课程文献中心 更多>>

关键词： Solid modeling   Training   Artificial intelligence   Stators   Software   Image segmentation   Topology   Feature extraction   Atmospheric modeling   Permanent magnets   3-D   computer-aided design (CAD)   electric machines   machine learning   Mask Region-based Convolutional Neural Network (Mask R-CNN)   optimization  

摘要： The state-of-the-art design processes for electrical machines (eMachine) are template-based methods and design-from-scratch approaches. Over the past four decades, significant advancements have been made to make these methods effective in terms of electromagnetic performance. However, the state of the art cannot provide information on the topology and the components of an eMachine from a given non-parametrized computer-aided design (CAD). This information is imperative for the automatic selection of an appropriate simulation profile to meet the required key performance indicators (KPIs enhancing the numerical computation of electromagnetic fields, and improving the user experience through an improved user interface. Moreover, it can be used to generate a parametric version of a given CAD design, which can subsequently be utilized by an optimization tool for geometric refinement and optimal material selection. The first step to achieve this is recognizing the components and their relative special positioning. This article uses a Mask Region-based Convolutional Neural Network (Mask R-CNN an object detection technique, to identify the components of an eMachine from a CAD design.

关键词： Visualization   Computational modeling   Robustness   Location awareness   Heating systems   Computer architecture   Convolutional neural networks   Aggregates   Standards   Semantics   Explainable AI (XAI)   convolutional neural networks (CNNs)   Winsorization   saliency Maps  

摘要： Interpreting Convolutional Neural Networks (CNNs) is critical for safety-sensitive applications such as healthcare and autonomous systems. Popular visual explanation methods like Grad-CAM use a single convolutional layer, potentially missing multi-scale cues and producing unstable saliency maps. We introduce Winsor-CAM, a single-pass gradient-based method that aggregates Grad-CAM maps from all convolutional layers and applies percentile-based Winsorization to attenuate outlier contributions. A user-controllable percentile parameter $p$p enables semantic-level tuning from low-level textures to high-level object patterns. We evaluate Winsor-CAM on six CNN architectures using PASCAL VOC 2012 and PolypGen, comparing localization (IoU, center-of-mass distance) and fidelity (insertion/deletion AUC) against seven baselines including Grad-CAM, Grad-CAM++, LayerCAM, ScoreCAM, AblationCAM, ShapleyCAM, and FullGrad. On DenseNet121 with a subset of Pascal VOC 2012, Winsor-CAM achieves 46.8% IoU and 0.059 CoM distance versus 39.0% and 0.074 for Grad-CAM, with improved insertion AUC (0.656vs. 0.623) and deletion AUC (0.197vs. 0.242). Notably, even the worst-performing fixed $p$p-value configuration outperforms FullGrad across all metrics. An ablation study confirms that incorporating earlier layers improves localization. Similar evaluation on PolypGen polyp segmentation further validates Winsor-CAM's effectiveness in medical imaging contexts. Winsor-CAM provides an efficient, robust, and human-tunable explanation tool for expert-in-the-loop analysis.

关键词： 3D CAD model generation   computer-aided design   graph diffusion   BRep   computer vision  

摘要： In modern computer-aided design (CAD Boundary Representation (B-rep) is a widely used geometric modeling technique in industrial design and manufacturing. However, existing B-rep generation methods, which rely on tree-based hierarchies to represent and generate B-reps, fail to fully exploit the inherent graph structure of B-reps, resulting in suboptimal efficiency and model quality. To address this issue, we propose BRep-GD, a graph diffusion-based model specifically designed for B-rep generation. Unlike prior methods, BRep-GD treats B-reps as graphs, where nodes represent face elements, and edges represent boundary and vertex elements. By utilizing a continuous topological graph data structure, BRep-GD overcomes the challenges associated with directly applying graph diffusion models to B-rep generation. Specifically, BRep-GD introduces a graph diffusion method tailored to the features of CAD data, generating faces and edges sequentially. During edge generation, continuous topology decoupling is employed to avoid the need for global attention calculations, reducing computational complexity while ensuring geometric consistency and high-quality results. Experimental results demonstrate that BRep-GD outperforms existing state-of-the-art methods in both unconditional and class-conditional generation tasks, particularly in generating watertight solids and handling complex geometries. It significantly reduces isolated or inconsistent geometric components and improves generation efficiency.

关键词： CAM   culturally-sensitive care   older Korean Americans   regional gap  

摘要： Korean American older adults face challenges in accessing healthcare due to affordability and culturally distinct health beliefs. Many turn to traditional complementary and alternative medicine (TCAM) to address their health needs, yet research on TCAM use among this population remains limited. This study examined individual- and geographic-level factors associated with TCAM use using the data from the Study of Older Korean Americans (N = 2,150 a cross-sectional survey conducted across five U.S. states. Logistic regression analysis showed that TCAM use was predicted by health and well-being factors (arthritis, health needs, and lack of interest in work/leisure acculturation (English use demographic factors (gender and religion and geographic factors (perceived Korean community density). Multilevel analysis revealed significant regional differences: individuals living in areas with higher Korean population density, both perceived and objective, were more likely to use TCAM. These findings support the need for culturally and regionally tailored healthcare practices and policies.

关键词： rs4977574   9p21   CAD   HDL-c   triglycerides   atorvastatin  

摘要： Background: Coronary artery disease (CAD) arises from the convergence of genetic susceptibility, lipid dysregulation, and modifiable environmental exposures. The polymorphism rs4977574, located proximal to the CDKN2A/CDKN2B gene cluster, has been repeatedly implicated in CAD risk across several populations, yet its relationship to intermediate cardiometabolic phenotypes and pharmacological treatment patterns in Saudi individuals remains poorly characterized. Objective: This study aimed to evaluate the association of rs4977574 with CAD status, lipid-related phenotypes, smoking history, obesity, and atorvastatin exposure in a Saudi cardiovascular cohort, and to assess the robustness of observed associations through sensitivity-adjusted analyses excluding participants with major metabolic confounders. Methods: A case-control genetic association study was conducted in Saudi participants with clinically confirmed CAD and healthy controls. Genomic DNA was genotyped for rs4977574 using TaqMan (R) allelic discrimination assays. Genotype-phenotype associations were examined using chi-square testing, binary logistic regression under additive and dominant inheritance models, and one-way ANOVA for continuous lipid traits. Hardy-Weinberg equilibrium (HWE) was assessed in controls. Sensitivity analyses were conducted by sequentially excluding participants with obesity, smoking, diabetes mellitus, hypertension, dyslipidaemia, and statin use. Results: After covariate adjustment, rs4977574 was not independently associated with CAD case-control status under any inheritance model. Genotype-stratified analyses identified significant differences in HDL-cholesterol and triglyceride concentrations among cases, with no equivalent effects on total cholesterol or LDL-cholesterol. A significant association was observed between rs4977574 genotype and atorvastatin prescribing patterns. Sensitivity-adjusted analyses were directionally consistent with primary findings. HWE deviation persisted in

摘要： Statement of problem. The growing adoption of digital workflows and artificial intelligence (AI)-assisted design has revolutionized occlusal device fabrication, offering improved precision, efficiency, and reproducibility. However, the clinical reliability of digitally predicted occlusal contacts, particularly across different intensity levels and anatomic regions, remains insufficiently validated. Purpose. This study aimed to evaluate the accuracy and reliability of AI-predicted occlusal contacts in computer-aided design and computer-aided manufacture (CAD-CAM) occlusal devices fabricated through a fully digital workflow, with comparisons stratified by contact intensity and anatomic region. Material and methods. A cross-sectional observational study was conducted with 53 occlusal devices (45 maxillary, 8 mandibular) fabricated using intraoral scanning, AI-based CAD software program (Medit Link v3.2.2;Medit and 3-dimensional (3D) printing. Predicted occlusal contacts were automatically generated by the software program and compared with clinical markings obtained using articulating paper during the initial adjustment session. Agreement rates were calculated by contact intensity (low, medium, high) and anatomic region (anterior, posterior). Statistical analyses included descriptive statistics, the Friedman test for repeated-measures comparisons across intensity levels, Bonferroni-adjusted post hoc tests, and intraclass correlation coefficients [ICC(2,1 to assess internal consistency among continuous measurements within each device (alpha=.05). Results. Agreement between digitally predicted and clinically verified contacts increased systematically with intensity, with mean coincidence rates of 59.4%, 69.7%, and 79% for low-, medium-, and high-intensity contacts, respectively. Low-intensity contacts showed the greatest dispersion, while high-intensity contacts displayed the most stable agreement values. Internal consistency among the 3 continuous agreement measurements

关键词： italic>Tawas   Philippine traditional medicine   Rituals   CAM   Wittgenstein  

摘要： Rituals in medical practice have either been seen as an anthropological aspect of current biomedical processes or as a pre-scientific aspect of complementary and alternative medicine (CAM). In either tendency, the literature has since failed to account for these rituals as rituals-conveyors of meaning, expressions of identity, and even as a rite of passage from illness to wellness. As an alternative to current discussions, this paper presents the case study of tawas, a diagnostic ritual from Philippine traditional medicine that determines personalistic and mystical causes of illnesses. As a non-intrusive procedure, tawas involves incantations and some ritual objects, e.g., rice, candle, axe, etc., that do not pose any direct harm nor benefit to the patient. While complete reliance on tawas at the expense of proper medical procedures could harm patients, the very ritual of tawas itself occupies a limbo within non-beneficence and non-maleficence. Following a Wittgensteinian perspective of treating rituals as meaning-laden human activities, this paper argues that rituals like tawas, much like other rituals embedded in biomedical practices, should be understood as rituals and not as empirical cures, thereby allowing their tolerance in medical practice in general.

关键词： FDG   MDA-MB-231   Ostrich CAM Model   PET/CT Imaging   U87   Xenografting   alternative animal model   cancer research  

摘要： Animal models are utilized in the investigation of a variety of research questions in nuclear medicine. Radiopharmaceutics are usually tested in mouse, rat or chick chorioallantoic membrane (CAM) models and visualisation of their biodistribution is performed using dedicated small-animal PET/CT scanners. However, the limited availability of such scanners represents a significant bottleneck in preclinical imaging. To address this limitation, we explored an alternative animal model compatible with clinical imaging systems. The ostrich chorioallantoic membrane (CAM) was utilized as a platform for tumor xenografts, enabling imaging with a standard human PET/CT scanner. Growth conditions for tumor formation were established using human glioblastoma (U87) and breast cancer (MDA-MB-231) cell lines. Tumor visualization was achieved using18F-fluorodeoxyglucose (18F-FDG), a widely used clinical PET tracer, and its pharmacodynamic behavior was assessed. Our findings demonstrate that the ostrich CAM tumor model is a feasible and efficient system for the rapid evaluation of diagnostic tracers. Importantly, tracer uptake and kinetics can be reliably assessed using a clinical PET/CT scanner. This approach highlights the potential of the ostrich embryonic model as a versatile and accessible preclinical platform for nuclear medicine research.

关键词： passenger flow prediction   improved complete ensemble EMD   temporal convolutional network   channel attention mechanism   long short-term memory   deep learning  

摘要： With the rapid development of intelligent operation and management of urban rail transit, accurate passenger flow prediction is crucial for management and operation. However, the complex, nonlinear and non-smooth characteristics make detecting passenger flow evolution features challenging. In this regard, a novel decomposition integration model, IC-TLCA, is proposed. The model first decomposes the raw passenger flow data into multiple sublayers with different frequencies using an improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) algorithm to better capture the intrinsic structure of the data. Then, the temporal convolutional network (TCN long-short-term memory network (LSTM) and channel attention module (CAM) are combined to predict each sublayer separately. Finally, by combining the prediction results of each sublayer, the final passenger flow prediction is obtained. After comparing with all baseline models and conducting ablation experiments, the IC-TLCA model has been validated to be innovative in theory and superior in practical applications, thereby providing an effective solution for passenger flow prediction.