检索结果-南通市图书馆

Flood susceptibility modelling using advanced ensemble machine learning models

在线全文

学校读者我要写书评

暂无评论

Geoscience Frontiers 2021年第3期12卷 60-77页

作者： Abu Reza Md Towfiqul Islam Swapan Talukdar Susanta Mahato Sonali Kundu Kutub Uddin Eibek Quoc bao Pham Alban Kuriqi Nguyen Thi Thuy Linh Department of Disaster Management Begum Rokeya UniversityRangpurBangladesh Department of Geography University of Gour BangaMaldaWest BengalIndia Environmental Quality Atmospheric Science and Climate Change Research GroupTon Duc Thang UniversityHo Chi Minh CityVietnam Faculty of Environment and Labour Safety Ton Duc Thang UniversityHo Chi Minh CityVietnam CERIS Instituto Superior TécnicoUniversidade de LisboaLisbonPortugal Institute of Research and Development Duy Tan UniversityDanang 550000Vietnam Faculty of Environmental and Chemical Engineering Duy Tan UniversityDanang 550000Vietnam

Floods are one of nature's most destructive disasters because of the immense damage to land,buildings,and human *** is difficult to forecast the areas that are vulnerable to flash flooding due to the dynamic and complex nature of the flash ***,earlier identification of flash flood susceptible sites can be performed using advanced machine learning models for managing flood *** this study,we applied and assessed two new hybrid ensemble models,namely Dagging and Random Subspace(RS)coupled with Artificial Neural Network(ann),Random Forest(RF),and Support Vector Machine(SVM)which are the other three state-of-the-art machine learning models for modelling flood susceptibility maps at the Teesta River basin,the northern region of *** application of these models includes twelve flood influencing factors with 413 current and former flooding points,which were transferred in a GIS *** information gain ratio,the multicollinearity diagnostics tests were employed to determine the association between the occurrences and flood influential *** the validation and the comparison of these models,for the ability to predict the statistical appraisal measures such as Freidman,Wilcoxon signed-rank,and t-paired tests and Receiver Operating Characteristic Curve(ROC)were *** value of the Area Under the Curve(AUC)of ROC was above 0.80 for all *** flood susceptibility modelling,the Dagging model performs superior,followed by RF,the ann,the SVM,and the RS,then the several benchmark *** approach and solution-oriented outcomes outlined in this paper will assist state and local authorities as well as policy makers in reducing flood-related threats and will also assist in the implementation of effective mitigation strategies to mitigate future damage.

关键词： Flood hazard Flood vulnerability Flash floods Debris flow Teesta River basin Bangladesh

Transforming Health Care Through a Learning Health System Approach in the Digital Era:Chronic Kidney Disease Management in China

在线全文

学校读者我要写书评

暂无评论

Health Data Science 2023年第1期3卷 160-162页

作者： Guilan Kong Jinwei Wang Hongbo Lin Beiyan bao Charles P.Friedman Luxia Zhang National Institute of Health Data Science Peking UniversityBeijingChina. Advanced Institute of Information Technology Peking UniversityHangzhouZhejiangChina. Renal Division Department of MedicinePeking University First HospitalBeijingChina. Yinzhou District Center for Disease Control and Prevention NingboZhejiangChina. Ningbo Urology and Nephrology Hospital NingboZhejiangChina. Department of Learning Health Sciences University of MichiganAnn ArborMIUSA.

Introduction The last 30 years have witnessed the development of evidencebased *** helps to achieve best practice by incorporating best available evidence into everyday ***,best evidence is generated through clinical studies such as randomized clinical trials(RCTs)and synthesized by systematic review and *** to evidence generation,fewer activities are taken to promote evidence uptake in *** is a long time lag between evidence and practice,and it may take up to 17 years[1].To close the gap,the concept of learning health system(LHS)was proposed in a roundtable on evidence-based medicine by the Institute of Medicine(IOM)in 2006,which provides a way to leverage data to learn knowledge and to feed it back to the frontline practice in real time[2].

关键词： everyday such Kidney

Affinity peptide developed by phage display selection for targeting gastric cancer

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Gastroenterology 2012年第17期18卷 2053-2060页

作者： Wen-Jie Zhang Yan-Xia Sui Arun Budha Jian-bao Zheng Xue-Jun Sun Ying-Chun Hou Thomas D Wang Shao-Ying Lu Department of General Surgery The First Affiliated Hospital of Medical School Xian JiaotongUniversity Xi＇an 710061 Shaanxi Province China The Third Hospital of Chengdu Chengdu610031 Sichuan Province China Shaanxi Normal University Xi＇an 710061Shaanxi Province China Department of Medicine Division of Gastroenterology and Hepatology School of Medicine Universityof Michigan Ann Arbor MI 48109 United States

AIM:To develop an affinity peptide that binds to gastric cancer used for the detection of early gastric ***:A peptide screen was performed by biopanning the PhD-12 phage display library,clearing non-specific binders against tumor-adjacent normal appearing gastric mucosa and obtaining selective binding against freshly harvested gastric cancer *** binding of selected peptides was confirmed by bound phage counts,enzyme-linked immunosorbent assay,competitive inhibition,fluorescence microscopy and semi-quantitative analysis on immunohistochemistry using different types of cancer ***:Approximately 92.8% of the non-specific phage clones were subtracted from the original phage library after two rounds of biopanning against normal-appearing gastric *** the third round of positive screening,the peptide sequence AADNAKTKSFPV(AAD) appeared in 25%(12/48) of the analyzed *** the control peptide,these values were 6.8 ± 2.3,5.1 ± 1.7,3.5 ± 2.1,4.6 ± 1.9 and 1.1 ± 0.5,*** values for AAD peptide were statistically signif icant(P < 0.01) for gastric cancer as compared with other histological classif ications and control ***:A novel peptide is discovered to have a specific binding activity to gastric cancer,and can be used to distinguish neoplastic from normal gastric mucosa,demonstrating the potential for early cancer detection on endoscopy.

关键词： Gastric cancer Peptide Phage library Molecular imaging Early detection Immunohistochemistry Enzyme-linked immunosorbent assay

Monitoring the little fire ant,Wasmannia auropunctata(Roger 1863),in the early stage of its invasion in China:Predicting its geographical distribution pattern under climate change

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

农业科学学报:英文版 2023年第9期22卷 2783-2795页

作者： ZHAO Hao-xiang XIAN Xiao-qing GUO Jian-yang YANG Nian-wan ZHANG Yan-ping CHEN bao-xiong HUANG Hong-kun LIU Wan-xue State Key Laboratory for Biology of Plant Diseases and Insect Pests Institute of Plant ProtectionChinese Academy of Agricultural ScienceBeijing 100193P.R.China Western Agricultural Research Center Chinese Academy of Agricultural SciencesChangji 831100P.R.China Rural Energy and Environment Agency Ministry of Agriculture and Rural AffairsBeijing 100193P.R.China

Invasive alien ants(IAAs)are among the most aggressive,competitive,and widespread invasive alien species(IAS)*** auropunctata,the greatest IAAs threat in the Pacific region and listed in“100 of the world’s worst IAS”,has established itself in many countries and on islands *** populations of *** were recently reported in southeastern China,representing a tremendous potential threat to China’s agricultural,economic,environmental,public health,and social *** the potential geographical distribution(PGD)of *** in China can illustrate areas that may potentially face invasion ***,based on the global distribution records of *** and bioclimatic variables,we predicted the geographical distribution pattern of *** in China under the effects of climate change using an ensemble model(EM).Our findings showed that artificial neural network(ann),flexible discriminant analysis(FDA),gradient boosting model(GBM),Random Forest(RF)were more accurate than categorical regression tree analysis(CTA),generalized linear model(GLM),maximum entropy model(MaxEnt)and surface distance envelope(SRE).The mean TSS values of ann,FDA,GBM,and RF were 0.820,0.810,0.843,and 0.857,respectively,and the mean AUC values were 0.946,0.954,0.968,and 0.979,*** mean TSS and AUC values of EM were 0.882 and 0.972,respectively,indicating that the prediction results with EM were more reliable than those with the single *** PGD of *** in China is mainly located in southern China under current and future climate *** climate change,the PGD of *** in China will expand to higher-latitude *** annual temperature range(bio7)and mean temperature of the warmest quarter(bio10)were the most significant variables affecting the PGD of *** in *** PGD of *** in China was mainly attributed to temperature variables,such as the annual temperature range(bio7

关键词： invasive alien ants potential geographical distribution Wasmannia auropunctata climate change Ensemble model

在线全文

学校读者我要写书评

暂无评论

基于改进多元宇宙算法的零件平面度测量研究

光电子．激光 2021年第3期32卷 251-256页

作者：熊保玉成都工业职业技术学院装备制造学院四川成都610218

为了提高零件平面度测量结果,采用改进多元宇宙算法。首先建立零件平面度测量模型,设置非线性最优化问题的目标函数;接着基于对数函数对多元宇宙算法虫洞概率调整,调整后的虫洞概率随着迭代次数的增加,物体穿越虫洞的机会增加,从而加速... 详细信息

为了提高零件平面度测量结果,采用改进多元宇宙算法。首先建立零件平面度测量模型,设置非线性最优化问题的目标函数;接着基于对数函数对多元宇宙算法虫洞概率调整,调整后的虫洞概率随着迭代次数的增加,物体穿越虫洞的机会增加,从而加速了宇宙物体的移动,提高了算法的搜索性能;然后基于指数函数对宇宙算法移动步长优化,在迭代初期具有较大值使得宇宙能够以较快速度进行全局探索,迭代后期具有较小值使得宇宙能够慢速进行局部开发,提升算法探索、开发能力;最后给出了算法流程。实例验证结果表明改进多元宇宙算法测量误差平均值为5.212μm,相比LSM、PSO、GA、DE、ann算法分别减少了37.63%、33.61%、27.51%、19.41%、10.17%,测量所需时间为3.282 s,分别减少了36.95%、30.33%、26.11%、18.52%、12.74%,明显优于其它算法,测量效果较好。

关键词：测量平面度多元宇宙虫洞概率移动步长

Human mobility data in the COVID-19 pandemic:characteristics,applications,and challenges

在线全文

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2021年第9期14卷 1126-1147页

作者： Tao Hu Siqin Wang Bing She Mengxi Zhang Xiao Huang Yunhe Cui Jacob Khuri Yaxin Hu Xiaokang Fu Xiaoyue Wang Peixiao Wang Xinyan Zhu Shuming bao Wendy Guan Zhenlong Li Department of Geography Oklahoma State UniversityStillwaterOKUSA Center for Geographic Analysis Harvard UniversityCambridgeMAUSA School of Earth and Environmental Sciences The University of QueenslandSt LuciaAustralia Institute for Social Research University of MichiganAnn ArborMIUSA School of Health Ball State UniversityMuncieINUSA Department of Geosciences University of ArkansasFayettevilleARUSA Department of Geography University of ConnecticutStorrsCTUSA Lake Erie College of Osteopathic Medicine Seton Hill UniversityGreensburgPAUSA School of Resource and Environmental Sciences Wuhan UniversityWuhanPeople’s Republic of China State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan UniversityWuhanPeople’s Republic of China China Data Institute Ann ArborMIUSA Geoinformation and Big Data Research Laboratory Department of GeographyUniversity of South CarolinaColumbiaSCUSA

The COVID-19 pandemic poses unprecedented challenges around the *** studies have applied mobility data to explore spatiotemporal trends over time,investigate associations with other variables,and predict or simulate the spread of *** objective was to provide a comprehensive overview of human mobility open data to guide researchers and policymakers in conducting data-driven evaluations and decision-making for the COVID-19 pandemic and other infectious disease *** summarized the mobility data usage in COVID-19 studies by reviewing recent publications on COVID-19 and human mobility from a data-oriented *** identified three major sources of mobility data:public transit systems,mobile operators,and mobile phone *** approaches have been commonly used to estimate human mobility:public transit-based flow,social activity patterns,index-based mobility data,and social media-derived mobility *** compared mobility datasets’characteristics by assessing data privacy,quality,space–time coverage,high-performance data storage and processing,and *** also present challenges and future directions of using mobility *** review makes a pivotal contribution to understanding the use of and access to human mobility data in the COVID-19 pandemic and future disease outbreaks.

关键词： COVID-19 public health human mobility open data mobile phone mobility index

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

DFB激光器调制特性ann建模与设计

压电与声光 2005年第3期27卷 335-338页

作者：李九生鲍振武天津大学电信学院天津300072

通过研究分布反馈式(DFB)激光器调制特性的速率方程,推导了调制特性的解析表达式,建立了调制特性神经网络(ann)模型,计算机仿真与理论分析的结果相吻合。用此模型对激光器结构进行了仿真设计,得到的结果对激光器的生产设计具有重要的指... 详细信息

通过研究分布反馈式(DFB)激光器调制特性的速率方程,推导了调制特性的解析表达式,建立了调制特性神经网络(ann)模型,计算机仿真与理论分析的结果相吻合。用此模型对激光器结构进行了仿真设计,得到的结果对激光器的生产设计具有重要的指导意义。

关键词：调制特性 DFB激光器 ann 建模解析表达式计算机仿真激光器结构速率方程神经网络仿真设计生产设计反馈式模型

在线全文

学校读者我要写书评

暂无评论

地震记录快速KL滤波的自组织神经网络方法

石油地球物理勘探 2005年第6期40卷 632-636页

作者：刘保童朱光明西安科技大学地质与环境工程系长安大学应用地球物理研究所

在地震数据处理中,常使用KL滤波来消除相干和随机噪声,以提高地震记录的信噪比。常规KL变换一般采用模式向量特征值分解(EVD)和相关的奇异值分解(SVD)等集中式计算方法,但记录道数较多时,计算成本就太高,难以在实际中应用。本文首次... 详细信息

在地震数据处理中,常使用KL滤波来消除相干和随机噪声,以提高地震记录的信噪比。常规KL变换一般采用模式向量特征值分解(EVD)和相关的奇异值分解(SVD)等集中式计算方法,但记录道数较多时,计算成本就太高,难以在实际中应用。本文首次将人工神经网络引入到地震信号的KL滤波中,通过自组织(无监督)学习自适应计算网络连接的权值来得到正交分解的投影向量。通过理论记录的试算,将常规的KL变换方法和本文介绍的方法进行对比,表明两种实现方法所得结果一致,但本文方法在输入记录道数较多时比常规方法速度快,可极大地降低滤波处理的计算成本。这使得KL滤波摆脱了耗时量大的缺点,更具实用性。文章最后给出了对实际资料进行KL滤波的两个算例。

关键词： KL变换地震数据处理神经网络去噪相干噪声信噪比

应用可见/近红外光谱技术快速检测果珍中二氧化钛的含量

在线全文

学校读者我要写书评

暂无评论

光谱学与光谱分析 2010年第1期30卷 74-77页

作者：段敏鲍一丹何勇浙江大学生物系统工程与食品科学学院浙江杭州310029

为了实现快速检测果珍中的二氧化钛含量,提出了应用近红外光谱技术结合化学计量学的快速检测方法。研究采用了320份果珍样本进行光谱特性的检测,其中200个样本用来建模,120个样本进行预测。首先比较了标准正态变量校正(SNV)、变量标准化... 详细信息

为了实现快速检测果珍中的二氧化钛含量,提出了应用近红外光谱技术结合化学计量学的快速检测方法。研究采用了320份果珍样本进行光谱特性的检测,其中200个样本用来建模,120个样本进行预测。首先比较了标准正态变量校正(SNV)、变量标准化(Normalize)、多元散射校正(MSC)等6种不同的数据预处理方法对偏最小二乘法(PLS)建模预测效果的影响。然后将PLS模型与应用主成分(PC)建立的主成分-神经网络校正(PC-ann)模型进行比较。结果表明,MSC预处理的效果最好,PLS模型的最佳主成分数为7,预测值与标准值的相关系数R^2达0.900 8,预测标准误差RMSEP为0.05。PC-ann模型预测值与标准值的R^2为0.868 4,RMSEP为0.04。说明PLS模型比PC-ann模型的预测效果好。同时本研究也说明能够应用可见/近红外技术对二氧化钛进行快速定量测定。

关键词：偏最小二乘法神经网络二氧化钛主成分检测