检索结果-内蒙古大学图书馆

Modified Hamiltonian Monte Carlo-based Bayesian finite element model updating of steel truss bridge

STRUCTURAL CONTROL & HEALTH MONITORING 2020年第8期27卷 e2556-e2556页

作者： Baisthakur, Shubham Chakraborty, Arunasis Indian Inst Technol Dept Civil Engn Gauhati India

The aim of this study is to develop a Hamiltonian Monte Carlo-based algorithm for finite element model updating in the Bayesian framework. The proposed algorithm uses adaptive prior-based approach, which helps to generate the intermediate pdfs. Numerical analysis is carried out with different coefficient of variations of the prior for model updating. Guidelines for their proper selection procedure are also prescribed in this work. The efficiency of the proposed method is demonstrated using synthetic experiments and actual test data for updating the finite element model of a steel truss bridge. Finally, performance of this algorithm is compared with the standard Markov chain Monte Carlo algorithm to demonstrate its advantages.

关键词： Bayesian inference maximum likelihood metropolis-hasting algorithm model updating modified Hamiltonian Monte Carlo simulation

来源：评论

学校读者我要写书评

暂无评论

On a logistic regression model with random intercept: diagnostic analytics, simulation and biological application

引用

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION 2020年第13期90卷 2354-2383页

作者： Tapia, Alejandra Leiva, Victor Galea, Manuel Werneck, Rachel Univ Catolica Maule Fac Basic Sci Curico Chile Pontificia Univ Catolica Valparaiso Sch Ind Engn Valparaiso Chile Pontificia Univ Catolica Chile Dept Stat Santiago Chile Univ Sao Paulo Inst Biosci Postgrad Program Ecol Sao Paulo Brazil Zool Res Museum Alexander Koenig Bonn Germany

This article proposes a methodology for diagnostics in a logistic regression with random intercept motivated by a biological study. The methodology includes local and global influence techniques allowing us to contrast the results of both types of influence. The proposed methodology is applied to a case study with real data to show its potential. This study corresponds to the reproduction of arachnids reporting how the local and global influence of atypical observations can modify the significance of parameters, and then the biological conclusions. The model fitting is evaluated through predictive indicators. The methodology is summarized in an algorithm and a demo example is implemented inRcode to facilitate its application. To evaluate the performance of the methodology, Monte Carlo simulations are conducted.

来源：评论

学校读者我要写书评

暂无评论

Inferences on Non-Identical Stress and Generalized Augmented Strength Reliability Parameters Under Informative Priors

引用

INTERNATIONAL JOURNAL OF RELIABILITY QUALITY AND SAFETY ENGINEERING 2020年第4期27卷

作者： Chandra, N. Rathaur, V. K. Ramanujan Sch Math Sci Dept Stat Pondicherry 605014 India Manipal Acad Higher Educ Dept Commerce Manipal 576104 Karnataka India

In this paper, an attempt has been made to estimate the augmented strength reliability of a system for the generalized case of Augmentation Strategy Plan (ASP) by assuming that the strength (X) and common stress (Y) are independently but not identically distributed as gamma distribution with parameters (alpha(1), lambda(1)) and (alpha(2), lambda(2)), respectively. ASP deals with two important challenges (i) early failures in a newly manufactured system while first and subsequent use and (ii) frequent failures of used system. ASP has a significant role in enhancing the strength of a weaker (or poor) system for failure-free journey to achieve its mission life. The maximum likelihood (ML) and Bayes estimation of augmented strength reliability are considered. In Bayesian context, the informative types of priors (Gamma and Inverted gamma) are chosen under symmetric and asymmetric loss functions for better comprehension purpose. A comparison between the ML and Bayes estimators of the augmented strength reliability is carried out on the basis of their mean square errors (mse's) and absolute biases by simulating Monte-Carlo samples from posterior distribution through metropolis Hosting approximation. Real life data sets are also considered for illustration purpose.

关键词： Stress-strength reliability augmentation MLE Bayesian estimators MCMC metropolis-hasting algorithm

来源：评论

学校读者我要写书评

暂无评论

Uncertainty analysis of a shape memory alloy model for dynamic analysis

引用

SMART MATERIALS AND STRUCTURES 2021年第2期30卷

作者： Hou, Hetao Li, Jinpeng Chen, Cheng Qiu, Canxing Shandong Univ Sch Civil Engn Jinan 250061 Shandong Peoples R China Shandong Engn & Technol Res Ctr Green Bldg & Inte Jinan 250061 Shandong Peoples R China Zhengzhou City Construct Grp Investment Co Ltd Zhengzhou 450001 Henan Peoples R China San Francisco State Univ Sch Engn San Francisco CA 94132 USA Beijing Univ Technol Minist Educ Key Lab Urban Secur & Disaster Engn Beijing 100124 Peoples R China

Superelastic shape memory alloys (SMAs) are capable of recovering large inelastic deformation and dissipating energy under loading reversals, and therefore present promising application in vibration control of engineering structures subjected to dynamic loads. Properties of SMAs are often optimised based on experimental results and treated as deterministic for dynamic analysis of structures with SMA-based devices. This study applies the metropolis-hasting algorithm to characterise the uncertainties within an SMA material model and to provide insight into its parameter uncertainty. Cyclic tests of SMA bars are first conducted and the experimental data are analysed using the Markov chain Monte Carlo method. The statistical properties of SMA model parameters are calculated based on posterior parameter distributions. The influence of SMA model parameter uncertainty is further explored on energy dissipation capacity under cyclic tests. The first four L-moment method is applied to transform the posterior parameter distributions into standard normal distribution to further evaluate the influence of model parameter uncertainty on energy dissipation in dynamic analysis.

关键词： shape memory alloys superelastic effect cyclic loading uncertainty metropolis-hasting algorithm Markov chain Monte Carlo first four L-moment method

来源：评论

学校读者我要写书评

暂无评论

Bayesian and maximum likelihood estimations from parameters of McDonald Extended Weibull model based on progressive type-II censoring

引用

JOURNAL OF STATISTICAL THEORY AND PRACTICE 2018年第2期12卷 231-254页

作者： Sel, Sanghun Jung, Myoungjin Chung, Younshik Pusan Natl Univ Dept Stat Busan 609735 South Korea

In recent years, there have been many efforts to develop a new statistical distribution with more flexibility that can be fitted well to complex data. In this article we consider the statistical inference of the six-parameter McDonald extended Weibull distribution (McEW) based on the progressively Type-II censored sample. The maximum likelihood estimates (MLEs) of the six parameters and their asymptotic distribution are obtained. Based on the asymptotic distribution, the asymptotic confidence limits of its parameters can be computed. We also propose bootstrap confidence intervals of the parameters. The Bayes estimates and the associated highest posterior density credible intervals are computed using the Markov-chain Monte Carlo (MCMC) method, including the Gibbs sampling technique and metropolis-hastings algorithm. Simulation experiments are performed to compare the proposed methods and the corresponding confidence intervals under the different censoring schemes. Finally, concluding remarks are given.

关键词： Bayesian estimation bootstrap method Gibbs sampler maximum likelihood estimate (MLE) McDonald extended Weibull (McEW) distribution metropolis-hasting algorithm progressive type-II censoring

来源：评论

学校读者我要写书评

暂无评论

Graph_sampler: a simple tool for fully Bayesian analyses of DAG-models

引用

COMPUTATIONAL STATISTICS 2017年第2期32卷 691-716页

作者： Datta, Sagnik Gayraud, Ghislaine Leclerc, Eric Bois, Frederic Y. Univ Technol Compiegne Sorbonne Univ BMBI Bat GICS 60 319 F-60203 Compiegne France Univ Technol Compiegne Sorbonne Univ LMAC Bat GICS 60 319 F-60203 Compiegne France Univ Tokyo LIMMS CNRS IIS UMI 2820 Inst Ind Sci Meguro Ku 4-6-1 Komaba Tokyo 1538505 Japan INERIS DRC VIVA METO Parc ALATA BP2 F-60550 Verneuil En Halatte France

Bayesian networks (BNs) are widely used graphical models usable to draw statistical inference about directed acyclic graphs. We presented here Graph_sampler a fast free C language software for structural inference on BNs. Graph_sampler uses a fully Bayesian approach in which the marginal likelihood of the data and prior information about the network structure are considered. This new software can handle both the continuous as well as discrete data and based on the data type two different models are formulated. The software also provides a wide variety of structure prior which can depict either the global or local properties of the graph structure. Now based on the type of structure prior selected, we considered a wide range of possible values for the prior making it either informative or uninformative. We proposed a new and much faster jumping kernel strategy in the metropolis-hastings algorithm. The source C code distributed is very compact, fast, uses low memory and disk storage. We performed out several analyses based on different simulated data sets and synthetic as well as real networks to discuss the performance of Graph_sampler.

关键词： Bayesian networks Structure learning Posterior distribution MCMC metropolis-hasting algorithm

来源：评论

学校读者我要写书评

暂无评论

Estimation and prediction for Chen distribution with bathtub shape under progressive censoring

引用

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION 2017年第2期87卷 348-366页

作者： Kayal, Tanmay Tripathi, Yogesh Mani Singh, Devendra Pratap Rastogi, Manoj Kumar Indian Inst Technol Patna Dept Math Patna Bihar India Natl Inst Pharmaceut Educ & Res Dept Biostat Hajipur India

We consider estimation of the unknown parameters of Chen distribution [Chen Z. A new two-parameter lifetime distribution with bathtub shape or increasing failure rate function. Statist Probab Lett. 2000;49:155-161] with bathtub shape using progressive-censored samples. We obtain maximum likelihood estimates by making use of an expectation-maximization algorithm. Different Bayes estimates are derived under squared error and balanced squared error loss functions. It is observed that the associated posterior distribution appears in an intractable form. So we have used an approximation method to compute these estimates. A metropolis-hasting algorithm is also proposed and some more approximate Bayes estimates are obtained. Asymptotic confidence interval is constructed using observed Fisher information matrix. Bootstrap intervals are proposed as well. Sample generated from MH algorithm are further used in the construction of HPD intervals. Finally, we have obtained prediction intervals and estimates for future observations in one- and two-sample situations. A numerical study is conducted to compare the performance of proposed methods using simulations. Finally, we analyse real data sets for illustration purposes.

关键词： Bayesian estimation Bayesian prediction bootstrapping EM algorithm Fisherinformation matrix metropolis-hasting algorithm

来源：评论

学校读者我要写书评

暂无评论

Seasonal fluctuations of photosynthetic parameters for light use efficiency models and the impacts on gross primary production estimation

引用

AGRICULTURAL AND FOREST METEOROLOGY 2017年 236卷 22-35页

作者： Lin, Xiaofeng Chen, Baozhang Chen, Jing Zhang, Huifang Sun, Shaobo Xu, Guang Guo, Lifeng Ge, Mengyu Qu, Junfeng Li, Lijuan Kong, Yawen Chinese Acad Sci Inst Geog Sci & Nat Resources Res State Key Lab Resources & Environm Informat Syst 11ADatun Rd Beijing 100101 Peoples R China Univ Chinese Acad Sci 19AYuquan Rd Beijing 100049 Peoples R China China Univ Min & Technol Sch Environm Sci & Spatial Informat Xuzhou 221116 Peoples R China Beijing Meteorol Bur Meteorol Informat Ctr Beijing 44 Zizhuyuan Rd Beijing 100089 Peoples R China China Univ Geosci Fac Earth Sci & Resources Beijing 100083 Peoples R China

How parameterization improves Light-use efficiency (LUE) models by taking into account the seasonal variations of the maximum LUE (epsilon(max)) has been rarely investigated. The LUE models include two categories which are the one-leaf LUE model (SL-LUE) and the two-leaf LUE model (TL-LUE) with separation of sunlit and shaded leaves (epsilon(msu) and epsilon(msh)). In this study, the SL-LUE and TL-LUE models were parameterized for 46 towers (176 site-years data) representing eighteen typical plant functional types (PFTs) by using the metropolis-hasting algorithm at monthly time scales. The results indicate that the maximum LUE parameters varied seasonally for most PFTs having a significant positive linear correlation with leaf area index (LAI) and ambient temperature changes. The relationships of epsilon(msu) and epsilon(msh) with epsilon(max) can be well described by linear equations, indicating the existence of general patterns across biomes. And as expected, The LUE models with the seasonal fluctuations of epsilon(max), epsilon(msu) and epsilon(msh) significantly improved GPP estimation except for needleleaf evergreen forests in mid- and low- latitude regions. The improvements of both the SL-WE and TL-LUE models were most significant in summer for tropical and Mediterranean climate regions, while most evident in spring and winter for temperate and boreal climate regions. Even with seasonal parameters, both the LUE models still cannot well capture GPP dynamics in cold season for some PFTs in Mediterranean and tropical regions (e.g., Tropical-BEF, C3-C4 grass). This study suggests that further improvement of modelling GPP requires taking into account seasonal variations of the key parameters. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Light use efficiency (LUE) models Seasonal variations of maximum LUE parameters Capacity of gross primary production metropolis-hasting algorithm Eddy covariance

来源：评论

学校读者我要写书评

暂无评论

On estimation of augmented strength reliability parameters under non-informative priors: A non-identical case

引用

Model Assisted Statistics and Applications 2017年第2期12卷 137-150页

作者： Chandra, N. Rathaur, V.K. Department of Statistics Ramanujan School of Mathematical Sciences Puducherry 605 014 India

In this article we consider the Bayesian and Maximum Likelihood (ML) estimation of augmented strength of a system for the generalized case of the proposed Augmentation Strategy Plan (ASP). ASP has interesting applications in stress strength reliability. The Bayes estimation is performed by assuming non-informative (uniform and Jeffreys) types of priors under two different loss functions i.e. squared error loss function (SELF) and LINEX loss function (LLF) for better comprehension purpose. It is assumed that the strength (X) and the imposed stress (Y) follow independent and non-identical two parameter gamma distributions. The MCMC simulation techniques are employed to study the comparison between the ML and Bayes estimators of augmented strength reliability on the basis of their mean square errors (mse) and absolute biases. The proposed estimators are validated by Monte Carlo simulated as well as real data sets. © 2017 - IOS Press and the authors. All rights reserved.

关键词： Augmented strength reliability Bayes estimator Gamma distribution Markov chain monte carlo simulation metropolis-hasting algorithm Non-informative prior

来源：评论

学校读者我要写书评

暂无评论

COMPUTER SIMULATION OF MOLECULAR SHAPE TRANSITIONS IN ADSORBED POLYMERS UNDER CONFINEMENT CONDITIONS

COMPUTER SIMULATION OF MOLECULAR SHAPE TRANSITIONS IN ADSORB...

引用

作者： Jessica Elena Harrison Laurentian University

学位级别：硕士

The structural and dynamical properties of polymer-covered surfaces under confinement and crowding effects are key to many applications. Earlier work showed the occurrence of "escape transitions" in small uncompressed clusters (or "islands") even for repulsive polymers. These transitions involve a switch from evenly-compact configurations ("trapped chains"), to uneven compactness ("escaped chains"). Here, we address a complementary question: if the crowding is reduced by having fewer neighbours, can an external compression produce "escaped configurations"? To this end, we focused on the confinement of grafted polymers. At low compression, the inter-chain entanglement increases with excluded volume as chains swell and interpenetrate, up to a critical chain length where the behaviour is reversed. We conclude that, when few chains are present or if a larger ensemble of them is arranged symmetrically, compression induces chain avoidance without inducing escape transitions. The switch in mechanism depends mostly on crowding, and not on the applied pressure.

关键词： Polymer islands Monte Carlo simulations self-avoiding walks radius of excluded volume escape transition chain avoidance entanglement complexity coarse-grained hard-sphere potential Marsaglia algorithm metropolis-hasting algorithm

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：