不同机器学习方法对新型冠状病毒感染与社区获得性肺炎鉴别诊断分析

目的：利用深度学习技术,全自动标注病变的计算机断层扫描（CT）数据,开发准确快速区分新型冠状病毒感染（COVID-19）和其他社区获得性肺炎的人工智能模型。方法：回顾性分析248例COVID-19患者及347例其他肺炎患者的资料,进行COVID-19与其他肺炎分类;在人工智能肺分割提取后将异常的CT图像特征降维,输入几种经典强化机器学习模型、三维卷积神经网络（3D CNN）和注意力多示例学习（Attention-MIL）深层神经网络架构中,模型诊断性能利用受试者工作特性（ROC）曲线、精确召回率（PR）曲线、曲线下面积（AUC）、敏感性、特异性、准确性指标进行评价。结果：在经典机器学习模型中K邻近算法（KNN）具有较好的效果,在外部测试集上的AUC值和平均精度（AP）值分别为0.79和0.89,平衡F分数（F1）值为0.76,准确率为0.75,敏感性为0.76,精确率为0.77;经典的3D CNN在外部测试集上效果良好,AUC值和AP值分别为0.64和0.82,F1值为0.71,准确率为0.78,敏感性为0.66,精确率为0.62;Attention-MIL模型在外部测试集上表现出更好...     

远震与极远震部分震相的幅值-震级-震中距-深度建模与应用研究

不同震相具有不同的振动特性和传播规律,对应各自不同的幅值-震中距-深度衰减规律,本文基于禁核试核查国际数据中心公报,统计P,PcP,PKP,PKPbc及PKPab远震和极远震震相样本随震中距的分布,运用基于残差统计的迭代方法回归上述震相的幅值-震级-震中距-深度模型,通过震级残差标准差与均值的统计进行模型评估,结果显示:P,PcP,PKP,PKPbc及PKPab震相的震级残差标准差范围为0.30—0.36,满足一般震相相容性判断的需求;除PKPbc的残差均值大于0.03外,其余震相残差均值均为0.01左右,模型的系统偏差极小,甚至可以忽略不计。最后针对模型进行了幅值预测比对、震级相容性检测、极远震体波震级计算等三个不同场景的应用研究,验证模型可用于日常地震监测。      

数字河道测量系统的研究与开发

河道测量作为河流治理和开发的基础,其技术发展和研究已引起有关部门的高度重视,在河流治理开发和水资源利用中占有极其重要的地位.文中介绍了GPS导航定位数字河道测量系统RISS的开发背景和意义,简述了该系统的总体结构、功能、特点和应用.     

AR模型谱在超导重力数据信号检测中的分析研究

在介绍AR(auto-regression)模型谱分析原理的基础上,分别采用AR模型谱和周期图法对法国Strasbourg、澳大利亚Mt Stromlo和日本Matsushiro三个站的超导重力数据进行信号检测,以半日波的理论值[1]为依据,运用两种方法进行半日波信号检测、分析与比较。结果表明,在超导重力数据信号检测分析中,AR模型谱比周期图法更准确、稳定,且受数据量的影响较小。     

双轴应力下非贯通节理岩体压缩损伤本构模型

针对目前节理岩体损伤变量定义中大多仅考虑节理长度、倾角等几何性质,而未考虑节理抗剪强度等力学性质的不足,基于断裂力学中的由于单个节理存在引起的附加应变能增量与损伤力学中的损伤应变能释放量相关联的观点,推导出了在双轴应力下含单条非贯通闭合节理岩体的损伤变量计算公式,并根据断裂力学理论对双轴压缩荷载下的单个节理尖端应力强度因子计算方法进行了研究,得出了应力强度因子KⅠ、KⅡ的计算公式;同时考虑多节理间的相互作用,给出了单组单排及单组多排非贯通节理尖端应力强度因子计算公式,由此建立了相应的节理岩体双轴压缩损伤本构模型,并利用该模型进行了相应的算例分析。结果表明：对含单条非贯通闭合节理的岩体而言,当节理倾角小于其内摩擦角时,岩体强度与完整岩石相同,岩体损伤为0,而后随着节理倾角增加,岩体强度、损伤随节理倾角的变化分别呈开口向上及向下的抛物线,当节理倾角约为60°时,岩体损伤最大,强度最低。随着节理长度增加,岩体损伤增加,而随着节理内摩擦角的增加,岩体损伤则减小;对含单组单排非贯通闭合节理的岩体而言,当节理总长度一定时,随着单条节理长度的减小及节理条数的增加,岩体损伤则逐渐减小,但其减小幅度与节理条数并不呈线性关系。     

西南印度洋中脊表层沉积物非碳酸盐组分的粒度特征及其地质意义

The carbonate-free fraction of 20 surface sediments collected from the ultraslow-spreading Southwest Indian Ridge(SWIR) was studied by grain size analysis and mineralogical analysis with X-ray powder diffraction(XRD),stereo microscopy and scanning electron microscopy(SEM). The characteristics of the carbonate-free fraction of the sediments were obtained, and related influential factors were discussed. The results show that the mean grain size of this fraction is in 1.96Φ–8.19Φ, with poorly sorting and unimodal, bimodal or irregular bimodal distribution patterns. Four grain size end members of the fraction are derived with the End Member Model method. The finest end member EM1 shows a significant contribution of terrigenous materials of the aeolian input and sediment carried by the bottom current. End member EM2 with medium size mainly reflects sediment of a siliceous bioclast origin. EM3 and EM4 are interpreted as representing the coarser volcanic materials related to bedrock weathering or volcanic activities. Multi-provenance is the dominant factor controlling the grain size pattern of the carbonate-free fraction of the sediments in that area. In addition, sediment transport processes such as the bottom current and wind are the minor factors that influence the grain size distribution of the carbonate-free fraction sediments.     

长江口北支盐水倒灌的数值模型研究

20世纪80年代以来,国内对长江口盐水入侵进行了大量系统专门的研究,对长江口的盐水入侵规律有了一个比较基本的认识.但是,长江口特别是在南支及南北港的盐度变化规律极其复杂,主要有盐度的周日变化峰值与潮流变化关系不尽协调,落潮时盐度反而最大;盐度的纵向分布上游比下游高;盐度的半月变化峰值一般发生在小潮和寻常潮期间,而且各测点盐度峰值的发生时间不尽一致[1,2]等等.其中北支盐水向南支倒灌是引起长江口盐度变化异常复杂的主要原因[1-5].北支倒灌在长江口盐度变化中扮演了重要的角色,掌握北支倒灌是认识长江口盐水入侵规律特别是南支和南北港盐度变化规律的重要内容,同时也是长江口淡水咨源利用的一个重要方面.     

Correlation analysis and partial least square modeling to quantify typical minerals with Chang＇E-3 visible and near-infrared imaging spectrometer＇s ground validation data

In 2013, Chang＇E-3 program will develop lunar mineral resources in-situ detection. A Visible and Near-infrared Imaging Spectrometer （VNIS） has been selected as one payload of CE-3 lunar rover to achieve this goal. It is critical and urgent to evaluate VNIS＇ spectrum data quality and validate quantification methods for mineral composition before its launch. Ground validation experiment of VNIS was carried out to complete the two goals, by simulating CE-3 lunar rover＇s detection environment on lunar surface in the laboratory. Based on the hyperspectral reflectance data derived, Correlation Analysis and Partial Least Square （CA-PLS） algorithm is applied to predict abundance of four lunar typical minerals （pyroxene, plagioclase, ilmenite and olivine） in their mixture. We firstly selected a set of VNIS＇ spectral parameters which highly correlated with minerals＇ abundance by correlation analysis （CA）, and then stepwise regression method was used to find out spectral parameters which make the largest contri- butions to the mineral contents. At last, functions were derived to link minerals＇ abundance and spectral parameters by partial least square （PLS） algorithm. Not considering the effect of maturity, agglutinate and Fe~, we found that there are wonderful correlations between these four minerals and VNIS＇ spectral parameters, e.g. the abundance of pyroxene correlates positively with the mixture＇s absorption depth, the value of absorption depth added as the in- creasing of pyroxene＇s abundance. But the abundance of plagioclase correlates negatively with the spectral parame- ters of band ratio, the value of band ratio would decrease when the abundance of plagioclase increased. Similar to plagioclase, the abundance of ilmenite and olivine has a negative correlation with the mixture＇s reflectance data, if the abundance of ilmenite or olivine increase, the reflectance values of the mixture will decrease. Through model validation, better estimates of pyroxene, plagioclase and ilmenite＇s abundances are given. It is concluded that VNIS has the capability to be applied on lunar minerals＇ identification, and CA-PLS algorithm has the potential to be used on lunar surface＇s in-situ detection for minerals＇ abundance prediction.     

节理峰值后归一化位移软化模型

切向荷载作用下贯通节理岩体峰值强度后的剪切应力、位移变形规律一般呈双曲线形式发展,即峰值后强度衰减速率逐步变小而趋于0,到达残余强度。直剪试验表明,非贯通节理岩体峰值后剪切应力、位移呈“S”型趋势发展,即强度衰减速率先是逐步增大,到达一定程度后逐步减少,最后趋于稳定达到残余强度值。贯通节理岩体峰值强度后的本构关系并不适合于描述该特征。提出一个新的非线性归一化位移软化本构模型,通过归一化剪切应力R与归一化剪切位移D的指数函数关系体现峰值后剪切应力、位移的发展趋势,即模型采用无量纲表达式。归一化剪切应力R是峰值后强度降? p-? 与峰值强度、残余强度差值? p-? r的比值;归一化位移D是峰值后剪切位移、峰值位移差值? -? p与残余位移、峰值位移差值? r -? p的比值。对含不同起伏角的非贯通节理岩体在常法向荷载条件下的直剪试验数据进行拟合分析,模型预测结果与实测值具有相当高的吻合度,验证了模型的正确性     

基于DSC模型的房屋开裂评估与监测分析

城市隧道下穿时,普遍存在着地表房屋变形超限、倾斜开裂等安全风险问题,而且当前针对房屋变形开裂的计算分析、风险评估研究,也严重滞后于实际工程的需要。通过综合分析、比选,以及单、三轴试验验证表明：DSC（disturbed state concept）本构模型能够较好地描述材料开裂后力学行为;采用该模型并结合厦门机场路隧道下穿建筑群的工程实践,对地表建筑群开裂进行定量评估,评估结果与现场房屋裂缝监测、变形监测结果一致性良好。同时,对照扰动变量与实际房屋开裂的对应关系,发现扰动变量可以作为房屋开裂的定量安全指标,进一步即可以建立房屋变形开裂的过程控制标准,从而使隧道下穿过程中每个关键施工部、每个时段,地表房屋变形开裂程度、开裂风险都可以进行量化评估。