and workshop strategies that align educational priorities with local and global needs. This study offers a replicable framework to empower educators and communities in diverse locations to navigate the complexities of the climate crisis in their quest for a more secure and sustainable future. Full article

This paper presents a novel adversarial Convolutional Neural Network (ConvNet) method for generating adversarial perturbations in 3D point clouds, enabling gradient-free robustness evaluation of object detection systems at inference time. Unlike existing iterative gradient methods, our approach embeds the ConvNet directly into the detection pipeline at the voxel feature level. The ConvNet is trained to maximize detection loss while maintaining perturbations within sensor error bounds through multi-component loss constraints (intensity, bias, and imbalance terms). Evaluation on a Sparsely Embedded Convolutional Detection (SECOND) detector with the KITTI dataset shows 8% overall mean Average Precision (mAP) degradation, while CenterPoint on NuScenes exhibits 24% weighted mAP reduction across 10 object classes. Analysis reveals an inverse relationship between object size and adversarial vulnerability: smaller objects (pedestrians: 13%, cyclists: 14%) show higher vulnerability compared to larger vehicles (cars: 0.2%) on KITTI, with similar patterns on NuScenes, where barriers (68%) and pedestrians (32%) are most affected. Despite perturbations remaining within typical sensor error margins (mean L2 norm of 0.09% for KITTI, 0.05% for NuScenes, corresponding to 0.9–2.6 cm at typical urban distances), substantial detection failures occur. The key novelty is training a ConvNet to learn effective adversarial perturbations during a one-time training phase and then using the trained network for gradient-free robustness evaluation during inference, requiring only a forward pass through the ConvNet (1.2–2.0 ms overhead) instead of iterative gradient computation, making continuous vulnerability monitoring practical for autonomous driving safety assessment. Full article

Background: Inappropriate antibiotic prescribing by dental practitioners is a significant problem in low- and middle-income settings, such as India, where there are no guidelines for dental prescribing. This study aims to report, in a step-by-step process, the co-development of a computer-based stewardship educational intervention with Indian stakeholders to reduce inappropriate antibiotic prescribing by primary care dental practitioners in India. Methods: The development process of our intervention was guided by the Medical Research Council framework for developing and evaluating complex interventions. In alignment with the framework’s core elements, a co-production research approach was employed. Engagement with local stakeholders, including primary care dental practitioners, academic dentists, and those from the Indian Dental Association, facilitated the development of a contextually appropriate intervention that was informed by a prior needs assessment (a systematic review and a policy document analysis conducted in India) and evidence from global literature. The intervention was refined through iterative feedback from stakeholders and pre-testing. Results: An educational antibiotic stewardship intervention was co-developed in collaboration with stakeholders from Chennai, a major city in southern India. The final intervention comprised three components: 1. A one-page chairside guide summarising common areas of dental antibiotic use for easy reference in clinical settings; 2. A training module based on the chairside guide; and 3. A patient information sheet to facilitate dentists’ communication with patients. The intervention components were designed to be clear, practical, and contextually relevant, with the potential to enhance clinical decision-making and promote evidence-based antibiotic prescribing practices. Conclusions: This research paper describes, in a structured manner, how an educational antibiotic stewardship intervention for dental practitioners in India was co-developed by researchers and local stakeholders. Further feasibility testing is required to address uncertainties identified at the conclusion of the development process, including those related to dentists’ perceptions of the intervention, the utility of the intervention tools, and prescription recording. Full article

The energy and resource efficient operation of continuously operated large-scale chemical plants is an important factor in the transition towards a sustainable and green process industry. In this work, the operation of the heat exchangers in the diphenylmethane diisocyanate (MDI) process is optimized to reduce fouling and thereby increase their energy efficiency. Real-time optimization (RTO) using Modifier Adaptation With Quadratic Approximation (MAWQA) is applied to cope with plant–model mismatch. It is combined with distributed estimation of the modifiers while retaining a centralized optimization to ensure rapid convergence. It reduces the data points needed for their computation and enables application to large-scale processes. The plant model that is used in the optimization is a surrogate of an available detailed flow-sheet simulator model. The algorithm is demonstrated first for a small problem and then applied to the operator training simulator (OTS) of the MDI process in several operation scenarios. Compared to previous work, the algorithm converges to the optimal operating conditions in fewer iterations. Full article

To improve the adaptability of 4WID electric vehicles under various operating conditions, this study introduces a model predictive control approach utilizing a neural network for adaptive weight parameter prediction, which integrates four-wheel steering and longitudinal driving force control. To address the difficulty in adjusting the MPC weight parameters, the neural network undergoes offline training, and the Snake Optimization method is used to iteratively optimize the controller parameters under diverse driving conditions. To further enhance vehicle stability, the real-time stability state of the vehicle is assessed using the $\beta -\dot{\beta }$ phase plane method. The influence of vehicle speed and road adhesion on the instability boundary of the phase plane is comprehensively considered to design a stability controller based on different instability degree zones. This includes an integral sliding mode controller that accounts for both vehicle tracking capability and stability, as well as a PID controller, which calculates the additional yaw moment based on the degree of instability. Finally, an optimal distribution control algorithm coordinates the longitudinal driving torque and direct yaw moment while also considering the vehicle’s understeering characteristics in determining the torque distribution for each wheel. The simulation results show that under various operating conditions, the proposed control strategy achieves smaller tracking errors and more concentrated phase trajectories compared to traditional controllers, thereby improving path tracking precision, vehicle stability, and adaptability to varying conditions. Full article

As Virtual Try-On (VTON) technology matures, 2D VTON methods based on diffusion models can now rapidly generate diverse and high-quality try-on results. However, with rising user demands for realism and immersion, many applications are shifting towards 3D VTON, which offers superior geometric and spatial consistency. Existing 3D VTON approaches commonly face challenges such as barriers to practical deployment, substantial memory requirements, and cross-view inconsistencies. To address these issues, we propose an efficient 3D VTON framework with robust multi-view consistency, whose core design is to decouple the monolithic 3D editing task into a four-stage cascade as follows: (1) We first reconstruct an initial 3D scene using 3D Gaussian Splatting, integrating the SMPL-X model at this stage as a strong geometric prior. By computing a normal-map loss and a geometric consistency loss, we ensure the structural stability of the initial human model across different views. (2) We employ the lightweight CatVTON to generate 2D try-on images, that provide visual guidance for the subsequent personalized fine-tuning tasks. (3) To accurately represent garment details from all angles, we partition the 2D dataset into three subsets—front, side, and back—and train a dedicated LoRA module for each subset on a pre-trained diffusion model. This strategy effectively mitigates the issue of blurred details that can occur when a single model attempts to learn global features. (4) An iterative optimization process then uses the generated 2D VTON images and specialized LoRA modules to edit the 3DGS scene, achieving 360-degree free-viewpoint VTON results. All our experiments were conducted on a single consumer-grade GPU with 24 GB of memory, a significant reduction from the 32 GB or more typically required by previous studies under similar data and parameter settings. Our method balances quality and memory requirement, significantly lowering the adoption barrier for 3D VTON technology. Full article

Background: The accurate classification of brain tumor subtypes from MRI scans is critical for timely diagnosis, yet the manual annotation of large datasets remains prohibitively labor-intensive. Method: We present SSPLNet (Semi-Supervised Pseudo-Labeling Network), a dual-branch deep learning framework that synergizes confidence-guided iterative pseudo-labelling with deep feature fusion to enable robust MRI-based tumor classification in data-constrained clinical environments. SSPLNet integrates a custom convolutional neural network (CNN) and a pretrained ResNet50 model, trained semi-supervised using adaptive confidence thresholds ($\tau = 0.98 \to 0.95 \to 0.90$) to iteratively refine pseudo-labels for unlabelled MRI scans. Feature representations from both branches are fused via a dense network, combining localized texture patterns with hierarchical deep features. Results: SSPLNet achieves state-of-the-art accuracy across labelled–unlabelled data splits ($90:10$ to $10:90$), outperforming supervised baselines in extreme low-label regimes (10:90) by up to 5.34% from Custom CNN and 5.58% from ResNet50. The framework reduces annotation dependence and with 40% unlabeled data maintains 98.17% diagnostic accuracy, demonstrating its viability for scalable deployment in resource-limited healthcare settings. Conclusions: Statistical Evaluation and Robustness Analysis of SSPLNet Performance confirms that SSPLNet’s lower error rate is not due to chance. The bootstrap results also confirm that SSPLNet’s reported accuracy falls well within the 95% CI of the sampling distribution. Full article

Background: Congenital talipes equinovarus (clubfoot) affects 1–2 per 1000 newborns worldwide. The Ponseti method, based on staged manipulations and casting, is the gold standard for correction. However, the biomechanical processes underlying these corrections remain poorly understood, as infants rarely undergo imaging. Computational modeling may offer a non-invasive approach to studying correction pathways and exploring novel applications, such as customized casts. Methods: We developed a proof-of-concept framework using iterative finite element analysis (iFEA) to approximate the surface-level geometric corrections targeted in Ponseti treatment. A 3D surface model of a training clubfoot foot was scanned, meshed, and deformed stepwise under applied computational loads. The model was assumed to be homogeneous and hyperelastic, and correction was quantified using Cavus, Adductus, Varus, Equinus, and Derotation angles. We also introduced a secondary adult leg 3D surface model to assess whether model simplification influences correction outcomes, by comparing a homogeneous soft tissue model with a non-homogeneous model incorporating bone structure. Results: In the training model, iFEA generated progressive deformations consistent with Ponseti correction, with mean angular deviations of ±3.2°. In the adult leg model, homogeneous and non-homogeneous versions produced comparable correction geometries, differing by <2° in outcomes. The homogeneous model required less computation, supporting its use for feasibility testing. Applied loads were computational drivers, not physiological forces. Conclusions: This feasibility study shows that iFEA can reproduce surface-level geometric changes consistent with Ponseti correction, independent of model homogeneity. While not replicating clinical biomechanics, this framework lays the groundwork for future work that incorporates clinician-applied forces, pediatric tissue properties, and patient-specific geometries, with potential applications in customized 3D-printed casts. Full article

Background: Differentiating Parkinson’s disease (PD) from essential tremor (ET) is often challenging, especially in early or atypical cases. Dopamine transporter (DAT) single-photon emission computed tomography (SPECT) with ¹²³I-Ioflupane supports diagnosis, and semi-quantitative tools such as DaTQUANT^® and BasGanV2™ provide objective measures. This study compared their diagnostic performance when integrated with supervised machine learning. Methods: We retrospectively analysed ¹²³I-Ioflupane SPECT scans from 169 patients (133 PD, 36 ET). Semi-quantitative analysis was performed using DaTQUANT^® v2.0 and BasGanV2™ v.2. Classification tree (ClT), k-nearest neighbour (k-NN), and support vector machine (SVM) models were trained and validated with stratified shuffle split (250 iterations). Diagnostic accuracy was compared between the two software packages. Results: All classifiers reliably distinguished PD from ET. DaTQUANT^® consistently achieved higher accuracy than BasGanV2™: 93.8%, 93.2%, and 94.5% for ClT, k-NN, and SVM, respectively, versus 90.9%, 91.7%, and 91.9% for BasGanV2™ (p < 0.001). Sensitivity and specificity were also consistently higher for DaTQUANT^® than BasGanV2. Class imbalance (PD > ET) was addressed using Synthetic Minority Over-sampling Technique (SMOTE). Conclusions: Machine learning analysis of ¹²³I-Ioflupane SPECT enhances differentiation between PD and ET. DaTQUANT^® outperformed BasGanV2™, suggesting greater suitability for AI-driven decision support. These findings support the integration of semi-quantitative and AI-based approaches into clinical workflows and highlight the need for harmonised methodologies in movement disorder imaging. Full article

Cloud cover can delay landslide detection in optical satellite imagery for weeks, complicating disaster response. Synthetic Aperture Radar (SAR) backscatter imagery, which is widely used for monitoring floods and avalanches, remains underutilised for landslide detection due to a limited understanding of landslide signatures in SAR data. We developed a conceptual model of landslide expression in SAR backscatter (σ°) change images through iterative investigation of over 1000 landslides across 30 diverse study areas. Using multi-temporal composites and dense time series Sentinel-1 C-band SAR data, we identified characteristic patterns linked to land cover, terrain, and landslide material. The results showed either increased or decreased backscatter depending on environmental conditions, with reduced visibility in urban or mixed vegetation areas. Detection was also hindered by geometric distortions and snow cover. The diversity of landslide expression illustrates the need to consider local variability and multi-track (ascending and descending) satellite data in designing representative training datasets for automated detection models. The conceptual model was applied to three recent disaster events using the first post-event Sentinel-1 image, successfully identifying previously unknown landslides before optical imagery became available in two cases. This study provides a theoretical foundation for interpreting landslides in SAR imagery and demonstrates its utility for rapid landslide detection. The findings support further exploration of rapid landslides in SAR backscatter data and future development of automated detection models, offering a valuable tool for disaster response. Full article

The growing adoption of modular robotic systems presents new challenges in ensuring ease of assembly, deployment, and reconfiguration, especially for end-users with varying technical expertise. This study proposes and validates an Assembly Complexity Index (ACI) framework, combining subjective workload (NASA Task Load Index) and task complexity (Task Complexity Index) into a unified metric to quantify assembly difficulty. Twelve participants performed modular manipulator assembly tasks under supervised and unsupervised conditions, enabling evaluation of learning effects and assembly complexity dynamics. Statistical analyses, including Cronbach’s alpha, correlation studies, and paired t-tests, demonstrated the framework’s internal consistency, sensitivity to user learning, and ability to capture workload-performance trade-offs. Additionally, we propose an augmented reality (AR) and virtual reality (VR) integration workflow to further mitigate assembly complexity, offering real-time guidance and adaptive assistance. The proposed framework not only supports design iteration and operator training but also provides a human-centered evaluation methodology applicable to modular robotics deployment in Industry 4.0 environments. The AR/VR-assisted workflow presented here is proposed as a conceptual extension and will be validated in future work. Full article

High-resolution remote sensing imagery offers detailed spatial and semantic insights into the Earth’s surface, yet its classification remains hindered by the limited availability of labeled data, primarily due to the substantial expense and time required for manual annotation. To overcome this challenge, we propose a hybrid semi-supervised tri-training framework that integrates traditional classification methods with a lightweight convolutional neural network. By combining heterogeneous learners with complementary strengths, the framework iteratively assigns pseudo-labels to unlabeled samples and collaboratively refines model performance in a co-training manner. Additionally, a landscape-metric-guided relearning module is introduced to incorporate spatial configuration and land cover composition, further enhancing the framework’s representational capacity and classification robustness. Experiments were conducted on four high-resolution multispectral datasets (QuickBird (QB), WorldView-2 (WV-2), GeoEye-1 (GE-1), and ZY-3) covering diverse land-cover types and spatial resolutions. The results demonstrate that the proposed method surpasses state-of-the-art baselines by 1.5–10% while generating more spatially coherent classification maps. Full article

The conventional dynamic fracture simulation by using the explicit algorithm often involves a large number of iteration computation due to the extremely small time interval. Thus, the most time-consuming process is the integration of constitutive relation. To improve the efficiency of the dynamic fracture simulation, a physics-informed neural network integration (PINNI) model is developed to calculate the integration of constitutive relation. PINNI employs a shallow multilayer perceptron with integrable activations to approximate constitutive integrand. To train PINNI, a large number of strains in a reasonable range are generated at first, and then the corresponding stresses are calculated by the mechanical constitutive relation. With the generated strains as input data and the calculated stresses as output data, the PINNI can be trained to reach a very high precision, whose relative error is about $7.8\times {10}^{-5}$%. Next, the mechanical integration of constitutive relation is replaced by the well-trained PINNI to perform the dynamic fracture simulation. It is found that the simulation results by the mechanical and PINNI approach are almost the same. This suggests that it is feasible to use PINNI to replace the rigorous mechanical integration of constitutive relation. The computational efficiency is significantly enhanced, especially for the complicated constitutive relation. It provides a new AI-combined approach to dynamic fracture simulation. Full article