教学课程资源库 更多>>

关键词： learning (artificial intelligence)   face recognition   image classification   image representation   sufficient training samples   single-sample FR   novel CRC-based FR framework   hierarchical extended collaborative representation   low-rank constrained variation dictionaries   discriminative training dictionary   proper samples   refined training dictionary   learned variation dictionaries   test sample   single-sample face recognition   hierarchical representation based classification   classification performance   CRC method   over-complete dictionary  

摘要： Collaborative representation based classification (CRC) has been widely used and shown good performance in face recognition (FR). Afterwards, hierarchical representation based classification has recently been proposed and aims to enhance the classification performance of the CRC method. However, these methods highly depend on the over-complete dictionary comprised of sufficient training samples, and cannot be directly applied for single-sample FR. In this study, the authors propose a novel CRC-based FR framework to address this issue, which is named hierarchical extended collaborative representation based classification (HECRC). Firstly, they integrate hierarchical representation based model with low-rank constrained variation dictionaries. Secondly, they select training samples that are the nearest neighbours of test images to obtain a more discriminative training dictionary, where an adaptive scheme is introduced to select proper samples automatically instead of setting a predefined number in traditional methods. Finally, the refined training dictionary and the learned variation dictionaries are jointly utilised to represent the test sample. Moreover, they combined the proposed HECRC with deep features to further improve the recognition rate. Experiments have been conducted on the AR and FERET datasets, and the results show that the proposed method has a substantial improvement over existing algorithms for single-sample FR.

关键词： 免疫检验   临床   质量控制   作用  

摘要： 探讨分析质量控制在临床免疫检验中的作用。方法:选取我院收集的324例临床免疫检验单为研究对象,采取随机分组方式将其研究对象分为观察组(162份)和对照组(162份),给予观察组应用质量控制处理方式,给予对照组应用常规检验处理方式,对比两组甲胎蛋白、血清胰岛素、C-肽、Ca199等各项指标的平均变异指数情况。结果:观察组甲胎蛋白为30.2±4.3,血清胰岛素为40.4±2.2,C-肽56.4±6.5,Ca199为30.3±2.5,对照组甲胎蛋白为67.2±8.3,血清胰岛素为60.5±3.4,C-肽为38.4±3.5,Ca199为60.6±6.5,由此可见,观察组经实施质量控制措施后,其甲胎蛋白、血清胰岛素、C-肽、Ca199等各项指标检测结果均优于对照组,两组数据差异对比具有显著统计学意义(P<0.05).结论在临床免疫检验中合理应用质量控制能为诊断和治疗提供合理且准确的医学参考,保证免疫检验科学化和标准化,消除影响免疫检验质量因素,提高免疫检验质量,因而值得临床大力推广和应用。

关键词： 血液分析仪   急慢性白血病   检验   应用价值  

摘要： 为分析研究血液分析仪对急慢性白血病检验的实际作用,随机选择住院接受治疗时间在2017年4月-2018年10月期间符合实验研究标准的80名急慢性白血病患者以及同期接受身体健康检查的40名体检合格者为研究对象,将40名急性白血病患者划归为A组,将40名慢性白血病患者划归为B组,将40名体检合格者划归为C组。方法:借助血液分析仪对所有患者进行血常规质量检验,研究实际的检验结果。结果:A、B两组患者在白细胞与血红蛋白检验结果的对比方面无显著差别(p<0.05)。与体检显示合格的40名健康人员相比,A、B两组患者的血红蛋白明显降低,白细胞水平上升显著。与A组患者相比,B组患者的血小板含量较低,患者之间的实验数据对比差异具有统计学意义(P<0.05)。结论:血液分析仪在急慢性白血病的检验方面具有重要的研究价值,依据检验结果,可以准确判断患者的患病种类,为临床此类疾病的诊断与治疗提供数据指标支持,且实际操作流程简单,值得在临床医疗服务研究领域进行深入的推广。

关键词： Film industry   entertainment industry   Hollywood   streaming services   streaming wars   video on demand   contracts   standard form contracts   entertainment industry contracts   film industry contracts   Netflix   Disney   HBO   Amazon   Comcast   AT&T  

摘要： Recent advancements in technology have changed the way consumers watch movies and television, and disrupted the entertainment industry. In the aftermath of this disruption, artists have more bargaining power than ever. This Note suggests ways to empower the industry ?outsider? by providing them with tools to educate themselves and effectively engage in negotiations with publishers. These tools include a collection of standard form contracts with terms tailored to the modern age of entertainment, increased funding for non-profits and labor unions, and appointed attorneys.

关键词： Compressed sensing  

摘要： The convolutional neural network (CNN) has recently achieved great breakthroughs in many computer vision tasks. However, its application in fabric texture defects classification has not been thoroughly researched. To this end, this paper carries out a research on its application based on the CNN model. Meanwhile, since the CNN cannot achieve good classification accuracy in small sample sizes, a new method combining compressive sensing and the convolutional neural network (CS-CNN) is proposed. Specifically, this paper uses the compressive sampling theorem to compress and augment the data in small sample sizes;then the CNN can be employed to classify the data features directly from compressive sampling;finally, we use the test data to verify the classification performance of the method. The explanatory experimental results demonstrate that, in comparison with the state-of-the-art methods for running time, our CS-CNN approach can effectively improve the classification accuracy in fabric defect samples, even with a small number of defect samples. © The Author(s) 2018.

关键词： PDCA管理   检验科危急值   漏报率  

摘要： 目的:分析应用PDCA循环法降低检验科危急值漏报率的效果。方法:医院2017年12月~2018年5月期间在检验科危急值报告及处理过程中引入PDCA循环法进行管理,改善危急值项目设置过多,门诊危急值管理缺陷,检验人员和医护人员不熟悉危急值处理流程等问题,比较管理前后检验科危急值漏报率情况。结果:经过PDCA循环法管理后,检验科月平均危急值数量明显减少,危急值报告比例降低,检验科危急值、门诊患者危急值平均确认时间均明显缩短,门诊危急值月平均延误数减少(P<0.05),经过PDCA循环法管理后,检验人员、医护人员对危急值处理流程知晓率均有明显提升(P<0.05),检验科危急值漏报率从1.03%下降到0(P<0.05)。结论:在检验科危急值报告及处理过程中应用PDCA循环法进行管理,能有效缩短检验科危急值平均确认时间,提高检验人员对危急值处理流程的知晓率,降低检验科危急值漏报率,为危重症患者临床抢救争取更多时间。

关键词： 溶血   生化检验   结果  

摘要： 目的研究溶血对临床生活检验结果的作用。方法选择2016年12月至2017年12月我院接受血液生化检查的患者41例,将患者血样分为A、B两组,A组血样采用常规离心处理,B组血样经冷冻、化冻和机械震荡后予以离心处理,分析和对比两组血液生化检验结果。结果三酰甘油、尿酸、肌酐及尿素氮指标组间差异性较低,无统计学意义(P>0.05);A组与B组血清白蛋白、丙氨酸转氨酶、天冬氨酸转氨酶、总蛋白、胆固醇指标,A组低于B组,二者差异明显,A组总胆红素及直接胆红素明显高于B组,组间差异明显(P<0.05)。结论溶血能够在一定程度上影响血液生化检验结果的准确性,因此,临床检查中应避免溶血问题。

关键词： 凝血酶原时间   血小板   肝硬化  

摘要： 目的探讨凝血酶原时间与血小板检验对肝硬化患者诊断的临床价值。方法选取2017年6月至2018年6月在本院诊疗肝硬化患者共58例作为研究组对象,同期选择58例健康受试者作为对照组。对比两组患者检测凝血酶原时间及血小板相关参数。结果研究组凝血酶原时间、血小板分布宽度、平均血小板体积均高于对照组,而血小板计数、血小板压积低于对照组,P<0.05,其差异具有统计学意义。结论凝血酶原时间和血小板参数可有效的反应患者肝脏出血情况,应用于诊断肝硬化临床效果理想,具备临床推广应用价值。