检索结果-内蒙古大学图书馆

BART WITH TARGETED SMOOTHING: AN ANALYSIS OF PATIENT-SPECIFIC STILLBIRTH RISK

ANNALS OF APPLIED STATISTICS 2020年第1期14卷 28-50页

作者： Starling, Jennifer E. Murray, Jared S. Carvalho, Carlos M. Bukowski, Radek K. Scotty, James G. Univ Texas Austin Dept Stat & Data Sci Austin TX 78712 USA Univ Texas Austin McCombs Sch Business Austin TX 78712 USA Univ Texas Austin Dell Med Sch Dept Womens Hlth Austin TX 78712 USA

This article introduces BART with Targeted Smoothing, or tsBART, a new bayesian tree-based model for nonparametric regression. The goal of tsBART is to introduce smoothness over a single target covariate t while not necessarily requiring smoothness over other covariates x. tsBART is based on the bayesian additive regression trees (BART) model, an ensemble of regression trees. tsBART extends BART by parameterizing each tree's terminal nodes with smooth functions of t rather than independent scalars. Like BART, tsBART captures complex nonlinear relationships and interactions among the predictors. But unlike BART, tsBART guarantees that the response surface will be smooth in the target covariate. This improves interpretability and helps to regularize the estimate. After introducing and benchmarking the tsBART model, we apply it to our motivating example-pregnancy outcomes data from the National Center for Health Statistics. Our aim is to provide patient-specific estimates of stillbirth risk across gestational age (t) and based on maternal and fetal risk factors (x). Obstetricians expect stillbirth risk to vary smoothly over gestational age but not necessarily over other covariates, and tsBART has been designed precisely to reflect this structural knowledge. The results of our analysis show the clear superiority of the tsBART model for quantifying stillbirth risk, thereby providing patients and doctors with better information for managing the risk of fetal mortality. All methods described here are implemented in the R package tsbart.

关键词： bayesian additive regression tree ensemble method Gaussian process regression tree regularization

来源：评论

学校读者我要写书评

暂无评论

Factors influencing neuromuscular responses to gait training with a robotic ankle exoskeleton in cerebral palsy

引用

ASSISTIVE TECHNOLOGY 2023年第6期35卷 463-470页

作者： Conner, Benjamin C. Spomer, Alyssa M. Steele, Katherine M. Lerner, Zachary F. Univ Arizona Coll Med Phoenix Phoenix AZ USA Univ Washington Dept Mech Engn Seattle WA 98195 USA No Arizona Univ Dept Mech Engn 15600 S McConnell DrNAU EGR Bldg 69 Flagstaff AZ 86011 USA

A current limitation in the development of robotic gait training interventions is understanding the factors that predict responses to treatment. The purpose of this study was to explore the application of an interpretable machine learning method, bayesian additive regression trees (BART), to identify factors influencing neuromuscular responses to a resistive ankle exoskeleton in individuals with cerebral palsy (CP). Eight individuals with CP (GMFCS levels I - III, ages 12-18 years) walked with a resistive ankle exoskeleton over seven visits while we measured soleus activation. A BART model was developed using a predictor set of kinematic, device, study, and participant metrics that were hypothesized to influence soleus activation. The model (R-2 = 0.94) found that kinematics had the largest influence on soleus activation, but the magnitude of exoskeleton resistance, amount of gait training practice with the device, and participant-level parameters also had substantial effects. To optimize neuromuscular engagement during exoskeleton training in individuals with CP, our analysis highlights the importance of monitoring the user's kinematic response, in particular, peak stance phase hip flexion and ankle dorsiflexion. We demonstrate the utility of machine learning techniques for enhancing our understanding of robotic gait training outcomes, seeking to improve the efficacy of future interventions.

关键词： bayesian additive regression tree cerebral palsy device engagement exoskeleton neurorehabilitation

来源：评论

学校读者我要写书评

暂无评论

Missing Data Analysis and Soil Compressive Modulus Estimation via bayesian Evolutionary trees 1

引用

19th International Conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Zhang, Wenchao Shi, Peixin Zhou, Xiaoqi Jia, Pengjiao Soochow Univ Suzhou Jiangsu Peoples R China

ISBN: (数字)9789819947522

ISBN: (纸本)9789819947515;9789819947522

Soil compression modulus (Es) is an elemental parameter in geotechnical designs. During Es prediction, missing values in some parameters are inevitable. By analyzing the missing mechanism of the parameters, it is found that some missing values contain important domain knowledge information. A new method for predicting Es with missing values in the parameters is proposed. This method, called BETm, modifies the recursive partitioning scheme during the construction of genetic programming (GP) trees and bayesian additive regression trees (BARTs) to incorporate missing data into partitioning rules. Compared to traditional interpolations or imputations, it can directly mine the domain information of missing values, avoiding the introduction of unnecessary errors and noise that can obscure this information. It can construct higher order feature variables to explore the interactions between parameters through GP and introduces beneficial uncertainty into an ensemble model through BART. To estimate Es, a database of 2955 geotechnical samples from 101 boreholes, including 5 missing input values, is constructed. A comparison is conducted with the hybrid models of interpolation (e.g., imputation using average values, multivariate imputation) and ensemble learning (e.g., random forest, extreme gradient boosting). The result reveals that BETm achieves an R-2 value of 0.978, MAE of 0.045 MPa, and MAPE of 0.318 outperforming other hybrid models. The proposed model introduces variable importance analysis with bayesian uncertainty.

关键词： Compression modulus Missing value Genetic programming bayesian additive regression tree

来源：评论

学校读者我要写书评

暂无评论

Comparison of Machine Learning Methods for Mapping the Stand Characteristics of Temperate Forests Using Multi-Spectral Sentinel-2 Data

引用

REMOTE SENSING 2020年第18期12卷

作者： Ahmadi, Kourosh Kalantar, Bahareh Saeidi, Vahideh Harandi, Elaheh K. G. Janizadeh, Saeid Ueda, Naonori Tarbiat Modares Univ Fac Nat Resources & Marine Sci Dept Forestry Tehran *** Iran RIKEN Ctr Adv Intelligence Project Goal Oriented Technol Res Grp Disaster Resilience Sci Team Tokyo 1030027 Japan Darya Tarsim Consulting Engineers Co Ltd Dept Mapping & Surveying Tehran *** Iran De Anza Coll Business Comp Sci & Appl Technol Div Cupertino CA 95014 USA Tarbiat Modares Univ Dept Watershed Management Engn Coll Nat Resources Tehran 14115111 Iran

The estimation and mapping of forest stand characteristics are vital because this information is necessary for sustainable forest management. The present study considers the use of a bayesian additive regression trees (BART) algorithm as a non-parametric classifier using Sentinel-2A data and topographic variables to estimate the forest stand characteristics, namely the basal area (m(2)/ha), stem volume (m(3)/ha), and stem density (number/ha). These results were compared with those of three other popular machine learning (ML) algorithms, such as generalised linear model (GLM), K-nearest neighbours (KNN), and support vector machine (SVM). A feature selection was done on 28 variables including the multi-spectral bands on Sentinel-2 satellite, related vegetation indices, and ancillary data (elevation, slope, and topographic solar-radiation index derived from digital elevation model (DEM)) and then the most insignificant variables were removed from the datasets by recursive feature elimination (RFE). The study area was a mountainous forest with high biodiversity and an elevation gradient from 26 to 1636 m. An inventory dataset of 1200 sample plots was provided for training and testing the algorithms, and the predictors were fed into the ML models to compute and predict the forest stand characteristics. The accuracies and certainties of the ML models were assessed by their root mean square error (RMSE), mean absolute error (MAE), and R-squared (R-2) values. The results demonstrated that BART generated the best basal area and stem volume predictions, followed by GLM, SVM, and KNN. The best RMSE values for both basal area (8.12 m(2)/ha) and stem volume (29.28 m(3)/ha) estimation were obtained by BART. Thus, the ability of the BART model for forestry application was established. On the other hand, KNN exhibited the highest RMSE values for all stand variable predictions, thereby exhibiting the least accuracy for this specific application. Moreover, the effectiveness of the na

关键词： machine learning remote sensing forest stand characteristics bayesian additive regression tree

来源：评论

学校读者我要写书评

暂无评论

Modeling tree species richness patterns and their environmental drivers across Hyrcanian mountain forests

引用

ECOLOGICAL INFORMATICS 2023年 77卷

作者： Ahmadi, Kourosh Mahmoodi, Shirin Pal, Subodh Chandra Saha, Asish Chowdhuri, Indrajit Kolyaie, Samira Linh, Nguyen Thi Thuy Thai, Van Nam Kumar, Lalit Tarbiat Modares Univ Fac Nat Resources & Marine Sci Dept Forestry Tehran Iran Natl Ctr Genet Resource Educ & Extens Org AREEO Tehran Iran Univ Burdwan Dept Geog Bardhaman W Bengal India Fauna Smart Technol Titangade 13A DK-2200 Copenhagen Denmark Thuyloi Univ 175 Tay Son Hanoi Vietnam HUTECH Univ HUTECH Inst Appl Sci 475ADien Bien PhuWard 25 Ho Chi Minh City Vietnam Univ New England Sch Environm & Rural Sci Armidale NSW 2351 Australia

Perception of the way tree species richness distribution varies along the elevational gradient is necessary for applying conservation strategies in favor of biodiversity hotspots. Hyrcanian Mountain Forests of Iran are among the most biodiverse forests in the world and are inscribed in the United Nations Educational, Scientific, and Cultural Organization (UNESCO) World Heritage List. Here, the bayesian additive regression tree (BART) and Stack-Species Distribution Model (S-SDMs) were used to understand tree diversity patterns of the Hyrcanian Mountain Forests. For all the tree species, we implemented the BART model with nine environmental variables, including six bioclimatic and three topographic variables, to create a habitat suitability map. We used the area under the curve (AUC), True skill statistic (TSS), type I error, and type II error to evaluate the BART model for each tree species. All models were then stacked to estimate tree species richness. Important variables affecting the distribution of tree species in northern Iran were different for each species but, in general, topographic variables such as slope and altitude played a very important role. BART model mapped all the 29 tree species distribution effectively with AUC 0.83-0.98, TSS 0.51-0.92;and low type I and type II errors. A very important point was the high ability of this model to predict species with low presence data. The achievement of this study was identifying the biodiversity hotspots based on the tree distribution pattern along the elevational gradient. We mapped regional richness at 1 km spatial resolution and it was the first effort to predict macroecological patterns in the Hyrcanian forests of Iran. The hotspots were mainly scattered from sea level and areas with 1000 m elevation, which were close to residential areas. In conclusion, these results help forest manager to plan new conservation strategies based on tree richness hotspots.

关键词： Hyrcanian forest bayesian additive regression tree Biodiversity hotspot Elevational distribution Stack species distribution model

来源：评论

学校读者我要写书评

暂无评论

Statistical comparison of additive regression tree methods on ecological grassland data

引用

ECOLOGICAL INFORMATICS 2021年 61卷

作者： Plant, Emily King, Rachel Kath, Jarrod Univ Southern Queensland Fac Hlth Engn & Sci Toowoomba Qld 4350 Australia Univ Southern Queensland Ctr Appl Climate Sci Toowoomba Qld 4350 Australia

additive tree methods are widely used in ecology. To date most ecologists have used boosted regression tree (BRT) methods. However, bayesian additive regression tree (BART) models may offer advantages to ecologists previously unexamined. Here we test whether BART has some benefits over the widely used BRT method. To do this we use two grassland data and 13 hydroclimatic and land use predictor variables. The dataset contained data from a period of drought as well as during a recovery phase after the drought. The response variable was the trend in the Enhanced Vegetation Index (EVI), which is an remotely sensed indicator of grassland degradation and recovery. The settable parameters of both methods (BRT and BART) were varied to compare the performance of each method. BRT and BART models were evaluated using three prediction error statistics;root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R-2). The best models across the two methods were assessed by inspecting the relative importance of predictor variables and the prediction error statistics. BRT and BART models exhibited similar variable selection abilities, but the BART method generated models with similar or more favourable prediction error statistics than the BRT method (BART explained an additional 10.17% to 11.92% of the variation than BRT models). Our results indicate that BARTs may be more effective at modelling ecological data than BRTs. BARTs also had shorter run times, more reasonable defaults in its software implementation, and greater functionality of said software implementation, beyond model building and prediction functions. Ecologists using additive regression approaches may benefit from using BART approaches and we suggest their use alongside more commonly used BRT methods in ecological studies.

关键词： bayesian additive regression tree Boosted regression tree Remote sensing Satellite Grassland Pasture

来源：评论

学校读者我要写书评

暂无评论

TARGETED SMOOTH bayesian CAUSAL FORESTS: AN ANALYSIS OF HETEROGENEOUS TREATMENT EFFECTS FOR SIMULTANEOUS VS. INTERVAL MEDICAL ABORTION REGIMENS OVER GESTATION

引用

ANNALS OF APPLIED STATISTICS 2021年第3期15卷 1194-1219页

作者： Starling, Jennifer E. Murray, Jared S. Lohr, Patricia A. Aiken, Abigail R. A. Carvalho, Carlos M. Scott, James G. Univ Texas Austin Dept Stat & Data Sci Austin TX 78712 USA Univ Texas Austin McCombs Sch Business Austin TX 78712 USA British Pregnancy Advisory Serv London England Univ Texas Austin Lyndon B Johnson Sch Publ Affairs Austin TX 78712 USA

We introduce Targeted Smooth bayesian Causal Forests (tsBCF), a non-parametric bayesian approach for estimating heterogeneous treatment effects which vary smoothly over a single covariate in the observational data setting. The tsBCF method induces smoothness by parameterizing terminal tree nodes with smooth functions and allows for separate regularization of treatment effects vs. prognostic effect of control covariates. Smoothing parameters for prognostic and treatment effects can be chosen to reflect prior knowledge or tuned in a data-dependent way. We use tsBCF to analyze a new clinical protocol for early medical abortion. Our aim is to assess the relative effectiveness of simultaneous vs. interval administration of mifepristone and misoprostol over the first nine weeks of gestation. Our analysis yields important clinical insights into how to best counsel patients seeking early medical abortion, where understanding even small differences in relative effectiveness can yield dramatic returns to public health. The model reflects our expectation that the treatment effect varies smoothly over gestation but not necessarily over other covariates. We demonstrate the performance of the tsBCF method on benchmarking experiments. Software for tsBCF is available at https://***/jestarling/tsbcf/ and in the Supplementary Material (Starling (2020)).

关键词： bayesian additive regression tree causal inference regularization Gaussian process heterogeneous treatment effects

来源：评论

学校读者我要写书评

暂无评论

Predation dynamics of Rhodeus sinensis on Procambarus clarkii larvae: Behavioral patterns and aquatic plant refuge effects in crayfish aquaculture

引用

AQUACULTURE REPORTS 2024年 39卷

作者： Jin, Shiyu Gu, Dangen Zhang, Tanglin Xu, Zhiqiang Xu, Yu Wang, Meng Wang, Qishuo Luo, Yan Qian, Zhen Zhu, Zhengyi Zou, Mengmei Luo, Si Huaiyin Inst Technol Sch Life Sci & Food Engn Jiangsu Prov Key Construct Lab Probiot Preparat Huaian 223003 Peoples R China Chinese Acad Fishery Sci Pearl River Fisheries Res Inst Guangzhou 510380 Peoples R China Chinese Acad Sci State Key Lab Freshwater Ecol & Biotechnol Inst Hydrobiol Wuhan 430072 Peoples R China Freshwater Fisheries Res Inst Jiangsu Prov Nanjing 210017 Peoples R China Guiyang Engn Corp Ltd Power China Guiyang 550081 Peoples R China

Non-target fish are frequently present in crayfish aquaculture systems, yet limited research has explored their predatory impacts on crayfish larvae. To address this gap, three experiments were conducted to examine the predation dynamics of Rhodeus sinensis on Procambarus clarkii larvae, focusing on the effects of predator sizes, group sizes, and aquatic plant refuges. In experiment 1, Cox proportional hazards regression model revealed that P. clarkii larvae (8.40 mm and 11.30 mm) faced heightened predation risks from R. sinensis, particularly when the predator's weight exceeded 2 g. Predation mortality significantly rose with increasing predator size. P. clarkii larvae primarily sought refuge in bottom corners and under heating rods, as indicated by Self-Organizing Map. Experiment 2, analyzed with bayesian additive regression tree, demonstrated that group predation of R. sinensis significantly enhanced predatory efficiency on larger crayfish larvae, resulting in reduced time to the first attack, increased total number of attacks and extended total attack duration. Experiment 3 disclosed that casualty and mortality rates of crayfish larvae markedly decreased when aquatic plants coverage exceeded 20 %, irrespective of plants types. Under predation pressure, crayfish larvae exhibited a preference for microhabitats on and under aquatic plants, indicating an adaptive behavior in response to predation. These findings underscore the susceptibility of P. clarkii larvae to predation by R. sinensis and suggest maintaining a 20 % aquatic plant coverage as an effective management strategy to mitigate predation risks and support juvenile crayfish survival in aquaculture systems.

关键词： Predator-prey interactions Group predation Refuge effects Cox proportional hazards regression model Self-Organizing Map bayesian additive regression tree

来源：评论

学校读者我要写书评

暂无评论

Assessing the effects of different factors on students' math grade:evidence from ECLS-K dataset

Assessing the effects of different factors on students' math...

引用

作者： Hanxiao Lu Department of Computer Science Columbia University

This study examined the causal effect of the Early Childhood Longitudinal Study,Kindergarten Class of 1998–1999(ECLS-K) program on students' academic achievements in ***,factors heavily impacting students' fifth grade math score are also *** result indicates that the ECLSK program has insignificant negative impact on student's math *** math score,fine motor skill and gender are top three positive factors and child's age at k entry,ECLS training program,attended head start are top three negative *** results provide a framework for educators to help children improve their math score.

关键词： Rubin Causal Model bayesian additive regression tree Machine Learning ECLS-K dataset

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：