Search Results (2,371)

Wood is a renewable and widely used material whose mechanical performance is strongly influenced by natural defects such as knots, cracks, and resin pockets. These defects affect structural accuracy and make quality assessment an essential step in wood processing and engineering applications. Traditional visual inspection methods are time consuming and subject to individual variability, motivating the development of automated inspection systems based on computer vision. This study proposes a YOLOv8-based framework for automated wood classification and specimen selection. Two YOLOv8 variants, Nano and Medium, were trained on a publicly available wood defect dataset containing more than 20,000 images and over 43,000 annotated defects. The models were used to distinguish defect-free specimens from specimens containing visible defects, enabling objective sample selection. Only specimens classified as defect-free were retained for subsequent three-point bending tests and finite element method (FEM) simulations. Both YOLOv8 models achieved reliable detection performance, allowing consistent separation of defective and defect-free wood samples. The selected specimens exhibited stable mechanical behavior during bending tests, while FEM predictions showed good agreement with the experimental results, with errors below 3.2% in the elastic range. The proposed methodology demonstrates the potential of integrating artificial intelligence, mechanical testing, and numerical simulation into a unified workflow for wood quality assessment and structural evaluation. Full article

Surface-enhanced Raman scattering (SERS) has been widely applied to food safety screening owing to its high sensitivity and fingerprint recognition. However, SERS faces challenges in practical applications related to the precise control of the number of hot spots and the determination of how many of them actually contribute to the collected signal. In this study, silver nanoparticles (AgNPs) were used to construct a series of layer-tunable AgNP film structures by assembling one to five layers of AgNP thin films using a liquid–liquid interface self-assembly method to obtain a large number of vertically coupled nanogap structures. The relationship between the stacking number and the effective enhancement was evaluated using crystal violet as a probe molecule. The results showed that the SERS intensity increased from one to three layers and then declined, mainly originating from the competition between the vertical plasmon coupling and the finite optical penetration depth; the point-to-point relative standard deviation of the crystal violet signal at 1617 cm⁻¹, determined from 30 randomly selected positions, was lowest for the three-layer film (5.52%) and rose to 10.15% for the five-layer film. Finite element simulations and monolayer WS₂ buried-probe measurements supported this result. Using the optimized three-layer AgNP film, four fluoroquinolone antibiotics were detected. The method was also applied to antibiotic residue screening in spiked chicken extracts. The layer-optimization approach may be adapted to other nanoparticle sizes and excitation wavelengths for broader SERS applications in environmental and food safety monitoring. Full article

Visible–thermal object detection benefits from the complementary properties of RGB and thermal imagery, but repeated cross-modal fusion can increase model complexity, particularly in lightweight detectors. This paper proposes SDR-YOLO, a scale-selective detector designed to make better use of shallow spatial details without adding an extra prediction scale. A P2-guided Cross-modal Detail Enhancement module uses visible and thermal P2 features as auxiliary detail sources and injects the resulting residual into the P3 fused feature. P4 and P5 retain simple concatenation-based fusion, while a Lightweight Shared Convolutional Detection Head reduces redundant prediction parameters across scales. Experiments are conducted on DroneVehicle and M3FD. On DroneVehicle, SDR-YOLO achieves 80.4% mAP@50 and 56.7% mAP@50:95, improving both metrics by 1.0 percentage point over YOLO11s, with 14.06 M parameters and 32.51 GFLOPs; under workstation profiling conditions, it reaches 197.62 ± 1.57 FPS. On M3FD, the model obtains 82.5% mAP@50 and 55.6% mAP@50:95, corresponding to changes of 0.2 and −0.1 percentage points relative to YOLO11s. Since these differences are comparable to the run-to-run variation observed across three training seeds, they are treated as numerical trends rather than statistically established improvements. On the Jetson Orin Nano, TensorRT FP16 deployment achieves 45.78 ± 0.16 FPS, with a latency of 21.84 ± 0.08 ms and peak additional unified-memory usage of 590.4 ± 5.1 MiB, although YOLO11s-RGBT runs faster on this platform. Overall, the proposed design provides a clearer benefit in dense UAV-view scenes while maintaining comparable accuracy and slightly lower model complexity on M3FD, although its runtime efficiency remains hardware-dependent. Full article

Introduction: Severe local envenomation following extremity snakebite may mimic acute compartment syndrome and complicate surgical assessment. We aimed to describe the clinical, laboratory, and treatment-timing characteristics of patients managed with and without fasciotomy. Methods: This single-center retrospective study included patients with extremity snakebite treated between 2023 and 2025. A six-item clinical profile score was constructed retrospectively to summarize documented local findings: pain at rest, pain with passive motion, delayed capillary refill, marked swelling or tenseness, paresthesia, and motor deficit (1 point for documented presence, 0 for documented absence; range, 0–6). Clinical, laboratory, and treatment-timing characteristics were compared between patients managed with and without fasciotomy; analyses were exploratory and interpreted descriptively. Results: The overall cohort included 50 patients, six of whom underwent fasciotomy. Antivenom administration was documented in 25 patients, absent in 14, and unknown in 11. The complete-case subset comprised 35 patients, including 21 antivenom-treated patients. Within this subset, patients undergoing fasciotomy had higher clinical profile scores (median, 6 vs. 1) and longer bite-to-presentation intervals (median, 4.5 vs. 2 h; both p < 0.001). No significant between-group difference was detected in emergency department arrival-to-antivenom intervals (p = 0.129). Platelet counts were lower and activated partial thromboplastin time was longer in the fasciotomy group. Median bite-to-fasciotomy and antivenom-to-fasciotomy intervals were 8 and 2 h, respectively. Conclusions: Patients selected for fasciotomy had more pronounced documented local findings and later presentation. These exploratory associations do not establish surgical necessity or pressure-confirmed acute compartment syndrome; the retrospectively constructed clinical profile score remains descriptive, without established diagnostic validity. Full article

Electronic toll collection (ETC) gantries generate transaction records, yet existing anomaly-detection approaches often depend on manual labels or external information, limiting multiview inconsistency ranking under restricted supervision. We propose consistency-aware weakly supervised anomaly sensing for ETC (CAWS-ETC), combining monetary, temporal, structural-pattern, and contextual-semantic evidence and transferring high-confidence references to Light Gradient Boosting Machine (LightGBM). Evaluation used 14,510,847 transactions from 2525 gantries. On joint-transfer benchmarks, CAWS-ETC achieved area under the precision–recall curve (AUPRC) values of 0.9354 for rule-aligned interventions and 0.9018 for rule-orthogonal challenges, versus 0.7609 and 0.7377 for Isolation Forest. A blinded audit of 1200 unmodified transactions by two independent reviewers yielded 777 determinate labels; CAWS-ETC achieved a sampling-weighted AUPRC of 0.7946, while Isolation Forest showed higher ranking point estimates on this temporal-only subset. Post hoc attribution showed that direct rule-created and high-confidence probabilistic labels were identical after the 0.90/0.10 selection, and matched LightGBM models produced essentially identical rankings. Thus, capability beyond direct rule activation arose primarily from discriminative transfer rather than measurable gains from probabilistic aggregation or posterior-confidence weighting. Because all experiments used one day from one provincial network, multi-day, seasonal, and cross-region generalizability remain unverified. Full article

Therapeutic options in renal cell carcinoma (RCC) have expanded rapidly, including adjuvant pembrolizumab, HIF-2α-directed therapy, and multiple effective first-line combinations for metastatic clear-cell RCC (ccRCC), yet treatment selection remains largely clinicopathologic. This review evaluates biomarkers at three clinical decision points: characterization of an indeterminate renal mass; recurrence-risk assessment and adjuvant treatment selection after nephrectomy; and first-line regimen selection in metastatic ccRCC. DNA-methylation classifiers and carbonic anhydrase IX-targeted [⁸⁹Zr]Zr-girentuximab PET/CT can improve characterization of selected renal tumors, but neither replaces histopathology in routine practice. After nephrectomy, elevated plasma kidney injury molecule-1 (KIM-1) and detectable circulating tumor DNA (ctDNA) identify patients at higher risk of recurrence; however, low tumor shedding limits ctDNA sensitivity, so a negative result does not exclude molecular residual disease or justify adjuvant de-escalation; neither biomarker is validated to direct surveillance, adjuvant therapy, or treatment escalation. In metastatic ccRCC, PD-L1 expression, tumor mutational burden, and individual genomic alterations do not reliably distinguish patients who should receive dual immune-checkpoint blockade from those who should receive an immune-checkpoint inhibitor plus a VEGFR tyrosine kinase inhibitor. Transcriptomic states, myeloid composition, and spatial immune organization provide more detailed treatment-relevant biology, but no prospective comparative trial has shown that biomarker-guided regimen selection improves outcomes. Clinical implementation will require standardized assays, independent multicenter validation, and prospective trials powered to test biomarker-by-treatment interactions. Full article

In roadside surveillance imagery, shadows, vegetation, vehicles, exposed pavement, and water stains may exhibit local textures and morphological characteristics similar to those of rockfalls, causing a standalone You Only Look Once (YOLO) real-time object detector to generate frequent false-positive detections. To address this issue, this study proposes a serial cascaded detection method that integrates an improved YOLO detector with machine-learning-based secondary verification. In the YOLO branch, channel-prior convolutional attention (CPCA) and learnable weighted multiscale feature fusion are introduced to enhance target representation under complex background conditions and generate candidate bounding boxes. In the machine-learning branch, handcrafted features describing texture, color, shape, edges, morphology, and frequency-domain characteristics are extracted from the candidate regions. A verifier selected through multi-model comparison and ensemble evaluation is then employed to confirm the YOLO-generated candidates. For parameter optimization, the operating point of the standalone YOLO detector with the highest $F_1$-score is first selected as the baseline. A two-dimensional grid search is subsequently performed over 95 threshold combinations consisting of five YOLO candidate-confidence thresholds and nineteen machine-learning confidence thresholds. The optimal configuration is determined using a weighted improvement score defined according to the relative changes in precision, recall, and the $F_1$-score with respect to the baseline. The best overall performance is achieved when the YOLO and machine-learning confidence thresholds are set to 0.25 and 0.75, respectively. Compared with the standalone YOLO detector, the proposed cascaded model improves accuracy from 93.3% to 94.1%, precision from 90.1% to 92.6%, and the $F_1$-score from 93.4% to 94.0%, while recall decreases slightly from 97.0% to 95.5%. These results demonstrate that interpretable local features can effectively filter out false-positive YOLO candidates, thereby suppressing false alarms and improving overall discrimination performance at the cost of only a limited reduction in recall. The developed system has been deployed on rockfall-prone sections of highways G210 and G108, providing technical support for real-time road rockfall monitoring and early warning. Full article

We propose a lightweight cone-based Region of Interest (ROI) filtering method for camera–LiDAR fusion on distributed edge systems. Multiple Neural Processing Unit (NPU) nodes perform camera inference, and a central edge board combines their detections with LiDAR point clouds. The relative rotation is obtained from IMU quaternions under a common attitude reference and aligned sensor axes, while camera Field of View (FOV) parameters define the viewing rays. The method avoids a separate offline extrinsic-rotation estimation procedure, but it requires initial alignment, a measured translation vector, and timestamp-based synchronization. Because the rotation follows from the attitude streams rather than from a per-pair calibration session, a camera node can be added or re-aimed without a new calibration session, which lowers the setup cost of extending the system to further viewpoints. A cone membership test replaces four plane-normal dot products with a forward sign test and a squared angular cosine comparison that reuse the same axis–point dot product; on the same hardware, the mean per-camera ROI-filtering and clustering latency decreases from 6.02 to 4.46 ms, a 25.9% reduction. An adaptive threshold tightens the ROI boundary using the angular separation between neighboring detections. Across six overlap events in a parking scenario, pair-level separation succeeds in 2/6 cases (33.3%) with Pyramid and 5/6 cases (83.3%) with Cone+Adp. These preliminary results indicate improved ROI point selection for the tested configurations, rather than a general increase in intrinsic spatial separation capability. Full article

Although Transformer-based real-time object detectors have achieved promising performance in autonomous driving scenarios, their ability to detect small objects remains limited. This limitation primarily arises because small objects occupy only a few pixels in an image and contain weak edge and texture information, which can be further degraded during feature extraction and multiscale feature propagation. To address these issues, this study proposes a wavelet-based frequency-aware feature enhancement method using RT-DETR as the baseline network. First, a Wavelet Frequency Unit is introduced into the feature fusion stage of the RT-DETR neck. The unit employs the Haar wavelet transform to decompose the input features into low- and high-frequency subbands, thereby decoupling information across different frequency components. Second, residual enhancement and a frequency attention mechanism are applied to strengthen edge and texture details in the high-frequency branch. Finally, the low-frequency subband is fused with low-resolution features across scales, followed by feature reconstruction using the inverse wavelet transform. This design improves the representation of small objects in the feature space. Tests on KITTI and BDD100K verify the method. On KITTI, it obtains 95.5% mAP@0.5 and 69.7% mAP@0.5:0.95, exceeding the RT-DETR baseline by 1.8 and 1.1 percentage points. APs and ARs rise by 2.7 and 2.3 percentage points. On the selected BDD100K subset, the corresponding mAP@0.5 and mAP@0.5:0.95 values are 51.7% and 29.7%. Full article

Background/Objectives: Monitored anesthesia care is increasingly used for transfemoral transcatheter aortic valve implantation (tf-TAVI), but the optimal sedative regimen remains uncertain. We compared remimazolam with dexmedetomidine during tf-TAVI. Methods: In this single-center randomized trial, 34 patients were assigned 1:1 to remimazolam or dexmedetomidine. Primary outcomes were the number of intraoperative hypotensive episodes, defined as mean arterial pressure <65 mmHg requiring vasopressor treatment, and cumulative phenylephrine and norepinephrine doses. Secondary outcomes included hemodynamic and physiological variables, regional cerebral oxygen saturation (rSO₂), arterial blood gases, recovery time, surgeon requests for deeper sedation, and procedural outcomes. Longitudinal variables were analyzed using generalized estimating equations with Holm adjustment for time-specific comparisons. Results: No significant between-group differences were detected in intraoperative hypotensive episodes or cumulative phenylephrine and norepinephrine doses, and no significant group-by-time interactions were observed for blood pressure. Both left and right rSO₂ showed significant group-by-time interactions, with higher remimazolam values at selected time points after Holm adjustment. Arterial carbon dioxide tension was higher and arterial pH lower with remimazolam immediately before rapid ventricular pacing and at procedure completion. Recovery was faster with remimazolam (mean ± standard deviation, 13.5 ± 7.2 vs. 32.4 ± 12.5 min; p < 0.001), and surgeon requests for deeper sedation were less frequent (11.8% vs. 76.5%; p < 0.001). Conclusions: Remimazolam was associated with faster recovery and fewer surgeon requests for deeper sedation; however, the trial was not designed or powered to establish equivalence for hypotensive episodes, vasopressor requirements or hemodynamic outcomes. Full article

It remains unclear why deformation results obtained by applying different MT-InSAR methods to the same dataset, as well as those from different SAR datasets, exhibit discrepancies. Hence, this study selects Baode County, located in the Loess Plateau, as the study area to conduct a comparative analysis of multi-source SAR data and multiple MT-InSAR techniques for surface deformation monitoring. The datasets consist of concurrent Radarsat-2 and Sentinel-1 images acquired from October 2020 to June 2024. PS-InSAR, SBAS-InSAR, and IPTA-InSAR are adopted to compare their applicability across multiple dimensions, such as point coverage, deformation correlation, and mapping performance. Furthermore, based on IPTA-InSAR, the influences of spatiotemporal resolutions from different datasets on monitoring results are analyzed. The Sequential Turning Point Detection (STPD) method is incorporated to characterize the dynamic evolution of deformation and its correlation with precipitation. The results indicate that the three techniques exhibit favorable consistency and complementarity across diverse landform types. Nevertheless, SBAS-InSAR’s superiority in point density cannot be translated into an ability to represent continuous deformation fields. In contrast, IPTA-InSAR demonstrates better adaptability to complex surface conditions. Regarding data sources, Radarsat-2 achieves superior monitoring performance thanks to its high spatial resolution, yet its monitoring capacity is sensitive to variations in spatial resolution. Multi-looking not only reduces the maximum subsidence rate by approximately half but also increases elevation uncertainty by up to 24.8% and deformation-rate uncertainty by up to 42.1%. Sentinel-1, with its shorter revisit cycle, provides temporal sampling advantages that significantly enhance the ability to capture rapid subsidence signals. Through controlled-variable experiments, a dual-comparison analysis of multi-source SAR datasets and multiple MT-InSAR techniques enables the separation of discrepancies induced by algorithms from those originating in the datasets. The multifaceted experimental design provides a relatively comprehensive assessment of the influencing factors. The findings of this study can serve as references for InSAR data source combinations, technique selection, results presentation, and reliability assessment of deformation results in complex monitoring areas. Full article

Antibiotic-associated gastrointestinal dysbiosis can compromise microbial homeostasis and mucosal health, creating a need for natural feed additives that support gastrointestinal resilience. Artemisia argyi contains bioactive compounds with antimicrobial, antioxidant, and immunomodulatory properties, but its integrated effects on the gastrointestinal tract of ruminants remain insufficiently characterized. This study evaluated whether dietary A. argyi inclusion after a gentamicin-associated gastrointestinal disturbance modifies gastrointestinal morphology, serum immune-related indicators, intestinal inflammatory and barrier-related markers, and rumen and colonic bacterial communities in young Hu sheep. Forty one-month-old male Hu sheep were randomly allocated to four groups (n = 10 per group): control (Ctrl), gentamicin-challenge model (Model), low-inclusion A. argyi (ML, 1%), and high-inclusion A. argyi (MH, 3%). Following a 7-day modeling phase, during which Model, ML, and MH received gentamicin, and Ctrl did not, gentamicin administration was discontinued. Day 0 was defined as the baseline sampling point immediately after completion of the modeling phase. Blood was collected from all four groups on Day 0; immediately after this baseline collection, the 21-day dietary intervention began. During the intervention, Ctrl and Model received the basal diet, whereas ML and MH received the basal diet containing 1% and 3% A. argyi, respectively. Blood samples were subsequently collected from all sheep on intervention days 7, 14, and 21; therefore, serum analyses used n = 10 animals per group and repeated measurements from the same animals. Terminal tissue- and content-based laboratory analyses used n = 3 euthanized sheep per group. Dietary A. argyi inclusion was associated with improvements in selected gastrointestinal morphological indices, although responses differed by segment and inclusion level. Serum immunoglobulins and cytokines showed time- and treatment-associated patterns rather than a uniform response. Intestinal qPCR responses were gene- and segment-specific, and immunohistochemical effects differed according to marker and quantitative metric. For microbiota, selected taxa differed among groups, whereas the genus-level PCoA analyses presented in the manuscript did not detect significant global separation in either rumen (R = 0.0803, p = 0.292) or colonic (R = −0.0185, p = 0.528) communities. Overall, dietary A. argyi inclusion was associated with selected host and microbial responses after gentamicin exposure, but the effects were not uniformly dose-dependent and did not establish generalized gastrointestinal recovery or microbial functional restoration. Larger analytical sample sizes and direct functional measurements are required for confirmation. Full article

Background/Objectives: A symptom-based scoring system (0–9 points) for the identification of radiation pneumonitis was previously evaluated in lung cancer patients without age restrictions. A threshold of five points appeared optimal to detect pneumonitis. Since elderly patients have a higher pneumonitis risk, this threshold may not be valid for this group. The POLCAR trial evaluated performance and threshold selection in elderly patients. Methods: Diagnostic discrimination was assessed by receiver operating characteristic analysis. The areas under the curve (AUCs) and a null hypothesis that AUC equaled 0.7 were evaluated. Youden indices were used to identify candidate thresholds. In addition, the change from baseline and patient satisfaction were assessed. The dissatisfaction rate should be <20%. Results: Thirty new patients, plus 31 patients from another prospective trial with an almost identical design, qualified for analyses. The AUC for the pneumonitis score was 0.85 (95% confidence interval: 0.73–0.97). The highest Youden index (0.535) was observed for a threshold of four points. A threshold of five points led to a similar Youden index, a lower sensitivity, and higher specificity. An increase from the baseline by two points had a Youden index of 0.566 and a sensitivity of 100%, while an increase by three points had a Youden index of 0.550 and a specificity of 92.5%. Statistically superior discrimination for the change-from-baseline approach was not observed. The dissatisfaction rate was 5.4%. Conclusions: The scoring system showed good discrimination and high acceptance by patients. A threshold of four points appeared appropriate use in routine screening for the early detection of pneumonitis, whereas the change from baseline was considered useful as an exploratory tool when baseline data were available. Since only eight pneumonitis events occurred, threshold estimates require external validation. Full article

Manual sorting is still the mainstream scheme for component identification in down feather quality evaluation, which suffers from low detection efficiency and poor stability. To address these drawbacks, this paper proposes a fine-grained component detection algorithm based on YOLO12 for down feather quality classification. Five typical down feather components are selected as detection targets, including discolored feathers, down filaments, immature down, feathers and pure down. A dedicated down feather object detection dataset consisting of 1140 images is established accordingly. To improve the feature representation capacity of the model for tiny objects, faint boundary features and subtle distinctions between analogous categories, this work integrates the Convolutional Gated Linear Unit (CGLU) into the A2C2f module of YOLO12. While maintaining the original feature aggregation pathways and residual architecture, the conventional MLP feed-forward branch within ABlock is replaced with convolutional gated transformation. Experimental results demonstrate that the proposed A2C2f-CGLU model achieves precision of 96.50%, recall of 94.49%, mAP50 of 98.05% and mAP50-95 of 57.89% with the optimal weights on the validation set. Compared with the original YOLO12, the mAP50-95 metric is elevated by 3.04 percentage points, and the overall performance surpasses two comparative variants, A2C2f-DFFN and A2C2f-KAN. Visualizations of PR curves, confusion matrices and real test samples validate that the proposed method effectively enhances the recognition stability of tiny down feather targets and similar classes. This research provides a visual inspection foundation for subsequent component proportion calculation, quality grade discrimination and the development of intelligent detection systems. Full article

Rail-surface defects are often small, low-contrast, and confused with steel texture or reflections, making it difficult to improve accuracy without increasing model cost. This study proposes ESiV-YOLOv8, a compact detector that assigns complementary modifications to feature selection, box regression, and multiscale fusion in YOLOv8n. EffectiveSE recalibrates deep backbone features, SIoU provides direction-aware regression, and a VoV-GSCSP/GSConv neck reduces redundant computation. Evaluation used a self-built four-class dataset of 4020 images, a near-duplicate-aware train-validation-test split, and matched seven-seed experiments. ESiV-YOLOv8 achieved 97.7% precision, 94.6% recall, 97.2% mAP@0.5, and 68.6% mAP@0.5:0.95. Relative to YOLOv8n, mAP@0.5:0.95 increased by 5.0 percentage points, while parameters and GFLOPs decreased by 17.1% and 12.2%, respectively. On the combined natural-condition subset, ESiV-YOLOv8 achieved 59.6% mAP@0.5:0.95, 5.6 percentage points above the baseline. The annotation audit yielded 98.0% class agreement and a mean box IoU of 0.89. Model-only and end-to-end latency increased by 1.4% and 2.2%, respectively. Overall, ESiV-YOLOv8 improves detection accuracy and reduces model scale with limited latency overhead on the tested backend. Full article