教学课程资源库 更多>>

关键词： automatic training samples generation   unsupervised segmentation   graph convolutional neural network   ALS point clouds  

摘要： The labeling of point clouds is the fundamental task in airborne laser scanning (ALS) point clouds processing. Many supervised methods have been proposed for the point clouds classification work. Training samples play an important role in the supervised classification. Most of the training samples are generated by manual labeling, which is time-consuming. To reduce the cost of manual annotating for ALS data, we propose a framework that automatically generates training samples using a two-dimensional (2D) topographic map and an unsupervised segmentation step. In this approach, input point clouds, at first, are separated into the ground part and the non-ground part by a DEM filter. Then, a point-in-polygon operation using polygon maps derived from a 2D topographic map is used to generate initial training samples. The unsupervised segmentation method is applied to reduce the noise and improve the accuracy of the point-in-polygon training samples. Finally, the super point graph is used for the training and testing procedure. A comparison with the point-based deep neural network Pointnet++ (average F1 score 59.4%) shows that the segmentation based strategy improves the performance of our initial training samples (average F1 score 65.6%). After adding the intensity value in unsupervised segmentation, our automatically generated training samples have competitive results with an average F1 score of 74.8% for ALS data classification while using the ground truth training samples the average F1 score is 75.1%. The result shows that our framework is feasible to automatically generate and improve the training samples with low time and labour costs.

关键词： Hyperspectral image classification   Collaborative learning   Lightweight convolutional neural networks   Dual-loss   Deep clustering   Limited training samples  

摘要： Deep learning provides excellent potentials for hyperspectral images (HSIs) classification, but it is infamous for requiring large amount of labeled samples while the collection of high-quality labels for HSIs is extremely expensive and time-consuming. Furthermore, when the limited training samples are available, deep learning methods may suffer from over-fitting. In this work, we propose a novel collaborative learning framework for semi-supervised HSI classification with joint deep convolutional neural networks and deep clustering. Specifically, a lightweight 3D convolutional neural network (CNN) with much less parameters compared with classical 3D CNNs is designed for deep discriminative feature learning and classification. Then a deep clustering method, that is approximate rank-order clustering (AROC) algorithm, is applied to cluster deep features to generate pseudo labels for abundant unlabeled samples. Finally, we fine-tune the lightweight 3D CNN by minimizing a dual-loss (softmax loss and center loss) using both true and pseudo labels. Experimental results on three challenging HSI datasets demonstrate that the proposed method can achieve better performance than other state-of-the-art deep learning based methods and traditional HSI classification methods methods.

关键词： land cover mapping   multiple classifier ensemble (MCE)   iterative classification (IC)   self-adaptive updating of samples   China-Pakistan economic corridor (CPEC)   remote sensing  

摘要： Land cover samples are usually the foundation for supervised classification. Unfortunately, for land cover mapping in large areas, only limited samples can be used due to the time-consuming and labor-intensive sample collection. A novel and practical Object-oriented Iterative Classification method based on Multiple Classifiers Ensemble (OIC-MCE) was proposed in this paper. It systematically integrated object-oriented segmentation, Multiple Classifier Ensemble (MCE), and Iterative Classification (IC). In this method, the initial training samples were updated self-adaptively during the iterative processes. Based on these updated training samples, the inconsistent regions (ICR) in the classification results of the MCE method were reclassified to reduce their uncertainty. Three typical case studies in the China-Pakistan Economic Corridor (CPEC) indicate that the overall accuracy of the OIC-MCE method is significantly higher than that of the single classifier. After five iterations, the overall accuracy of the OIC-MCE approach increased by 5.58%-8.38% compared to the accuracy of the traditional MCE method. The spatial distribution of newly added training samples generated by the OIC-MCE approach was relatively uniform. It was confirmed by ten repeated experiments that the OIC-MCE approach has good stability. More importantly, even if the initial sample size reduced by 65%, the quality of the final classification result based on the proposed OIC-MCE approach would not be greatly affected. Therefore, the proposed OIC-MCE approach provides a new solution for land cover mapping with limited samples. Certainly, it is also well suited for land cover mapping with abundant samples.

关键词： Rectal surgery   Laparoscopic   Volume  

摘要： Background Laparoscopic rectal surgery is technically challenging and often low volume. Alternatively, colon resections utilize similar advanced laparoscopic skills and are more common but it is unknown whether this experience affects laparoscopic rectal surgery outcomes. The purpose of this paper is to determine the volume-outcome relationship between several colorectal procedures and laparoscopic rectal surgery outcomes. Methods This was a population-based retrospective cohort of all colorectal surgeries with primary anastomoses performed across Canada (excluding Quebec) between April 2008 and March 2015. Patient characteristics, comorbidities, procedures, and discharge details were collected from the Canadian Institute for Health Information. Volumes for common colorectal procedures were calculated for individual surgeons. All-cause morbidity, defined as complications arising during the index admission and contributing to an increased length of stay by more than 24 h, was the primary outcome examined. Results A total of 5323 laparoscopic rectal surgery cases and 108,034 colorectal cases, between 180 hospitals and 620 surgeons, were identified. Data analysis demonstrated that high-volume laparoscopic rectal surgeons (OR 0.77, CI 0.61-0.96, p = 0.020) and high-volume open rectal surgeons (OR 0.76, CI 0.61-0.93, p = 0.009) significantly reduced all-cause morbidity. Conversely, surgeon volumes for laparoscopic and open colon cases had no effect on laparoscopic rectal outcomes. Conclusion High-volume surgeon status in laparoscopic and open rectal surgery are important predictors of all-cause morbidity after laparoscopic rectal surgery, while laparoscopic colon surgery volumes did not impact outcomes. This may reflect more dissimilarity between colon and rectal cases and less transferability of advanced laparoscopic skills than previously thought.

关键词： 微生物形态学检验   感染性疾病   痰涂片   分泌物涂片  

摘要： 探讨微生物形态学检验用于感染性疾病诊断的作用。方法:收集我院2018年1月至2019年1月儿科患者痰标本7200例以及妇科分泌物标本28800例,对所有标本进行盐水涂片、革兰氏染色以及镜检等一系列微生物形态学检验,统计和分析检验结果。结果:收集的7200例儿科痰样本微生物形态学检验结果显示,细菌阳性患儿共3758例,阴性患儿3522例,总检出率为52.19%。其中,细菌阳性患儿所检出得病原菌种类依次为卡他莫拉菌、肺炎链球菌、流感嗜血杆菌、金黄色葡萄球菌以及其他菌群;妇科分泌物涂片检测结果显示病原菌依次为霉菌感染、细菌感染、滴虫感染及其他感染。其中,阴道清洁度为Ⅰ~Ⅱ患者5769例,清洁度为Ⅲ~Ⅳ患者23031例,炎症检出率为79%。其中,单一感染者5988例,混合感染患者17043例。结论:微生物形态学检验具有一定的实验室诊断价值,尤其在感染性疾病诊断上,具有较高的准确性,值得在临床上做进一步的推广。

关键词： 常规凝血检验   宫外孕大出血   输血不良反应  

摘要： 宫外孕大出血输血治疗不良反应检测中常规凝血检验应用价值探究。方法:本院妇产科2015.1~2016.1就诊宫外孕大出血输血者82例。依照是否有输血不良反应分组。对比两组输血前后血常规及凝血功能各指标差异。结果:输血前两组血常规、凝血功能指标未见明显差异(P>0.05)。输血后不良反应组HB、RBC、HCT、PLT、FIB低于无异常组;PT、APTT、TT高于无异常组,差异有统计学意义,(P<0.05)。结论:常规凝血检验可监测宫外孕大出血接受输血治疗的患者有无输血不良反应发生。

关键词： 化工分析   化工检验   重要性   管理措施  

摘要： 化学分析与化工检验工作主要是将化学知识和化工分析工作之间进行有效的衔接,以此来保证工作人员可以对化学知识的具体应用范围和具体化工产品的性质有着全方位的了解。由于受到外界因素的干扰,在我国化工分析工作当中经常存在一些问题亟待解决。鉴于此,文章首先对化工分析与化工检验发挥的重要作用进行了阐述,然后研究了化工分析与化工检验工作中存在的问题及洁具措施,以供参考。

关键词： 垃圾分类   包装   标识  

摘要： 全国推行垃圾分类工作已近一年,而实际推动效果较为缓慢,其中一个重要原因就是民众对日常用品的垃圾分类标准不了 解。借鉴塑料包装回收标志的成功做法,本文提出了利用包装标识来提升民众对垃圾分类的认知,做到分类明显、对应投放。从日用品 包装生产源头落实垃圾分类工作,进而利用包装产品标准实现垃圾分类标识的标准化推广,有效推动日用品包装产品垃圾分类工作的落 实。

关键词： 社会网络   内生性问题   人职匹配   产权安排   熵平衡法  

摘要： 劳动力市场的社会网络研究已取得了丰硕成果,但进一步推进此研究却面临两大挑战:第一,如何排除内生性问题的干扰,确切证实使用社会网络(即"找关系")对求职结果有因果效应;第二,如何准确估计宏观因素(如制度、文化)对作用效应的影响和形塑,以回答"关系"现象的文化观与制度观之争。文章从实证方法论层次出发,以人与职位的匹配过程为分析对象,演绎性地论述了网络使用及网络资源(信息、人情)对"低才高就"的作用效应,以及人情资源的作用效应在体制内外的差异。基于八城市抽样调查数据(JSNET2009),使用简单回归模型和熵平衡法对假设进行了交叉检验,实证结果一致表明:使用社会网络对求职结果有因果效应;核心表现是通过人情影响帮助求职者实现"高就";形塑网络效应的根本力量是制度安排而非文化环境。