课程文献中心 更多>>

关键词： Attention mechanism   Deep learning   Ensemble learning   Explainable AI   Federated learning   Hi-ResCAM   Lung cancer   SHapley Additive exPlanations (SHAP)  

摘要： Lung cancer is a predominant cause of cancer-related deaths globally, and early detection is essential for improving patient prognosis. Deep learning models with attention mechanisms have shown promising accuracy in detecting lung cancer from medical imaging data. However, privacy concerns and data scarcity present significant challenges in developing robust and generalizable models. This paper proposes a novel approach for lung cancer detection, ‘FVCM-Net’, integrating federated learning with attention mechanisms and ensemble learning to address these challenges. Federated learning is employed to train the model across multiple decentralized institutions, allowing for collaborative model development without sharing sensitive patient data and minimizing the risk of such sensitive data being misused. Furthermore, this approach enables the development of more accurate and generalized models by leveraging diverse datasets from multiple sources. We employed ensemble learning to produce more accurate predictions than a single model. For interpretability of the lung cancer identification model, we employ XAI (Explainable Artificial Intelligence) techniques such as SHAP (SHapley Additive exPlanations) and HiResCAM (High-Resolution Class Activation Mapping). These techniques help us understand how the model makes its decisions and predictions. This study utilizes a diverse collection of lung CT scan images from four datasets, including LIDC-IDRI, IQ-OTH/NCCD, a public Kaggle dataset, and additional online sources. Experimental results revealed that the proposed method achieved higher performance in lung cancer detection with 98.26% average accuracy and 97.37% average F-1 score. The high performance of FVCM-Net and ensemble learning has the potential to significantly impact medical imaging, helping radiologists make better clinical decisions.

关键词： DeepSeek   CAD   AutoLISP   绘图插件  

摘要： 随着DeepSeek大模型技术与创新理念的快速发展并席卷全球,基于人工智能的CAD插件开发成为提升设计效率与智能化的一个方向.研究探讨基于DeepSeek大模型的CAD绘图插件的开发应用,旨在通过开发自然语言指令和生成式AI技术获得智能绘图功能的插件.结合深度学习模型,DeepSeek不仅能理解设计师描述的文本意图并生成代码,加载插件后可实现在CAD环境中的绘图、抄图、编号、尺寸自动标注和图层自动设置等参数化建模工作,还能在深度思考中实现错误检测及自动化修正,为用户增加反馈信息,提出设计优化建议方案.利用交互式设计,可为非专业用户提供低门槛的CAD工具,也可为不精通编程的设计人员跳过编程环节或降低编程操作复杂度,实现调用插件绘图.结果表明,插件的使用可提高绘图效率,缩短设计周期,由AI驱动的CAD技术为设计创新提供了可行路径.

关键词： High-order mesh   High-Order Methods   Mesh adaptation   Mesh Generation  

摘要： The present article studies the problem of approximating 3D surface models with meshes composed of curved triangles of arbitrary order. The considered process derives from a high-order solution-based mesh adaptation method called log-simplex method. In this case, it is locally applied on a specific 2D high-order solution, which is built from the features of the model and is defined on the tangent plane to the surface. This way, for a given mesh complexity, an optimal metric field is computed, which then drives the mesh adaptation procedure.

关键词： 透湿性   GB/T 12704—2009   测试方法对比   洗涤耐久性   统计分析   面料  

摘要： 系统地比较GB/T 12704.1—2009《纺织品透湿性试验方法第1部分:吸湿法》与GB/T 12704.2—2009《纺织品透湿性试验方法第2部分:蒸发法》(方法B)两种透湿性测试方法的差异性,并深入探究标准洗涤程序对纺织品透湿性能的耐久性影响。实验选取同批次面料样本,分别采用两种方法对其洗涤前后的透湿率进行测试。结果表明:洗涤可能改变面料透湿性能,但不同测试方法对测试敏感度不同,后者所测结果洗涤后数据变化幅度更大;方法间对比显示,同一样品,透湿蒸发法测试值高于吸湿法,这一差异揭示了测试原理的根本性不同对结果产生的巨大影响。结论强调,在评价纺织品的透湿性时,必须明确测试方法标准,并考虑其在使用寿命内的性能衰减;建议在产品开发与质量监控中,根据产品最终用途选择适宜的测试方法,并建立基于洗涤后性能的评价体系。

关键词： coronary artery disease   CMR   heart failure   left ventricle filling pressure   noninvasive   outcomes   AF   atrial fibrillation   CAD   coronary artery disease   CIROC   Cardiovascular Imaging Registry of Calgary   CMR   cardiovascular magnetic resonance   EF   ejection fraction   HF   heart failure   HFpEF   heart failure with preserved ejection fraction   HFrEF   heart failure with reduced ejection fraction   HR sub   subdistribution HR   ICD-10-CA   International Statistical Classification of Diseases-10th Revision_Canadian version   LAV   left atrial volume   LGE   late gadolinium enhancement   LV   left ventricle   LVAD   left ventricular assist device   LVEF   left ventricular ejection fraction   LVFP   left ventricular filling pressure   LVFP cmr   CMR-derived left ventricular filling pressure   NT-proBNP   N-terminal pro-B-type natriuretic peptide   RCS   restricted cubic spline   TTE   transthoracic echocardiography  

摘要： Cardiovascular magnetic resonance (CMR)-derived left ventricle filling pressure (LVFP_cmr) has shown strong correlation with invasively measured values and early promise as a prognostic marker in defined patient populations.

关键词： 热生物工程   纺织品   热湿传递   热舒适性   先进材料   功能性CAD软件   信息学与人工智能  

摘要： 纺织热生物工程(TTB)是一个新兴的交叉学科领域,它运用物理、化学和计算科学来设计和制造能够与人体体温调节系统、热舒适性和个人热管理实现最佳交互的材料和纺织产品。该领域专注于建立系统热湿传递科学理论,从分子和纳米尺度材料到纺织产品以及人体-服装-建筑环境-气候/外太空热环境生态系统,旨在维持人体热平衡,预防热应激或冷应激,并促进身心健康。多尺度建模、热功能设计CAD、先进热功能和智能材料、测试方法和标准以及热功能CAD、数字孪生和人工智能技术的进步,已将纺织科学研究领域转变为连接人体生理学、材料科学、纺织工程和环境可持续性的综合性生物工程跨学科领域。本综述总结了从基础理论、建模和仿真、测试方法和标准热CAD软件到材料创新在日常气候适应性服装、运动、生物医学、消防、建筑施工、汽车和火车等交通工具以及太空飞行器等领域的最新进展,并重点介绍了纺织热生物工程与信息学面临的挑战及未来发展方向。

关键词： 蒸发热板法   热阻   湿阻   均匀性   稳定性  

摘要： 为了提高纺织品稳态条件下热阻和湿阻试验结果的准确性,依据GB/T 11048—2018研制了一批蒸发热板法测定纺织品热阻和湿阻用标准样品。为了验证该标准样品的均匀性和稳定性,按照GB/T 15000.3—2003和GB/T 11048—2018的相关要求,对该批测定纺织品热阻和湿阻用标准样品的热阻和湿阻值进行了验证。该试验表明,该批标准样品符合GB/T 11048—2018对参照样的要求且均匀性和稳定性良好,可用于校准仪器台间差、确保检测机构间测试结果具有可比性。

摘要： We read with great interest the recent article published in the European Journal of Radiology evaluating the diagnostic performance of AI-assisted coronary CT angiography for CAD-RADS classification. This work highlights ongoing efforts to improve...

关键词： 压铸成型   凸轮轴承盖   气孔率   浇注系统   排溢系统  

摘要： 针对汽车凸轮轴承盖一体化压铸成型气孔率要求低的问题,运用PQ2图优化凸轮轴承盖压铸模设计,采用MAGMA软件进行有限元模型的建立及模拟分析,预测铸件成型气孔率,并通过正交试验、遗传算法进行凸轮轴承盖一体化压铸成型工艺优化。通过确定最优成型工艺参数组合,再进行成型模拟分析和生产验证,对生产的汽车凸轮轴承盖进行X射线探伤检测。结果表明,通过PQ2图优化模具设计及正交试验,遗传算法优化压铸成型工艺参数,有效控制汽车凸轮轴承盖压铸成型气孔率,提升了铸件品质,缩短了铸件开发及生产周期。

关键词： 牙齿缺失   计算机辅助设计和制造种植导板技术   常规种植技术   种植体精度   炎症因子  

摘要： 目的 探讨基于临床CT数据的计算机辅助设计和制造(CAD/CAM)种植导板技术对牙齿缺失患者种植体精度、炎症因子及美观度的影响。方法 选取2022年1月至2024年5月济南市中西医结合医院收治的96例牙齿缺失患者,以随机数字表法将其分为对照组(n=48)和观察组(n=48)。对照组采取常规种植技术,观察组采取CAD/CAM种植导板技术。对比两组的种植效果、种植体精度、牙周指数[龈沟出血指数(SBI)、菌斑指数(PLI)]、咀嚼效率、龈沟液炎症因子[基质金属蛋白酶-2(MMP-2)、金属蛋白酶组织抑制剂-2(TIMP-2)、前列腺素E_(2)(PGE_(2))]、美观度(种植体外形、色泽)及并发症发生情况。结果 观察组的种植效果优于对照组,种植体深度误差、头部误差、根部误差、角度误差低于对照组(P<0.05)。术后3个月,观察组的SBI、PLI评分及MMP-2、PGE_(2)水平较对照组低,咀嚼效率、TIMP-2水平及种植体外形、色泽评分较对照组高(P<0.05)。观察组的并发症总发生率低于对照组(P<0.05)。结论 CAD/CAM种植导板技术可提高牙齿缺失患者种植体精度及美观度,降低炎症因子水平,减少并发症,改善牙周指数及咀嚼效率。