Search Results (1,416)

The reliable detection of spot-weld defects in automotive structural components is challenged by large variations in defect scale, severe background interference and limited detection accuracy. Here, we propose YOLOv8-RFA-iEMA-RH, an improved YOLOv8n-based detector for spot-weld defects. A receptive field attention convolution module (RFACM) is introduced into the backbone to strengthen local texture representation through multi-receptive-field feature modelling. An improved Efficient Multi-scale Attention module (iEMA) is incorporated into the neck to enhance global context modelling and suppress background interference. In addition, a structurally re-parameterized RepHead is integrated into the detection head to enhance feature learning during training while maintaining a simplified single-branch structure for inference. On the self-built spot-weld defect dataset, the proposed model achieves 92.7% Recall, 91.2% F1, 97.9% mAP@0.5 and 71.9% mAP@0.5:0.95, improving on the YOLOv8n baseline by 2.3, 1.3, 2.5 and 3.1 percentage points, respectively. Cross-dataset evaluation on NEU-DET further yields 78.8% mAP@0.5 and 48.7% mAP@0.5:0.95. These results demonstrate improved detection accuracy and cross-dataset adaptability; actual inference speed and memory consumption require further validation on specific deployment hardware. Full article

Objective: Cognitive behaviour therapy (CBT) for binge eating disorder (BED) is fairly effective, yet relapse remains problematic. Treatment outcomes may be improved if patients gain more insight into symptom patterns. In this qualitative study embedded in BED treatment, we evaluated user experiences with an Ecological Momentary Assessment (EMA) smartphone application to self-monitor affect and binge eating episodes in daily life. Methods: Participants were 20 adults who received group-CBT for BED at a mental health institute in the Netherlands. Via an EMA smartphone app, the participants filled out 5 micro-questionnaires daily for 6 weeks. An overview of mood fluctuations and binge eating episodes was graphically displayed in the app and discussed with the therapist. Semi-structured interviews were conducted with 16 participants and 5 practitioners to evaluate feasibility and usefulness. Results: Qualitative analyses of the interviews showed that the app was perceived as user-friendly, yet invasive due to many registrations. This was reflected in low response rates (mean: 31.1%), with only 9 participants reaching a response rate above 30% (>65 of 210 EMA micro-questionnaires completed). Some participants thought the daily registrations were insightful, but some also perceived the registrations as confronting and shameful, suggesting potential iatrogenic effects. Conclusions: This study offers a real-world example of using EMA in treatment and provides meaningful insights for developers of behaviour change-focused EMA tools. The experiences of the participants and practitioners were mixed, yet several indicated improved reflection and awareness of (fluctuations in) emotions. Given the cautiously positive feedback from several participants and therapists, we recommend a carefully designed evaluation, including a shorter assessment period, a control group and an assessment of emotional awareness. Full article

Human tracking plays a crucial role in video surveillance systems. However, tracking humans in surveillance videos remains challenging because targets are often captured at long distances, occupy only a small number of pixels, and exhibit substantial scale variations. These challenges require not only accurate detection of small, low-texture targets but also fast and robust data association for multi-object tracking. We propose an enhanced human-tracking method that integrates improved object detection with complementary appearance and motion cues. Specifically, we improve YOLOv12 by incorporating large-kernel deformable attention, dynamic convolution, and phantom convolution. These components enhance the detector’s ability to perceive small-target features under complex backgrounds and occlusion while reducing its computational cost. The OSNet appearance embeddings incorporated into the EMA update framework construct a robust trajectory-level temporal appearance representation, which improves the discrimination between different individuals in the tracking stage. Extensive experiments demonstrate that the proposed method achieves more accurate identity association and more stable target trajectories than state-of-the-art tracking methods, including StrongSORT and ByteTrack. Full article

The manual identification of non-metallic pipelines in ground-penetrating radar (GPR) images is inefficient and heavily experience-dependent. Existing deep-learning methods suffer from performance degradation caused by image noise, signal attenuation, and false anomalies. To address these challenges, this paper proposes YOLOv8-WT, which introduces a novel WTConv-ATT module combining wavelet transform and multi-dimensional dynamic attention. This module performs multi-level wavelet decomposition to extract frequency-domain features and enhance global and low-frequency information perception; meanwhile spatial-channel-pixel attention adaptively generates feature fusion weights to suppress noise interference. Several existing well-established modules (Wise-IoU, C2f-FSDA, CBAM, EMA) are also integrated to further boost detection performance. Experimental results on merged public GPR datasets show that compared with the YOLOv8s baseline, the proposed model achieves increases of 1.27, 4.59, and 2.55 percentage points in Precision, Recall, and mAP50, reaching 92.98%, 91.83%, and 96.76%, respectively. YOLOv8-WT obtains promising detection performance for non-metallic pipelines under mixed-dataset conditions. Further validation is still required for unknown real-world GPR scenarios. Full article

Cell and gene therapies (CGTs) have progressed from proof of concept to an established commercial pipeline, yet global translation remains constrained by fragmented regulatory frameworks; heterogeneous Chemistry, Manufacturing, and Controls (CMC) requirements; and divergent approval pathways. This narrative review compares CGT quality, CMC, and approval-pathway regulation across the US Food and Drug Administration (FDA), European Medicines Agency (EMA), and Japan’s Pharmaceuticals and Medical Devices Agency (PMDA), together with five emerging-market agencies: Brazil, Russia, India, China, and Mexico (BRIC-M), current to June 2026. Four convergence gaps recur across all eight jurisdictions: unstandardized potency assay validation, inconsistent post-change comparability expectations, uneven ICH guideline implementation, and divergent evidentiary thresholds for small-population trials. Convergence readiness varies sharply within the emerging-market group, from ICH Regulatory Membership and internationally benchmarked CMC guidance in China and Brazil to reference-country reliance in Mexico and observer status in Russia and India. On this basis, we propose the Global CGT Regulatory Convergence Framework (GCRC-F), a reference architecture of four independently adoptable pillars: (i) Unified CMC Standards, (ii) a Data Harmonization Layer for long-term follow-up and real-world evidence, (iii) an Adaptive Approval Layer linking accelerated designations across agencies, and (iv) a Manufacturing Standardization Layer that is built on existing regulatory precedents rather than novel instruments, with participation tiered by demonstrated regulatory-science maturity. The framework is offered as a structured proposal for discussion; it has not been evaluated by regulators or industry stakeholders, and its feasibility remains to be tested through the consultation and case-study methods identified. Full article

Modern cultural and educational buildings are important material carriers of regional modernization, educational transformation, and Sino-Western cultural exchange. In Hunan, these buildings exhibit complex stylistic features shaped by the interaction of Western architectural languages, Chinese revival forms, modern decorative expressions, and early modern architectural tendencies. This study aims to explore a subject-focused deep learning framework for auxiliary-style recognition of modern educational and cultural buildings in Hunan and to investigate the feasibility of transferring stylistic representations learned from non-Hunan samples to the Hunan target domain under cross-regional conditions. A six-class style classification system with operational morphological criteria was established, and a geographically isolated cross-regional target-domain evaluation framework was adopted. Modern public, educational, and cultural building samples from outside Hunan Province were used for training and validation, while Hunan samples were retained as a fixed target-domain test set. Several representative backbone networks were used as references for model selection, and Swin Transformer was adopted as the unified backbone. The effects of L-Softmax, multi-scale feature fusion, global channel–spatial attention, PFP/PA, GBVS/AGL subject guidance, and Grad-CAM-based background constraints were compared under the unified cross-regional target-domain evaluation protocol. EMA was used only as an auxiliary training stabilization strategy. Model performance was evaluated using image-level accuracy, building-level accuracy based on multi-view majority voting, balanced accuracy, macro-F1, bootstrap confidence intervals, confusion matrices, and representative boundary cases. On the fixed Hunan target-domain test set containing 186 images from 37 building instances, the highest image-level accuracy reached 58.60%, while the highest building-level accuracy reached 64.86%. Considering the strong class imbalance and limited number of building instances in several categories, these results were further interpreted together with balanced metrics and bootstrap confidence intervals rather than accuracy alone. The A1–A8 ablation experiments indicated that the A7 variant incorporating GBVS/AGL achieved a relatively balanced performance between image-level and building-level evaluations under the current target-domain condition. The proposed framework provides an exploratory auxiliary approach for architectural heritage surveys, digital documentation, and style-boundary analysis, rather than a fully generalized architectural style recognition system, while offering methodological reference for future component-level quantitative research on Si-no-Western architectural integration. Full article

Bridge surface cracks are important early indicators of structural performance degradation. However, affected by complex environmental interferences and irregular morphologies, existing models still fall short in micro-crack recognition, accurate bounding-box localization, and lightweight. To address these challenges, this study proposes a multi-module collaborative lightweight model (MCL-YOLO) based on YOLOv12. Specifically, the existing ADown module from YOLOv9 is incorporated into the YOLOv12 architecture to reduce computational complexity while preserving critical information during feature downsampling. To enhance the representation of slender, curved, and branched crack patterns, a C3k2-RFAConv module is designed by integrating a receptive-field attention mechanism. Furthermore, an iEMA module is embedded before the high-resolution detection branch to strengthen the semantic response to weak-texture cracks. A bridge crack dataset containing 4029 images was constructed to evaluate the proposed model. Experimental results show that MCL-YOLO achieves Precision, Recall, mAP@50, and mAP@50:95 values of 0.891, 0.757, 0.844, and 0.675, with 5.5 GFLOPs, 2.240 M parameters, and a model-file size of 4.689 M. Compared with the YOLOv12n baseline, MCL-YOLO improves the four detection metrics by 2.30%, 4.56%, 4.07%, and 3.21%, while reducing GFLOPs and parameter count (Params) by 12.70% and 12.77%, respectively. Ablation experiments, model version comparisons, attention mechanism comparisons, and qualitative detection results collectively verify the effectiveness of the integrated architectural modifications. Full article

Mesenchymal neoplasms driven by protein kinases represent an increasing group with a broad clinicopathologic and genetic spectrum. Recently, tumors harboring a GAB1::ABL1 fusion have been reported, resulting in constitutive activation of the non-receptor tyrosine kinase ABL1. We describe six cases (one previously reported) investigated by fusion gene analysis and DNA-methylation profiling. Tumors were from three males and three females aged 7–71 years and arose in the neck, axilla, lower back, thigh, and digits. Lesions were excised. Available follow-up was uneventful. Neoplasms were circumscribed but unencapsulated, with infiltration of the surrounding tissue, and characterized by haphazardly arranged monomorphous spindle cells. There was a fibromyxoid stroma and staghorn-like vessels were present. Immunohistochemically, expression of CD34 (3/6), S100 (1/6), EMA (2/6), and GLUT1 (3/3) was observed. All cases harbored a GAB1::ABL1 fusion. RNA expression profile (n = 2) showed high-confidence similarity to dermatofibrosarcoma protuberans (DFSP). DNA-methylation profiling demonstrated that all cases clustered together in close proximity to DFSP. Application of the latest Heidelberg methylation sarcoma classifier did not confidentially classify these neoplasms. However, four showed low-confidence matches to NTRK-rearranged spindle cell neoplasms. GAB1::ABL1 spindle cell neoplasms represent a distinct member of the family of kinase-driven mesenchymal tumors with an indolent clinical course, while the activating ABL1 fusion raises the possibility of targeted therapy in selected cases. Full article

Background/Objectives: Vaccination represents one of the most significant achievements of modern medicine and public health. However, the scope, mandatory status, and vaccination coverage vary considerably across European countries. Methods: This narrative review compares selected elements of vaccination programmes in Poland, purposively selected EU/EEA countries, and the United Kingdom. Official data from the WHO, UNICEF, ECDC, EMA, and national sources were used to delineate vaccination policies, reimbursement models, delivery arrangements, coverage rates, and educational approaches. Due to temporal and methodological heterogeneity, the findings were interpreted descriptively. Results: Poland, together with Latvia, has the largest number of vaccinations classified as mandatory among the EU/EEA countries included in this comparison. Vaccination is mandatory in only nine EU/EEA countries; however, several countries without such policies also report high vaccination coverage in settings characterized by extensive public education and accessible vaccination services. Adult vaccination policies, recommendations, and reimbursement frameworks for influenza, pneumococcal, and RSV vaccines vary significantly depending on the country, target population, age criteria, and scope of funding. Conclusions: This comparison indicates a potential gap between the structured delivery of childhood vaccinations and the predominantly recommendation-based adult vaccination approach in Poland. Strategies utilized in selected European countries suggest that life-course vaccination continuity can be enhanced through accessible delivery systems, adequate reimbursement, systematic assessment of vaccination status, active engagement of healthcare professionals, sustained public communication, and trust-building. Mandatory status alone should not be regarded as sufficient to ensure high vaccination coverage. Full article

Acoustic-to-articulatory inversion (AAI) predicts articulatory movements from acoustic signals; however, current methods often overlook external, visible articulatory features and frequency domain information. Limited paired acoustic–articulatory data remain a practical constraint on robust AAI modeling and evaluation. This paper proposes a novel AAI framework integrating external visible articulatory features and a channel attention mechanism for feature fusion. We first construct a Mandarin EMA dataset for language learning, then explore the impact of visible features (e.g., lip movements) on predicting internal articulatory trajectories. We additionally investigate short-time Fourier magnitude representations computed from EMA-measured lip–jaw trajectories as auxiliary kinematic features. SENet- and ECA-based group-attention variants are evaluated as alternatives for reweighting input groups before concatenation. Experiments on SAIT-EMA and MOCHA show that visible articulatory features and frequency-domain information improve prediction accuracy, with channel attention fusion providing further gains in selected configurations. These findings demonstrate the value of attention-based multimodal data fusion for intelligent audio and articulatory information processing in pronunciation-learning contexts. Full article

Accurate perception of eggplant fruits and stems remains challenging for greenhouse harvesting robots because illumination changes, foliage occlusion, fruit overlap, and background branches can degrade target visibility, particularly for small and curved stems. To improve joint fruit-and-stem detection under these conditions, this study develops an enhanced YOLOv8n model using a greenhouse dataset collected across different illumination levels, viewpoints, occlusion degrees, and fruit-overlap situations. The baseline network was modified in three aspects. Selected conventional convolutions in the backbone and neck were replaced by Omni-Dimensional Dynamic Convolution (ODConv) to improve feature adaptation to targets with different scales and shapes. Efficient Multi-Scale Attention (EMA) was placed after the SPPF module to emphasize informative responses from fruit and stem regions while reducing background interference. In addition, C2f_MSBlock was incorporated into the neck to strengthen multi-scale feature representation and fusion. The resulting model achieved 96.4% precision, 97.2% recall, 99.0% mAP@0.5, and 86.0% mAP@0.5:0.95, with 3.74 M parameters, 6.5 GFLOPs, and a model size of 7.9 MB. Relative to the original YOLOv8n, these four detection metrics increased by 2.2, 0.3, 0.5, and 2.9 percentage points, respectively, while GFLOPs decreased by 16.7%. These results indicate that the modified model improves detection robustness in complex greenhouse scenes while maintaining moderate computational requirements, providing a feasible visual perception approach for eggplant fruit recognition and stem localization in robotic harvesting. Full article

This study applies a Craig–Bampton (CB) substructure reduction procedure to the prediction of natural frequency changes upon rotor replacement in a shaft generator shafting system and quantifies its accuracy and computational cost for that configuration. Because the shafting conditions are determined by the customer, performing full finite element analysis or experimental modal analysis (EMA) for every design change is impractical. The shafting system is divided into shaft and rotor substructures, and CB reduced-order models are constructed independently for each substructure. A three-stage verification framework—FE analysis versus EMA, the CB reduced-order model versus FE analysis, and the CB reduced-order model versus EMA—is employed to separate FE model error from CB reduction error. The CB pipeline reproduced the bending modes of the assembly with a maximum error of 0.26% against the parent finite element model, with a subspace MAC of 1.0000 for every mode group below 720 Hz, while reducing the model from 192,678 to 5379 degrees of freedom. With 20% of the interface degrees of freedom retained, the first three bending modes are predicted within 0.60%, and the reduced model comprises 1173 degrees of freedom, a reduction of 99.39%. The first bending mode error varies monotonically with the retention level, and the errors of all three bending modes remain bounded below 0.60% down to 20% retention. For the annular interface examined, the error-retention relation, therefore, provides a quantitative basis for selecting a retention level against a stated error tolerance, but its extension to other interface topologies, mesh densities, and mode ranges remains to be established. Full article

Valerian (Valeriana officinalis L.), passionflower (Passiflora incarnata L.), and ginkgo (Ginkgo biloba L.) are among the most widely used medicinal plants in European phytotherapy, with well-documented traditional use for anxiety, insomnia, cognitive decline, attention-deficit/hyperactivity disorder (ADHD), and Parkinson’s disease. This narrative review critically analyses available clinical, pharmacological, toxicological, and regulatory data on these three species in the context of central nervous system (CNS) disorders. A comprehensive literature search was conducted in PubMed, Scopus, and the Cochrane Library; regulatory documents from the European Medicines Agency (EMA), the European Scientific Cooperative on Phytotherapy (ESCOP), and the World Health Organization (WHO) were also included. Valerian showed the most consistent clinical evidence for an improvement in sleep quality and reduction in anxiety. Passionflower demonstrated anxiolytic and mild sedative effects in several controlled trials. Ginkgo showed clinically relevant benefits in mild cognitive impairment, dementia, and vertigo. All three plants exhibited acceptable safety profiles at the recommended doses; however, significant drug interactions were identified, notably ginkgo’s inhibition of CYP2C19 and antiplatelet effects, and valerian’s potentiation of CNS depressants. Regulatory frameworks across EU member states remain inconsistent. Further high-quality randomized controlled trials with standardized extract characterization are needed. Full article

Heavy-duty manipulators are generally driven by hydraulic systems. The control valves in these systems cause substantial throttling losses, resulting in low overall system energy efficiency. To address this problem, this study proposes an electro-mechanical direct drive system (EMDDS) based on an electro-mechanical actuator (EMA) for energy-efficient actuation of heavy-duty manipulators. A supercapacitor energy-management strategy combining current feedforward with voltage feedback is also developed to recover and reuse the gravitational potential energy of the manipulator efficiently. System parameters were selected for the boom of a 6 t excavator, after which a multidisciplinary co-simulation model was established and an experimental prototype was built for validation. The simulation and experimental results show that the proposed system incurs no throttling loss during operation and achieves high drive efficiency. The system recovers and reuses gravitational potential energy with an efficiency of up to 46.4%. Compared with the load-sensing (LS) system, the EMDDS reduces energy consumption over one boom raising and lowering cycle from 42.25 kJ to 16.86 kJ, a reduction of 60.1%. The analysis and experiments provide a basis for developing energy-efficient electric drives and potential-energy recovery technologies for heavy-duty manipulators. Full article

Background: Over the last decade, numerous studies have investigated the administration of monoclonal anti-amyloid antibodies (AAAs) as a therapeutic approach in Alzheimer’s disease (AD). The purpose of this umbrella review is to summarize current knowledge concerning the efficacy and safety of FDA- and EMA-approved AAAs for AD, namely, lecanemab and donanemab. Methods: We conducted a literature search in the PubMed, Scopus, and Web of Science databases in English, focusing on systematic reviews and/or meta-analyses, assessed by AMSTAR 2, concerning clinical and imaging efficacy, i.e., cognitive improvement and reduction of beta-amyloid on PET scan, as well as safety, i.e., adverse events and amyloid-related imaging abnormalities (ARIA). The extracted review-level dataset was entered into SPSS Version 26 for descriptive statistical analysis. Results: This umbrella review included 11 systematic reviews and/or meta-analyses. Patients treated with lecanemab or donanemab showed statistically significant changes on cognitive scales such as the Clinical Dementia Rating-Sum of Boxes (CDR-SB) (mean effect estimate −0.485, SD = 0.152, −0.70 to −0.34) and the Alzheimer’s Disease Assessment Scale-Cognitive Subscale (ADAS-Cog), but most were below or around clinically meaningful thresholds. Lecanemab and donanemab showed a statistically significant decrease in amyloid PET outcomes, including centiloids or the standardized uptake value ratio. Both antibodies were linked to ARIA, including amyloid-related imaging abnormalities-edema (ARIA-E OR 8.32–12.26) and amyloid-related imaging abnormalities-hemorrhage (ARIA-H OR 2–5.77), especially in ApoEε4 carriers. Conclusions: Lecanemab and donanemab are biologically active drugs for the treatment of early AD, with cognitive benefits below or around the clinically meaningful threshold. They are, however, associated with increased ARIA risk. Their administration depends upon careful patient selection, shared decision-making, and clear communication regarding expectations. Full article