教学课程资源库 更多>>

关键词： Learning algorithms  

摘要： The difficulties of obtaining sufficient high-quality labelled samples have always been one of the important factors hindering the practical application of hyperspectral images (HSI) classification. The regular deep learning models only attempt to mine the discriminant and informative features in the target HSI. Therefore, the satisfactory results cannot be obtained with only a few labelled samples because their huge parameter space cannot be fully trained. To this end, a simple and effective framework is proposed utilizing the idea of meta-learning to improve HSI classification performance under the condition of small sample. Specifically, we design a simple model by stacking convolutional blocks, and introduce a model-agnostic meta-learning algorithm (MAML) to enable the model to implement meta-optimization on vast different tasks. The MAML algorithm can enable the model to acquire the more general-purpose representations, so as to adapt quickly to new tasks with only a few labelled samples and a small number of gradient update steps. To improve the practical value of the research, two kinds of classification scenarios, cross-data small sample classification on the same HSI and cross-scene small sample classification between different HSI, are designed for experiments. The results on three public HSI demonstrate that our method outperform the state-of-the-art methods in both scenarios. In addition, the proposed method, actually an optimization-based meta-learning method, provides a new idea for HSI small sample classification.

关键词： Loneliness   Depression   Emotional regulation   Mental health   Longitudinal studies   COVID-19  

摘要： Background: Longitudinal studies examining the temporal association between mental health outcomes during the COVID-19 outbreak are needed. It is important to determine how relationships between key outcomes, specifically loneliness and depressive symptoms, manifest over a brief timeframe and in a pandemic context. Method: Data was gathered over 4 months (March - June 2020) using an online survey with three repeated measures at monthly intervals (N = 1958;69.8% females;Age 18-87 years, M = 37.01, SD =12.81). Associations between loneliness, depression symptoms, and emotion regulation difficulty were tested using Pearson's product moment correlations, and descriptive statistics were calculated for all study variables. Cross-lagged structural equation modelling was used to examine the temporal relationships between variables. Results: The longitudinal association between loneliness and depressive symptoms was reciprocal. Loneliness predicted higher depressive symptoms one month later, and depressive symptoms predicted higher loneliness one month later. The relationship was not mediated by emotion regulation difficulties. Emotion regulation difficulties and depressive symptoms were also reciprocally related over time. Limitations: Limitations include the reliance on self-report data and the non-representative sample. There was no pre-pandemic assessment limiting the conclusions that can be drawn regarding the mental health impact of the COVID-19 crisis. Conclusions: Loneliness should be considered an important feature of case conceptualisation for depression during this time. Clinical efforts to improve mental health during the pandemic could focus on interventions that target either loneliness, depression, or both. Potential approaches include increasing physical activity or low-intensity cognitive therapies delivered remotely.

关键词： Deep learning   Transfer learning   Image processing   Classification  

摘要： Recent developments in deep learning have brought huge breakthroughs in the image processing area, which triggered numerous successful applications and positively impacted the current big data context of Industry 4.0. On the other hand, it is widely known that large amounts of training data are required to train a deep learning model with millions of parameters, which limits its application in many industrial applications where sufficient data resources are lacking. Transfer learning is one of the practical solutions to reduce the data required for training, which tries to reuse learned knowledge for similar tasks. Nevertheless, many technical details of transfer learning implementation are not well documented. Therefore, in this work, two datasets collected from plastics manufacturing processes were studied to investigate different transfer learning approaches and implementation details for high-performance model building under the constraint of limited available training data. Different transfer learning implementations are compared and important technical details are also discussed in this study. Through this study, the minimum number of training samples can be estimated. Transfer learning is compared with the newly developed few-shot learning approach as a brief comparative study. Finally, this work summarizes practical guidelines for the development of image classification models with limited data resources.

关键词： 贫血   临床诊断   血常规检验   应用效果  

摘要： 分析针对贫血患者在临床诊断中实施血常规检验的临床应用效果。方法:于2019年1月~2020年12月期间选取在本院治疗贫血的98例患者作为研究对象,根据疾病类型的的不同将其分为研究组、对照组,每组49例,另外选取49例健康人群作为常规组,其中研究组患者属巨幼细胞贫血,对照组患者属缺铁性贫血,对以上三组均进行血常规检验,将三组血常规指标(RBC、HGB、RDW)检验结果进行对比。结果:经过检验后,研究组患者与常规组患者中的RBC、HGB指标含量高于对照组(P<0.05),且该两组患者的RDW指标也明显低于对照组(P<0.05);另外研究组患者中的RBC、HGB、RDW三项指标中,RBC与RDW指标水平高于常规组(P<0.05),而HGB指标水平低于常规组(P<0.05)。结论:针对贫血患者在临床诊断中实施血常规检验能够大幅度提升诊断效果,提高准确率,进而增强对患者的治疗时效性,效果显著。

关键词： 突发公共卫生事件   理化检验质量控制   应用效果  

摘要： 研究理化检验质量控制在突发公共卫生事件中的实际作用。方法:以92例突发公共卫生事件作为研究对象,发生时间均在2019年2月-2020年7月之间,研究方式为分组对比,即对照组(46例)和观察组(46例),观察组采取理化检验质量控制,对照组实行常规理化检验管理,观察指标为报告发出时间、有效控制时间,以及民众满意度。结果:观察组各项指标均优于对照组,P1=0.0000,P2=0.0000,P3=0.0000,有统计学意义。结论:突发公共事件的控制效果与理化检验质量控制密切相关,应予以充分的重视。

关键词： Machine learning   16S rRNA   Amplicon sequencing   Fecal source tracking   SVM  

摘要： The bacterial diversity and corresponding biological significance revealed by high-throughput sequencing contribute massive information to source tracking of fecal contamination. The performances of classification models on predicting the fecal source of geographical local and foreign samples were examined herein, by applying support vector machine (SVM) algorithm. Random forest (RF) and Adaboost were applied for comparison as well. Discriminatory sequences were selected from Clostridiale, Bacteroidales, or Lactobacillales bacterial groups using extremely randomized trees (ExtraTrees). 1.51-12.64% of the unique sequences in the original library composed the representative markers, and they contributed 70% of the discrepancies between source microbiomes. The overall accuracy of the SVM model and the RF model on local samples was 96.08% and 98.04%, respectively, higher than that of the Adaboost (90.20%). As for the non-local samples, the SVM assigned most of the fecal samples into the correct category while several false-positive judgments occurred in closely related groups. The results in this paper suggested that the SVM was a time-saving and accurate method for fecal source tracking in contaminated water body with the potential capability of executing tasks based on geographically unassociated samples, and underlined the necessity of qPCR analysis for accurate detection of human source pollution.

关键词： 新型城镇化   流通业   高质量发展   中介效应模型   省际面板数据  

摘要： 本文利用2008-2019年我国省际面板数据,通过构建中介效应模型,从结构升级视角探究新型城镇化建设对流通业高质量发展的影响及其作用渠道。研究发现:新型城镇化显著促进了流通业高质量发展。从影响机制来看,新型城镇化建设通过推动消费结构升级和产业结构优化等中介效应渠道,促进流通业高质量发展,且两种中介效应之和占总效应的比例达77.26%。进一步对比发现,消费结构升级的中介效应要强于产业结构优化中介效应。上述结论为新型城镇化助推产业结构优化,加快释放消费潜力、促进消费升级,为畅通国民经济循环和现代流通体系建设提供重要的经验证据支撑。

关键词： 共享平台   医技检验检查   结果互认   医疗管理   现状  

摘要： 分析部分地区医学检验检查互认工作发展现状以及受阻原因,从功能模块、搭建运维、参与主体、科技支撑等方面阐述医技共享平台构建,以促进实现检验检查结果互认。

关键词： 血液样本   溶血现象   生化检验  

摘要： 目的分析溶血现象对临床生化检验项目作用。方法便利选取2018年1月—2020年1月到该院行健康体检的60名人员的血液样本作为研究对象,随机平均分为实验组和对照组两组。对照组血液标本置入肝素抗凝管,而实验组则震荡使其溶血。标本采用全自动生化分析仪检测后,比较分析生化指标中的天门冬氨酸氨基转移酶、葡萄糖、乳酸脱氢酶、血钾、尿素氮、总胆固醇、三酰甘油水平。结果实验组的天门冬氨酸氨基转移酶为(57.21±2.45)U/L、葡萄糖为(3.21±0.52)mmol/L、乳酸脱氢酶为(211.25±21.36)U/L、血钾水平为(5.62±0.35)mmol/L,对照组的天门冬氨酸氨基转移酶为(53.24±2.78)U/L、葡萄糖为(4.35±1.15)mmol/L、乳酸脱氢酶为(125.75±20.36)U/L、血钾为(3.45±0.89)mmol/L,差异有统计学意义(t=5.868、5.782、15.870、12.428,P<0.05)。实验组尿素氮为(5.32±1.24)mmol/L、总胆固醇为(4.35±0.72)mmol/L、三酰甘油为(1.35±0.25)mmol/L,对照组尿素氮为(5.42±1.25)mmol/L、总胆固醇为(4.28±0.73)mmol/L、三酰甘油为(1.32±0.27)mmol/L,差异无统计学意义(P﹥0.05)。结论溶血会影响到生化检验的准确性和精度,对检验有着较大的负面影响,为了避免检测指标失真,临床需要采取适当的措施保障血液标本不发生溶血现象。