Search Results (2,711)

Background and Objectives: Chronic nonspecific neck pain (NSNP) is among the most common musculoskeletal disorders. Global postural re-education (GPR) might be effective in decreasing neck pain (NP) and dysfunction and improving forward head posture (FHP) by recovering muscle chains and reducing postural alteration. Deep neck flexor activation (DNF) might also decrease NP and improve FHP by improving DNF endurance. This study aimed to compare the effects of GPR versus DNF activation on pain, dysfunction, FHP, and DNF endurance. Materials and Methods: Forty-six physiotherapy students with chronic NSNP participated in this non-randomized comparative study and were allocated into two equal groups based on their availability and preference regarding session duration. Group A underwent GPR exercises combined with active neck exercises, whereas group B received DNF activation in addition to active neck exercises. All participants were assessed pre- and post-intervention for pain intensity using a visual analog scale (VAS), neck disability using the Arabic version of the neck disability index (NDI), FHP via a photometric method with Kinovea software, and DNF endurance using pressure biofeedback. Results: A significant effect of both treatments was reported on reducing pain intensity, improving the FHP and enhancing the neck functional status with no substantial differences between both groups. A significant improvement in DNF endurance was observed in both groups, with substantially higher values between groups in favor of the DNF group. Conclusions: Both GPR and DNF activation exercises were associated with reductions in pain and improvements in neck disability among physiotherapy students with chronic NSNP and FHP. Also, both CVA and DNF endurance improved, with more improvement observed in DNF endurance in the DNF group compared with the GPR group. Full article

Intracranial hemorrhage (ICH) is a life-threatening neurological condition that requires rapid and accurate diagnosis to reduce mortality and improve patient health. Computed tomography (CT) imaging is widely used for ICH detection. However, manual interpretation can be time-consuming and prone to errors, particularly in high-volume clinical settings. Recent studies have demonstrated the effectiveness of deep learning techniques in automating medical image analysis and improving diagnostic accuracy. In this study, we propose a novel deep learning model, MGiT-X, for the automated detection of intracranial hemorrhage using head CT images. The MGiT-X model is a hybrid deep learning architecture that uses dual scale Swin Transformer modules to extract features at multiple scales, capturing local and global contextual information on CT images. It has a Gradient Fusion mechanism to enhance feature representation by combining complementary features to distinguish between hemorrhagic and healthy tissue. In addition, to further improve feature representation, the use of Jensen–Shannon divergence is used to provide better mutual alignment and consistency between the distribution of features. An adaptive weight strategy is also employed to provide refinement to the importance of features for classification. MGiT-X is evaluated on two publicly available datasets including the Head CT Hemorrhage dataset and the Brain CT Hemorrhage dataset. The proposed approach leverages advanced feature extraction and classification capabilities to distinguish between hemorrhage and healthy cases effectively. Experimental results demonstrate that the proposed MGiT-X achieves high performance across both datasets. On Dataset 1, the model attains an overall accuracy of 95.87% and a Kappa score of 91.80%, while on Dataset 2, it achieves an improved accuracy of 99.12% with a Kappa score of 98.20%. Class-wise evaluation further shows strong performance, with F1-scores exceeding 95% for both hemorrhage and healthy classes across datasets. Full article

In low-light, occluded, and cluttered environments, single-modality RGB detectors are prone to false positives and missed detections. While infrared (IR) imaging provides relatively stable target visibility under poor illumination, it lacks texture and color information and is susceptible to background thermal noise and imaging variations. To address these limitations, this paper proposes an RGB–IR object detection network, named MCF-YOLO, consisting of three core components. First, the Cross-Modal Hierarchical Fusion (CMHF) module performs stage-wise alignment and fusion on multi-scale features, jointly modeling RGB texture details and IR thermal responses to exploit the structural and semantic complementarity between the two modalities. Second, the Soft Attention Regularization based on Attention Prior (SAR-AP) module derives attention priors from IR features to impose soft constraints on cross-modal attention maps. This mechanism helps the network maintain attention on target-relevant regions, thereby suppressing attention drift caused by low-light noise and complex backgrounds. Third, the Small-Object-Sensitive Detection Head (SOS-Head) processes high-resolution features to strengthen the representation of small targets, improving detection capability in long-range and occluded scenarios. In evaluations on two RGB–IR benchmarks—M3FD and VEDAI—MCF-YOLO achieves improvements of 2.7% in mAP@0.5 and 1.1% in mAP@0.5:0.95 on M3FD, and 5.4% and 4.4%, respectively, on VEDAI. These results suggest that consistency-guided cross-modal fusion and high-resolution small-target modeling are beneficial for RGB–IR detection in low-visibility and cluttered scenes. Full article

Radiation-induced oral mucositis (RIOM) frequently causes severe pain and treatment interruptions in patients with head and neck cancer. While earlier guidelines suggested zinc supplementation, updated MASCC/ISOO guidelines downgraded it to ‘No Guideline Possible’ due to highly conflicting evidence. This study aims to resolve these inconsistencies by evaluating zinc’s prophylactic efficacy and investigating whether the route of administration determines its clinical benefit. Following PRISMA guidelines and INPLASY registration (INPLASY202620063), we searched PubMed, Embase, and the Cochrane Library through February 2026. We included randomized controlled trials (RCTs) comparing prophylactic zinc versus placebo or standard care in head and neck cancer patients receiving radiotherapy. Risk of bias was assessed using the Cochrane Risk of Bias 2 (RoB 2) tool. The primary outcome was severe (Grade 3–4) RIOM incidence. Data from five RCTs (332 patients) were pooled using a random-effects model. Overall, zinc significantly reduced severe mucositis risk (RR = 0.35, 95% CI: 0.17–0.73, p = 0.005). Crucially, an exploratory subgroup analysis revealed a striking divergence based on delivery route. Topical zinc mouthwash demonstrated encouraging protection (RR = 0.16, 95% CI: 0.05–0.49, p = 0.001) with zero heterogeneity (I² = 0%). In contrast, systemic zinc yielded borderline, inconsistent benefits (RR = 0.52, 95% CI: 0.27–1.01, p = 0.055, I² = 37%). In conclusion, the localized pool of contemporary evidence clearly demonstrates that the systemic oral ingestion of zinc supplements does not provide a reliable prophylactic benefit against severe radiation-induced oral mucositis in head and neck cancer care. Conversely, topical zinc mouthwashes exhibit an encouraging protective trend; however, the severe paucity of available randomized trials and low cumulative patient volume preclude definitive clinical verification. While these exploratory findings suggest that topical administration may provide a more consistent protective trend compared to systemic routes, they should be interpreted as hypothesis-generating rather than definitive. Future large-scale, multi-center RCTs are strictly warranted to validate these promising route-specific benefits before formal guideline integration. Full article

Unmanned Aerial Vehicle (UAV) image object detection holds significant application value in the low-altitude economy, traffic monitoring, intelligent agriculture, and disaster rescue. However, due to the top-down perspective, UAV images typically suffer from challenges such as small target scales, dense object distribution, severe occlusions, and complex backgrounds. These issues often limit the recall and localization accuracy of general-purpose detectors when they are directly applied to UAV small-object detection scenarios. To address these aforementioned challenges, this paper proposes an Adaptive Dynamic Aggregation YOLO network, termed ADA-YOLO. The novelty of ADA-YOLO lies in its highly efficient combinatorial design specifically tailored for UAV small object detection, while retaining the efficient backbone of YOLOv8, we systematically reconstruct the neck and detection head to improve accuracy. Specifically, a high-resolution P2 detection branch is incorporated to construct a P2–P5 multi-scale prediction structure. Furthermore, the lightweight DySample dynamic upsampling module is adopted to replace traditional upsampling methods, and an Adaptive Spatial Feature Fusion (ASFF) mechanism is introduced to alleviate semantic conflicts and noise interference during multi-scale feature fusion. This synergistic combination explicitly addresses multi-scale representation challenges and enhances small-object detection performance in complex scenes. Comparative experiments with the baseline YOLOv8n on the VisDrone2019 dataset demonstrate that ADA-YOLO achieves an improvement of 11.3% in mAP@0.5 and 8.2% in mAP@0.5:0.95. The improved model achieves these performance gains with a modest parameter increase and acceptable computational complexity. Finally, ablation experiments further validate the effectiveness of each individual module and their synergistic gains. Full article

Radiomics has the potential to improve risk stratification in head and neck squamous cell carcinoma (HNSCC), but clinical adoption is limited by inconsistent performance across institutions. A key source of variability is how radiomic features are generated, preprocessed, and selected prior to model development. This multicenter study evaluated how radiomics parameterization and feature selection strategies affect external model performance, feature stability, and time-to-event risk stratification. We studied pre-treatment CT scans from 752 patients with primary HNSCC from three hospitals. For each scan, 1648 radiomic features were computed using 20 different preparation methods that varied in scaling, outlier removal, and gray-level bin width. We compared five feature selection methods: Graph-FS with connected components, Boruta, Lasso, RFE-RF, and mRMR. The classification models used were Random Forest, XGBoost, CatBoost, and Logistic Regression. We measured performance using external ROC-AUC, bootstrap confidence intervals, Brier score, and RobustScore. Stability of feature selection was assessed using the Kuncheva and Jaccard indices. Cox proportional hazards models confirmed time-to-event results, and consensus SHAP analysis helped explain the models. Radiomics parameterization influenced model performance, and no single configuration was optimal across all analyses. Radiomics-only models outperformed clinical-only models, while clinical–radiomics models achieved the highest overall performance. mRMR and Lasso produced the highest average external AUCs, while Graph-FS showed the greatest stability. The best classification model achieved an external AUC of 0.817. In Cox validation, the best clinical–radiomics configuration achieved an external C-index of 0.662 and separated high- and low-risk patients in the external cohort. Full article

Accurate prediction of the load–settlement response of axially loaded piles remains challenging because the pile–soil interface undergoes progressive elastoplastic shear deformation accompanied by stress-dependent volumetric changes. Conventional one-dimensional load-transfer models are computationally efficient but usually rely on empirical or hyperbolic fitting functions, making it difficult to explicitly describe the coupled evolution of interface shear hardening, volumetric hardening, and radial effective stress. Although three-dimensional elastoplastic models provide a more rigorous mechanical representation, their high computational cost limits routine engineering application. To address this gap, this study develops a double-hardening elastoplastic load-transfer model for axially loaded piles based on a physically interpretable pile–soil interface constitutive formulation. In the proposed model, the Hardening Soil model is used to characterize interface shear hardening, while the Modified Cam-clay model is introduced to describe volumetric hardening. These two mechanisms are coupled through a stress–dilatancy relationship. According to the loading direction and the position of the current stress point relative to the shear and volumetric yield surfaces, the p′–q stress plane is divided into elastic, shear-hardening, volumetric-hardening, and coupled double-hardening regions. The corresponding incremental constitutive equations are derived and embedded into a conventional load-transfer framework. The model is validated using interface direct shear tests and field-scale static pile load tests. The predicted shear stress–displacement curves and pile-head load–settlement responses agree well with the measured data. Quantitative evaluation shows that the MAPE values are lower than 5%, the maximum relative errors are below 7.6%, and the R² values exceed 0.96 for all validation cases. Full article

Preserving cultural heritage sites requires an interoperable digital framework capable of integrating heterogeneous spatial data and supporting immersive interaction for inspection and management. This study investigates the integration of multiple heritage data representations—including IFC-based Heritage Building Information Modeling (HBIM), terrestrial and UAV LiDAR point clouds, and 3D Gaussian Splatting reconstructions—into a unified digital management environment for the East Hall (Aula Timur) heritage site within the Bandung Institute of Technology (ITB) campus. A semantic–spatial interoperability workflow is proposed to harmonize BIM, point cloud, and landscape-scale data within a common georeferenced context, supported by a CityGML-based base map of the surrounding site. An immersive virtual environment was implemented using a head-mounted display to enable walkthrough-based inspection and damage annotation. All datasets were georeferenced within a unified coordinate system, allowing spatial registration between digital objects and the physical heritage site. The results demonstrate that multi-source heritage datasets can be integrated with high geometric accuracy, achieving TLS registration errors of approximately 2 mm and georeferencing residuals within 11.1 cm (horizontal) and 0.95 cm (vertical), while preserving semantic information and ensuring spatial coherence across HBIM, GIS, and immersive environments. The system is implemented in VR, with an architecture designed to support future MR-based on-site annotation and visualization. The proposed framework establishes a foundation for future heritage digital twin deployments and supports informed conservation decisions. Full article

With the large-scale development of renewable energy such as wind, solar and ocean energy, the demand for energy storage is more urgent. Pumped hydro energy storage (PHES) is one of the fundamental solutions to the problem of intermittent supply of renewable energy. The large-capacity/low-head pumped hydro energy storage (LL-PHES) system with the use of tubular pump turbine is a beneficial extension of traditional PHES systems owing to large flow rate and cheaper civil structures. However, the continuous competition between the “static water pressure difference caused by gravity” and the “pressure increase caused by accelerated impeller rotation” leads to prominent instability in the start-up process of the LL-PHES system under pump conditions. An explicit coupling algorithm is proposed for analyzing the transient characteristics in the start-up process of the LL-PHES system under pump conditions. This algorithm is based on the idea of dimensional transformation, and performs 3D flow calculations and 2D rigid body dynamics equation solution in the pump domain and the flap gate domain, respectively. This algorithm avoids the problems of high computational cost and poor convergence that exist in existing fully three-dimensional coupling algorithms and ensures the efficiency of transient hydraulic characteristic calculation. A comprehensive analysis of the transient characteristics of the LL-PHES system during pump start-up process is conducted using the proposed new algorithm. The entire process of the increase in rotational speed, valve opening, flow rate, and the continuous evolution of blade surface pressure during the start-up process is quantitatively described. The amplitude and spectral characteristics of the alternating pressure on multiple blades are clarified. The evolution law of blade load during the stage of severe pressure fluctuations during the start-up process is explained. The load distribution characteristics of “high in the leading and trailing edge areas and low in the middle” in the blade stream direction is presented. The research results have a direct guiding role in improving the hydraulic design and enhancing the operational stability of LL-PHES systems. Full article

To address the challenges of detecting sugar orange fruits in complex natural orchard environments—where fruits are frequently occluded by leaves and branches and may be mutually occluded due to dense growth, leading to missed detections, false positives, and low detection confidence—we propose an improved algorithm based on YOLOv8n, named YOLO-FSEP. A Spatial-Channel Synergistic Attention (SCSA) module is introduced into the main network to enhance feature extraction capabilities; the IoU loss function is replaced with Focal_SIOU to improve the detection accuracy for difficult samples; and an SE attention mechanism is embedded in the detection head, with the addition of a P6 high-resolution detection layer to optimize multi-scale object performance. Experimental results on a self-built sugar orange dataset show that, compared to the baseline YOLOv8n, the improved model achieves a 0.9% increase in accuracy, a 1.3% increase in recall, and a 3.2% increase in mAP50-95, while maintaining an inference speed of 62.6 FPS. To evaluate the model under dynamic conditions, we performed a 200-frame continuous test of the 3D localization pipeline on a laptop with a RealSense D435i camera. The average YOLO inference time was 49.90 ms, post-processing (depth extraction and 3D coordinate conversion) took 0.24 ms, and the total processing time was 50.15 ms. Given that the typical response time for a robotic arm’s single positioning operation is 100–200 ms, this real-time performance meets the dynamic localization requirements of sugar orange harvesting. Full article

Rice production in flooded paddy systems must increasingly balance grain productivity with greenhouse gas (GHG) efficiency. This study evaluated two GroMore^® crop-protection program variants under two nitrogen input levels in a temperate Korean paddy field to determine whether these treatments could improve yield-scaled climate performance without compromising grain yield. Heading date was identical across all treatments, indicating that treatment effects were not attributable to phenological shifts. Grain yield ranged from 6.87 Mg ha⁻¹ in the conventional treatment to 9.88 Mg ha⁻¹ in GroMore-Duo N90. GroMore-Star N90 maintained high yield (9.05 Mg ha⁻¹) with the lowest greenhouse gas intensity (GHGI; 0.69 kg CO₂-eq kg⁻¹ grain) and reduced cumulative methane emission by 10.6% relative to the conventional treatment. Logistic analysis showed that the GroMore treatments reached the methane-accumulation inflection point earlier than the control and conventional treatments. GroMore-Duo N90 and GroMore-Star N90 reached this point at approximately 69 days after transplanting, whereas the control and conventional treatments reached it at 86 and 89 DAT, respectively. Overall, the GroMore programs were associated with differences in yield components and yield-scaled climate performance under flooded paddy conditions without changing crop phenology. Full article

Background: Pressure injury (PI) prevention relies heavily on the application of the Braden Scale, yet its predictive performance is limited mainly due to subjective measurements and fixed cut-off points, yielding potential errors in terms of false-positive alarm rates and workforce misuse. Machine learning (ML) has emerged as a promising approach to improve discrimination, but fair comparisons with traditional tools remain scarce in clinical settings. Methods: Using data from 446 hospitalized patients in a tertiary hospital in Chile, we compared five classic ML models for classification against the Braden Scale. ML models were trained exclusively on routinely collected clinical and nursing variables, excluding Braden inputs. A matched operating-point framework was applied, aligning ML decision thresholds with Braden cutoffs based on equivalent recall or specificity. Results: The XGB model showed the highest overall discrimination performance (AUC = 0.835). When matched to Braden recall, XGB achieved about 17% gains in specificity, substantially reducing false positives. When matched on specificity, recall improvements ranged from 13% to 25%. These gains were consistent across clinically relevant thresholds considered during the comparison. Conclusions: ML models, particularly XGB, outperform the Braden Scale under equivalent clinical operating conditions. Rather than replacing Braden, ML has emerged as a promising approach that preserves patient safety while improving precision and resource allocation. Full article

Accurate traffic sign detection is important for the safety of autonomous driving systems. However, fully supervised methods require a large amount of manual annotation, which is cost-prohibitive and time-consuming. Semi-supervised methods employ a small amount of labeled data and a large amount of unlabeled data to train the models, hence largely reducing the annotation costs. However, these methods have the following challenges: (1) with an imbalanced long-tail class distribution of traffic signs, they tend to achieve poor performance on tail classes; (2) they often fail to detect small traffic signs. To solve these issues, we propose a Semi-Supervised Traffic Sign Detection method with Dynamic Pseudo-Label Selection and Gated Feature Fusion-based Proposal Refinement. Firstly, we design a Class Distribution-based Dynamic Pseudo-Label Selection module (CD-DPLS) to select pseudo-labels for different classes based on the class distribution information, which reduces the tendency to select more pseudo-labels from head classes instead of tail classes, thereby improving the tail class detection performance. Secondly, we employ a Gated Feature Fusion-based Proposal Refinement strategy (GFF-PR) to refine detection proposals by fusing different-scale features with a gating mechanism, which facilitates the detection of small traffic signs. In addition, we use an Adaptive-Weight Focal Loss (AWFL), with which the weight of each pseudo-label is determined by the ratio between its classification confidence and the corresponding class-specific classification-confidence threshold. Experiments on traffic sign datasets demonstrate that the proposed method outperforms state-of-the-art semi-supervised approaches, with mAP${}_{50}$ scores of 10.8% and 34.9% using only 1% and 10% labeled data, respectively. Full article

To address electric bicycle detection in confined indoor environments affected by occlusion and image degradation, this study proposes DCM-YOLO, a robustness-oriented detection framework designed to improve detection accuracy under complex indoor visual conditions. First, the Dual-branch Adaptive Fusion (DAF) module combines lightweight feature generation with adaptive modulation to preserve local structures and channel diversity when target appearances are incomplete. Second, the Spatial–Channel Synergistic Attention (SCSA) mechanism sequentially refines informative regions and semantic channels, allowing the detector to suppress background interference more effectively. Third, the Multi-Scale Group-Aware Head (MSGA-Head) introduces multi-branch receptive-field modeling and grouped refinement to improve scale-sensitive classification and localization. These components form a coordinated backbone–attention–head design, reducing detection ambiguity caused by partial visibility and degraded image quality, including underexposure, overexposure, low contrast, and blur. Experimental results on a public dataset collected from representative indoor environments indicate that DCM-YOLO achieves 87.6% Precision, 83.7% Recall, 86.2% mAP50, and 65.1% mAP50-95, exceeding the baseline model by 2.5, 2.9, 2.8, and 1.7 percentage points, respectively. Additional evaluations on public benchmark datasets further verify the effectiveness and robustness of DCM-YOLO. Full article

Unmanned aerial vehicle (UAV) object detection plays an essential role in modern visual perception, but it remains challenging because UAV imagery typically contains extremely small, densely distributed objects embedded in complex backgrounds. Conventional detectors, including the recent YOLOv12, are prone to losing critical spatial details during downsampling and often exhibit task misalignment between classification and localization, particularly under severe scale variations. To address these problems, this study proposes SPTD-YOLO, a small-object-aware pyramidal and task-aligned dynamic detector. Specifically, a Small Object Enhanced Pyramid (SOEP) is developed by incorporating SPDConv and CSPOmniKernel to preserve and refine shallow, fine-grained features. In addition, a high-resolution P₂ detection layer is introduced to increase spatial grid density and strengthen the structural representation of tiny objects. Furthermore, a Task-Aligned Dynamic Detection Head (TADDH) is designed to decouple and coordinate classification and regression through dynamic convolution and a synergistic dual-gating mechanism. Experiments on VisDrone2019 show that SPTD-YOLO improves mAP@0.5 by 8.37% and mAP@0.5:0.95 by 5.11% over YOLOv12 while maintaining practical efficiency for UAV edge deployment. Full article