检索结果-内蒙古大学图书馆

Use of the 50-g glucose challenge test to predict excess delivery weight

INTERNATIONAL JOURNAL OF GYNECOLOGY & OBSTETRICS 2018年第1期142卷 61-65页

作者： Beksac, M. Sinan Tanacan, Atakan Hakli, Duygu A. Ozyuncu, Ozgur Hacettepe Univ Div Perinatol Dept Obstet & Gynecol Med Fac Ankara Turkey Hacettepe Univ Med Fac Dept Biostat Ankara Turkey

Objective: To identify a cut-off value for the 50-g glucose challenge test (GCT) that predicts excess delivery weight. Methods: A retrospective study was conducted among pregnant women who undertook a 50-g GCT at Hacettepe University Hospital, Ankara, Turkey, between January 1, 2000, and December 31, 2016. Patients with singleton pregnancies who delivered live neonates after 28 weeks of pregnancy were included. Patients were classified according to their 50-g GCT values into group 1 (<7.770 mmol/L);group 2 (7.770 to <8.880 mmol/L, group 3 (8.880-9.990 mmol/L);or group 4 (>9.990 mmol/L). classification and regression tree data mining was performed to identify the 50-g GCT cut-off value corresponding to a substantial increase in delivery weight., Results: Median delivery weight were 3100 g in group 1 (n=352), 3200 g in group 2 (n=165), 3720 gin group 3 (n=47), and 3865 gin group 4 (n=20). Gravidity, 50-g GCT value, and pregnancy duration at delivery explained 30.6% of the observed variance in delivery weight. The cut-off required for maternal blood glucose level to predict excessive delivery weight was 8.741 mmol/L. Conclusion: The 50-g GCT can be used to identify women at risk of delivering offspring with excessive delivery weight.

关键词： 50-g glucose challenge test classification and regression tree Cut-off value Excess birthweight Gestational diabetes mellitus Pregnancy Screening

来源：评论

学校读者我要写书评

暂无评论

Functionality between the size and indicators of smart cities: A research challenge with policy implications

引用

CITIES 2018年 78卷 17-26页

作者： Borsekova, Kamila Korony, Samuel Vanova, Anna Vitalisova, Katarina Matej Bel Univ Fac Econ Res & Innovat Ctr Banska Bystrica Slovakia Matej Bel Univ Fac Econ Dept Publ Econ & Reg Dev Banska Bystrica Slovakia

The paper focusses on the concept of a smart city and its specific components in relation to size of the city. Smart cities are a topic whose key importance is being increasingly recognised across both academic disciplines and urban planning. The idea of a smart city is a dream of urban planners all over the world, and a subject of many research and business initiatives as well as policy debates. As cities vary considerably in size, it is important to ask if the size influences the level of selected indicators of smart cities. Our main presumption is that the development level of indicators of smart cities varies in cities of different size. Our scientific objective is to find a simple understandable model linking the categorical variable "city size" to a group of smart city indicators. Our data set contains 26 smart city indicators for 158 European smart cities, divided into two sizes: medium-sized cities and larger cities. We draw from the methodology of "European Smart Cities" elaborated by the Vienna University of Technology (Project ID: 314704) that classify European smart cities and smart city indicators by considering their size. Analysing the statistics by using decision tree modelling, we identify the most significant indicators of smart cities that can divide smart cities into size categories with impressive 96.2% correct classification. Besides excellent classification result based on real empirical data, several research results overturn common assumptions about smart cities. Based on the research results the paper also highlights intriguing future challenges in smart city research and policy development. Several research results have policy implications and might be useful for urban planners, policy representatives and decision makers.

关键词： Smart city Medium-sized cities Larger cities Ecological awareness classification and regression tree Decision tree

来源：评论

学校读者我要写书评

暂无评论

Development and validation of a Brief Diet Quality Assessment Tool in the French-speaking adults from Quebec

引用

INTERNATIONAL JOURNAL OF BEHAVIORAL NUTRITION AND PHYSICAL ACTIVITY 2019年第1期16卷 61-61页

作者： Lafreniere, J. Harrison, S. Laurin, D. Brisson, C. Talbot, D. Couture, P. Lemieux, S. Lamarche, B. Laval Univ Inst Nutr & Funct Foods Quebec City PQ Canada Laval Univ Sch Nutr Quebec City PQ Canada Laval Univ CHU Quebec Res Ctr Populat Hlth & Optimal Hlth Practices Res Unit Quebec City PQ Canada Laval Univ Fac Pharm Quebec City PQ Canada Laval Univ Fac Med Dept Social & Prevent Med Quebec City PQ Canada Laval Univ CHU Quebec Ctr Rech Endocrinol & Nephrol Unit Quebec City PQ Canada

Background The objective of this study was to develop and validate a short, self-administered questionnaire to assess diet quality in clinical settings, using the Alternative Healthy Eating Index (AHEI) as reference. Methods A total of 1040 men and women (aged 44.6 +/- 14.4 y) completed a validated web-based food frequency questionnaire (webFFQ) and had their height and weight measured (development sample). Participants were categorized arbitrarily according to diet quality (high: AHEI score >= 65/110, low: AHEI score < 65/110) based on dietary intake data from the webFFQ. The Brief Diet Quality Assessment Tool was developed using a classification and regression tree (CART) approach and individual answers to the webFFQ among participants considered to have a plausible energy intake (ratio of reported energy intake to basal metabolic rate >= 1.2 and < 2.4;n = 1040). A second sample of 3344 older adults (aged 66.5 +/- 6.4 y) was used to test the external validity of the Brief Diet Quality Assessment Tool (external validation sample). Results The decision tree included sequences of 3 to 6 binary questions, yielding 21 different pathways classifying diet quality as being high or low. In the development sample, the area under the receiver operating characteristic (ROC) curve of the predictive model was 0.92, with sensitivity, specificity and agreement values of 89.5, 83.9 and 87.2%. Compared with individuals having a low-quality diet according to the Brief Diet Quality Assessment Tool (mean AHEI 56.7 +/- 11.4), individuals classified as having a high-quality diet (mean AHEI 71.3 +/- 11.0) were significantly older, and had lower BMI, percent body fat and waist circumference, and had lower blood pressure, triglycerides, cholesterol/HDL ratio and fasting insulin as well as higher HDL-cholesterol concentrations (all P < 0.05). Similar results were observed in the external validation sample, although overall performance of the Brief Diet Quality Assessment Tool was slightly l

关键词： Diet quality classification and regression tree Alternative healthy eating index Brief diet quality assessment tool

来源：评论

学校读者我要写书评

暂无评论

Researches on Inverting Forest Biomass by Integrated Models Based on SAR Backscattering Coefficient

Researches on Inverting Forest Biomass by Integrated Models ...

引用

作者： Ling HAN Yizheng WEI Kun WANG Heng ZHANG School of Geology Engineering and Geomatics Chang'an University State Key Laboratory of Geo-Information Engineering

The backscattering coefficient of synthetic aperture radar（SAR for short） is used to measure the interaction between the radar incident electromagnetic wave and the ground *** has a wide range of applications and outstanding performance on recognizing the ground objects and retrieving the land surface parameters;Forest has a significant effects in sustainable development,and the forest biomass generally refers to above ground biomass（AGB for short）,which is an essential indicator to measure the forest ecological *** this thesis,according to sentinel-1 A data and frequently-used machine-learning algorithms,it probes into the application of integrated model on forest AGB inversion in view of SAR backscattering ***,three common machine-learning regression models are built up as K-nearest neighbor（KNN for short）,classification and regression tree（CART for short） as well as random forest（RF for short）;next,in accordance with the stacking pattern of bagging ideology,it assembles the three regression models into four various integrated models as A（KNN and CART）,B（KNN and RF）,C（CART and KNN） and D（KNN,CART and RF）;finally,regression and result analyses of the forest AGB are conducted on the basis of established integrated *** conclusion:（1）.The integrated model possesses favorable performance and potential in forest AGB *** integrated models in the research area all possess relatively good fitting *** worst accuracy in training data:R=0.9438,RMSE=0.3278,MAE=0.2609,while the worst accuracy in testing data:R=0.7690、RMSE=0.5339、MAE=0.4574;（2）.In the process of integration,both the quantity and category of member models may influence the ultimate fitting *** fitting accuracy in testing data:D>C>B>A,but that in training data:B>D>A>C.

关键词： Forest AGB Backscattering coefficient K-nearest neighbors classification and regression tree Random forest Integrated model

来源：评论

学校读者我要写书评

暂无评论

An actuarial investigation into maternal hospital cost risk factors for public patients

引用

ANNALS OF ACTUARIAL SCIENCE 2018年第1期12卷 106-129页

作者： William, Jananie Martin, Michael A. Chojenta, Catherine Loxton, Deborah Australian Natl Univ Res Sch Finance Actuarial Studies & Stat Canberra ACT 0200 Australia Univ Newcastle Res Ctr Generat Hlth & Ageing Newcastle NSW Australia

We investigate an actuarial approach to identifying the factors impacting government-funded maternal hospital costs in Australia, with a focus on women who experience adverse birth outcomes. We propose a two-phase modelling methodology that adopts actuarial methods from typical insurance claim cost modelling and extends to other statistical techniques to account for the large volume of covariates available for modelling. Specifically, classification and regression trees and generalised linear mixed models are employed to analyse a data set that links longitudinal survey and administrative data from a large sample of women. The results show that adverse births are a statistically significant risk factor affecting maternal hospital costs in the antenatal and delivery periods. Other significant cost risk factors in the delivery period include mode of delivery, private health insurance status, diabetes, smoking status, area of residence and onset of labour. We demonstrate the efficacy of using actuarial techniques in non-traditional areas and highlight how the results can be used to inform public policy.

关键词： Generalised linear mixed model classification and regression tree Maternal hospital costs Public health costs Adverse birth outcome

来源：评论

学校读者我要写书评

暂无评论

Use of a Big Data Mining Technique to Extract Relative Importance of Performance Shaping Factors from Event Investigation Reports

Use of a Big Data Mining Technique to Extract Relative Impor...

引用

AHFE International Conference on Human Error, Reliability, Resilience, and Performance

作者： Park, Jinkyun Kim, Yochan Jung, Wondea Korea Atom Energy Res Inst Risk & Environm Safety Res Div 989-111 Daedeok Daero Daejeon 34057 South Korea

ISBN: (纸本)9783319606453;9783319606446

In this study, the relative importance of significant performance shaping factors (PSFs), which is critical for estimating the human error probability (HEP) of a given task environment is extracted from event investigation reports of domestic nuclear power plants (NPPs). Each event was caused by one or more human performance related problems (i.e., human errors), and its investigation report includes detailed information describing why the corresponding event has occurred. Based on 10 event reports, 47,220 data records were identified, which represent the task environment of 11 human errors in terms of significant PSFs. After that, the relative importance of the associated PSFs was analyzed by using a CART (classification and regression tree) method that is one of the representative techniques to scrutinize the characteristics of big data.

关键词： Human reliability analysis Performance shaping factors Event investigation report classification and regression tree Nuclear power plant

来源：评论

学校读者我要写书评

暂无评论

ON treeD GAUSSIAN PROCESSES FOR MODELLING STRUCTURAL DYNAMIC SYSTEMS

ON TREED GAUSSIAN PROCESSES FOR MODELLING STRUCTURAL DYNAMI...

引用

作者： Zhang, Tianwei The University of Sheffield

学位级别：博士

The aim of this PhD project is to develop an approach to particle damper modelling based on Gaussian process regression trees (GPRTs). Developing validated particle damper models is a prerequisite for being able to optimise their performance when applied, for example, in the damping of various components and assemblies for a range of frequencies. The objective of the model is to make a credible prediction of damper behaviour for a given set of design parameters and input excitations. Particle damper modelling may be approached in one of three ways: analytically from first principles; numerically using finite or discrete element methods; or ex- perimentally, with the structure and parameters of a reduced-order model inferred from measured data. This project focuses on the third of these approaches, with low-order, physics-based models being combined with experimental training data. The aim is to both identify the model structure that most accurately captures the behaviour of the damper and to infer the model parameters. The model can then be used to predict damper behaviour for design parameters and excitation conditions that have not been tested experimentally. This is made more challenging by the fact that particle dampers will in general, display nonlinear dynamic behaviour which can lead, for example, to switching behaviour in the observed responses. Gaussian process (GP) regression has emerged as a powerful and adaptable approach for modelling experimental data. The basic GP is, however, best suited to modelling outputs that vary smoothly as a function of input values - something that is em- phatically not the case for switching behaviour. An alternative is to develop a treed model which partitions the input space into regions that display smooth behaviour and to infer a separate GP model within each partition. This project will focus on the application of these approaches to particle damper modelling, including inves- tigation of the contributing statistical te

关键词： Machine Learning Structural Dynamics Structural Health Monitoring Gaussian Processes Decision tree classification and regression tree Particle Damping

来源：评论

学校读者我要写书评

暂无评论

A New Multilevel Cart Algorithm and Its Application in Propensity Score Analysis

A New Multilevel Cart Algorithm and Its Application in Prope...

引用

作者： Lin, Shuqiong Texas A&M University

学位级别：Ph.D., Doctor of Philosophy

The logistic regression model is the most commonly used analysis method for modeling binary data. Unbiased estimation using logistic regressions heavily depends on strong model assumptions which are often violated in reality. The classification and regression tree (CART) algorithm gains its popularity to replace the logistic regression, because CART does not require model assumptions and can model complex relationships automatically. However, only limited studies developed multilevel CART (M-CART) algorithms for modeling multilevel data with binary outcomes. Therefore, in the first study, a new M-CART algorithm was proposed for modeling multilevel data with binary outcomes which combines the multilevel logistic regression (M-logit) and the single-level CART (S-CART) using an expectation-maximization algorithm. This proposed algorithm allows inclusion of covariates at all levels, depends on no model assumptions, and captures interaction and nonlinearity in an automatic way. The performance of the proposed M-CART was compared with M-CART, S-CART, and single-level logistic regression (S-logit) in terms of prediction accuracy. Results from simulation study showed that M-CART lead to higher classification accuracy, sensitivity, specificity and Klecka's tau values than all other three methods. In the second study, the proposed M-CART algorithm was applied in propensity score analysis (PSA) when having multi-site non-randomized control trials (non-RCTs). PSA is the most popular statistical technique that estimates the casual effect of a treatment by eliminating the systematic differences of pre-treatment covariates between individuals who receive treatment and individuals who do not receive treatment. M-logit and S-CART have been applied to estimate propensity scores, while no study has explored the performance of using M-CART for estimation. Thus, in the second study, the performance of the proposed M-CART was compared with M-logit, S-CART, and S-logit in terms of covaria

关键词： Multilevel CART algorithms Propensity Score Analysis classification and regression tree

来源：评论

学校读者我要写书评

暂无评论

A novel dendrochronological approach reveals drivers of carbon sequestration in tree species of riparian forests across spatiotemporal scales

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2017年 574卷 1261-1275页

作者： Rieger, Isaak Kowarik, Ingo Cherubini, Paolo Cierjacks, Arne Tech Univ Berlin Dept Ecol Ecosyst Sci Plant Ecol Rothenburgstr 12 D-12165 Berlin Germany Berlin Brandenburg Inst Adv Biodivers Res BBIB D-14195 Berlin Germany WSL Swiss Fed Inst Forest Snow & Landscape Res Zurcherstr 111 CH-8903 Birmensdorf Switzerland Univ Hamburg Bioctr Klein Flottbek Biodivers Useful Plants Ohnhorststr 18 D-22609 Hamburg Germany

Aboveground carbon (C) sequestration in trees is important in global C dynamics, but reliable techniques for its modeling in highly productive and heterogeneous ecosystems are limited. We applied an extended dendrochronological approach to disentangle the functioning of drivers from the atmosphere (temperature, precipitation), the lithosphere (sedimentation rate), the hydrosphere (groundwater table, river water level fluctuation), the biosphere (tree characteristics), and the anthroposphere (dike construction). Carbon sequestration in aboveground biomass of riparian Quercus robur L and Fraxinus excelsior L was modeled (1) over time using boosted regression tree analysis (BRT) on cross-datable trees characterized by equal annual growth ring patterns and (2) across space using a subsequent classification and regression tree analysis (CART) on cross-datable and not cross-datable trees. While C sequestration of cross-datable Q robur responded to precipitation and temperature, cross-datable F. excelsior also responded to a low Danube river water level. However, CART revealed that C sequestration over time is governed by tree height and parameters that vary over space (magnitude of fluctuation in the groundwater table, vertical distance to mean river water level, and longitudinal distance to upstream end of the study area). Thus, a uniform response to climatic drivers of aboveground C sequestration in Q robur was only detectable in trees of an intermediate height class and in taller trees (>21.8 m) on sites where the groundwater table fluctuated little <= 0.9 m). The detection of climatic drivers and the river water level in F. excelsior depended on sites at lower altitudes above the mean river water level (<= 2.7 m) and along a less dynamic downstream section of the study area. Our approach indicates unexploited opportunities of understanding the interplay of different environmental drivers in aboveground C sequestration. Results may support species-specific and locally

关键词： Boosted regression tree Carbon sequestration classification and regression tree Climate Danube River Dendrochronology

来源：评论

学校读者我要写书评

暂无评论

Survival Analysis with Time-varying Relative Risks: A tree-Based Approach

引用

Methods of Information in Medicine 2018年第2期40卷 141-147页

作者： R. Xu S. Adak

A tree-based method for estimating time-varying effects of baseline patient characteristics on survival is introduced. A Cox-type model for censored survival data is used in which the time-varying relative risks are modelled as piecewise constants. The tree method consists of three steps: 1. Growing the tree, in which a fast algorithm using maximized score statistics is utilized to determine the optimal change points; 2. A pruning algorithm is applied to obtain more parsimonious models; 3. Selection of a final tree, which may be either via bootstrap resampling or based on a measure of explained variation. The piecewise constant model is more suitable for clinical interpretation of the regression parameters than the more continuously time-varying models (spline, loess, etc.) that have been proposed previously.

关键词： Change Point classification and regression tree Maximized Score Test Non proportional Hazards Time varying regression Effect

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：