Bayes分析中基于充分性测度的多源验前信息融合

针对工程实践中遇到的验前信息的多源性特点 ,给出了一种基于充分性测度的多源验前分布的融合方法 ,通过综合利用多源验前信息 ,给出了一种较为合理的融合验前分布 ,在此基础上即可进一步进行各种可靠性分析 .最后通过仿真实例证明了该方法的有效性     

基于证据理论的可靠性信息融合方法研究

在对大型客机、导弹、卫星等复杂系统进行可靠性评估时,由于可靠性试验代价昂贵且周期太长,导致可靠性现场试验数据很少,需要充分合理地利用各种来源和各种类型的验前信息,如专家经验、相关型号产品的试验信息及来自不同的试验环境和阶段的信息等,为提高可靠性和置信度的精度,运用Bayes小子样统计推断方法.但Bayes方法应用的一个关键问题就是验前分布的获取和表示问题,提出了利用修正证据组合规则融合多源验前信息的方法,并在融合验前分布的基础上对二项分布产品的可靠性进行了综合评估,并进行仿真,实例表明方法在工程实际中有效果,还可推广应用于其它分布类型的产品的可靠性评估.     

捷联惯组验前分布随机加权分散融合估计

在小子样理论中,验前分布的获取与表示是一个关键问题.获取验前分布必须利用各种验前信息,而这些信息是在不同实验条件下得到的,针对同一对象可能获取多种验前信息,如何合理地利用这些验前信息给出验前分布,这样就出现了多源验前信息融合的问题.针对捷联惯性测量组合(捷联惯组)历次测试数据验前分布的获取问题,讨论了在异总体情况下,多种验前信息的融合问题.提出了通过随机加权分散融合法来实现多种异源信息融合,获取捷联惯组历次测试数据验前分布,从而减小了小样本情况下的统计分析误差.通过实例检验取得了良好的效果.     

基于ML-Ⅱ原理的多源验前信息融合方法研究

在Bayes小子样理论中,验前分布的获取和表示是一个关键问题.针对反舰导弹靶场试验中遇到的验前信息的多源性,给出了一种基于第二类极大似然估计原理（ML-Ⅱ）的多源异总体验前分布的融合方法,并通过仿真实例证明了该方法的有效性.     

水中兵器一体化试验总体设计探讨

一体化试验是一种统筹试验项目、共享试验资源、综合试验信息、提高试验质效的试验鉴定模式;为全面考核水中兵器战术技术指标和作战使用性能,介绍了武器装备试验类型,分析了水中兵器试验面临主要问题,从模式上提出了水中兵器一体化试验需求,从构想上提出了一体化试验总体框架、基本目标和实现思路,从方法上探讨了一体化试验验前分布构建、验前信息相容性检验、验后分布确定和多源信息融合,从要求上提出了一体化试验体制管理和质量管理,为实现水中兵器一体化试验总体设计提供技术途径。     

基于验前试验信息熵的测试性验证试验方案

产品在研制阶段存在大量的试验数据,为有效利用验前数据,降低测试性验证试验样本量,提出一种基于验前试验信息熵的测试性验证试验方案。该方案利用信息熵来度量研制阶段多次验前试验数据对测试性验证试验所起的作用,依据平均互信息熵和信息总量相等的原则,将多次验前试验数据等效成一次成败型数据;在此基础上,通过相容性检验方法确定验前数据与试验数据的相容性水平,并以Beta分布为验前分布,利用加权混合贝叶斯理论建立混合验后分布,之后,基于贝叶斯平均风险理论求解满足双方风险要求的试验方案;最后,以某型雷达发射分机为例,对其进行测试性验证试验研究,研究结果验证了该方案的有效性。     

融合专家经验和寿命试验数据的产品可靠性评估

专家经验是可靠性工程中常见的一类可靠性数据,通过将其与产品的寿命试验数据融合,可以扩充可靠性信息,为产品可靠性的评估提供新的思路.对此,利用Bayes理论,考虑不同类型和不同形式的专家经验,通过验前矩拟合的方法将其转化为产品寿命分布参数的验前分布.进一步,根据寿命试验数据确定似然函数,推断分布参数的验后分布,可求得数据融合后产品的可靠度和剩余寿命等可靠性评估结果.通过蓄电池算例分析,表明所提出方法的应用及其有效性.     

多阶段实验数据融合的Bayes可靠性评定模型

为实现多源先验信息的合理利用,基于多阶段实验数据融合数据方法,建立Bayes可靠性评定分析模型。提出多阶段实验数据融合方法,将各种实验数据进行阶段分类,将第1阶段的实验数据作为最初的先验信息,当获取第2阶段的数据后,按Bayes方法进行信息融合,以得到后验信息,并将其作为下一阶段的先验信息,依次递推,进行多阶段的信息融合。仿真结果表明,该模型简单易行,可有效融合多源先验信息,实现小子样条件下的Bayes可靠性评定。     

基于混合贝叶斯SVM的电价分类与预测

电价的分类与预测是电力市场电价理论研究中的重要内容。该文提出了混合贝叶斯支持向量机方法(BE-SVM),通过贝叶斯统计方法对电价进行分类,挖掘有效的数据信息,并结合支持向量机(SVM)技术预测现货电价数据,贝叶斯前验分布和后验分布用来估计SVM中的参数。通过比较模型BE-SVM、SVM 和神经网络(ANN)的预测结果,表明该文提出的BE-SVM方法提高了电价的预测精度,是一种有效的方法。     

基于随机自适应方法的多传感器融合算法

针对基于熵理论的贝叶斯信息融合技术需要进行无穷区间的积分运算,容易出现数值不稳定的问题,提出一种基于随机自适应方法的多传感器融合算法。利用传感器测量值之间的差值自适应地建立传感器的后验概率分布模型;结合互信息的理论实时识别和剔除伪测量值,避免求熵时的积分计算;将该方法分别应用于集中式融合方案和分布式融合方案中得到了两种新的数据融合方法。仿真实验结果表明,在存在伪测量值的情况下,该算法性能明显优于一般的贝叶斯融合方法。     

A spatially-constrained normalized Gamma process prior

In this work, we propose a novel nonparametric Bayesian method for clustering of data with spatial interdependencies. Specifically, we devise a novel normalized Gamma process, regulated by a simplified (pointwise) Markov random field (Gibbsian) distribution with a countably infinite number of states. As a result of its construction, the proposed model allows for introducing spatial dependencies in the clustering mechanics of the normalized Gamma process, thus yielding a novel nonparametric Bayesian method for spatial data clustering. We derive an efficient truncated variational Bayesian algorithm for model inference. We examine the efficacy of our approach by considering an image segmentation application using a real-world dataset. We show that our approach outperforms related methods from the field of Bayesian nonparametrics, including the infinite hidden Markov random field model, and the Dirichlet process prior.     

贝叶斯学习中基于贝叶斯判别分析的先验分布选取

In this paper we propose an experimental method to choose a prior distribution. Different from many re-searchers, who offered lots of principles that separated from sample information, we consider it a Bayesian discrimina-tion problem combining with the sample information. We introduce the concept of Posterior belief about prior distri-butions. With the well-known Bayes theorem we give out a formula to calculate it and propose a method to discrimi-nate a prior between prior distributions-Highest Posterior Belief (HPB). We also show that under certain condition,the HPB method is identical with the ML-Ⅱ method.     

一种增量贝叶斯分类模型

分类一直是机器学习，模型识别和数据挖掘研究的核心问题，从海量数据中学习分类知识，尤其是当获得大量的带有类别标注的样本代价较高时，增量学习是解决该问题的有效途径，该文将简单贝叶期方法应用于增量分类中，提出了一种增量贝叶斯学习模型，给出了增量贝叶斯推理过程，包括增量地修正分类器参数和增量地分类测试样本，实验结果表明，该算法是可行的和有效。     

基于共轭先验分布的贝叶斯网络分类模型

针对贝叶斯网络后验概率需计算样本边际分布,计算代价大的问题,将共轭先验分布思想引入贝叶斯分类,提出了基于共轭先验分布的贝叶斯网络分类模型.针对非区间离散样本,提出一种自适应的样本离散方法,将小波包提取模拟电路故障特征离散化作为分类模型属性.仿真验证表明,模型分类效果较好,算法运行速度得以提高,也可应用于连续样本和多分类的情况,扩展了贝叶斯网络分类的应用范围.     

Designing Bayesian Two-Sided Group Chain Sampling Plan for Gamma Prior Distribution

Acceptance sampling is used to decide either the whole lot will be accepted or rejected, based on inspection of randomly sampled items from the same lot. As an alternative to traditional sampling plans, it is possible to use Bayesian approaches using previous knowledge on process variation. This study presents a Bayesian two-sided group chain sampling plan (BTSGChSP) by using various combinations of design parameters. In BTSGChSP, inspection is based on preceding as well as succeeding lots. Poisson function is used to derive the probability of lot acceptance based on defective and non-defective products. Gamma distribution is considered as a suitable prior for Poisson distribution. Four quality regions are found, namely: (i) quality decision region (QDR), (ii) probabilistic quality region (PQR), (iii) limiting quality region (LQR) and (iv) indifference quality region (IQR). Producer’s risk and consumer’s risk are considered to estimate the quality regions, where acceptable quality level (AQL) is associated with producer’s risk and limiting quality level (LQL) is associated with consumer’s risk. Moreover, AQL and LQL are used in the selection of design parameters for BTSGChSP. The values based on all possible combinations of design parameters for BTSGChSP are presented and inflection points’ values are found. The finding exposes that BTSGChSP is a better substitute for the existing plan for industrial practitioners.     

Bayesian analysis of Birnbaum-Saunders distribution with partial information

In Bayesian analysis with objective priors, it should be justified that the posterior distribution is proper. In this paper, we show that the reference prior (or independent Jeffreys prior) of a two-parameter Birnbaum-Saunders distribution will result in an improper posterior distribution. However, the posterior distributions are proper based on the reference priors with partial information (RPPI). Based on censored samples, slice sampling is utilized to obtain the Bayesian estimators based on RPPI. Monte Carlo simulations are used to compare the efficiencies of different RPPIs, to assess the sensitivity of the choice of the priors, and to compare the Bayesian estimators with the maximum likelihood estimators, for various scales of sample size and degree of censoring. A real data set is analyzed for illustrative purpose.     

Alternative prior assumptions for improving the performance of naïve Bayesian classifiers

The prior distribution of an attribute in a naïve Bayesian classifier is typically assumed to be a Dirichlet distribution, and this is called the Dirichlet assumption. The variables in a Dirichlet random vector can never be positively correlated and must have the same confidence level as measured by normalized variance. Both the generalized Dirichlet and the Liouville distributions include the Dirichlet distribution as a special case. These two multivariate distributions, also defined on the unit simplex, are employed to investigate the impact of the Dirichlet assumption in naïve Bayesian classifiers. We propose methods to construct appropriate generalized Dirichlet and Liouville priors for naïve Bayesian classifiers. Our experimental results on 18 data sets reveal that the generalized Dirichlet distribution has the best performance among the three distribution families. Not only is the Dirichlet assumption inappropriate, but also forcing the variables in a prior to be all positively correlated can deteriorate the performance of the naïve Bayesian classifier.     

后向散射系数的贝叶斯估计

后向散射系数是合成孔径雷达图像中重要的物理参数.由于合成孔径雷达测量系统的噪声干扰和其他不确定因素影响使得测量数据往往不够精确,这就需要对测量数据进行合理估计.为了对后向散射系数做出准确合理的估计,文章将后向散射系数的先验知识考虑进去,给出了后向散射系数的三种贝叶斯估计算法.贝叶斯估计的关键是概率密度模型的选取.例中选用贝塔(Beta)分布作为先验概率密度模型,伽玛(Gamma)分布作为条件概率密度模型得到了合理的估计结果,并与最大似然估计(ML)算法进行了比较,比较结果表明在对后向散射系数的估计中,贝叶斯估计算法要明显优于最大似然估计算法.     

Bayesian revision of the individual pair-wise comparison matrices under consensus in AHP–GDM

Analytic hierarchy process (AHP) has been widely used in group decision making (GDM). There are two traditional aggregation methods for the synthesis of group priorities in AHP–GDM: aggregation of the individual judgments (AIJ) and aggregation of the individual priorities (AIP). However, AIJ and AIP may be less reliable because of inconsistency of the individual pair-wise comparison matrices (PCMs) and deviation among decision makers. Based on multiplicative AHP model with lognormal errors, we propose a Bayesian revision method for improving the individual PCMs under the assumption that the consensus exists among decision makers, which is considered an aid to AIJ and AIP. In order to effectively deal with decision making involving multiple actors when using AHP as the methodological support, we revise the individual PCMs using the Bayesian revision method before using AIJ and AIP for the synthesis of group priorities. The Bayesian revision method not only makes full use of the prior distribution for parameters and sample information while complying with the Pareto principal of social choice theory, but also provides the reliable individual Bayesian PCMs for AIJ and AIP. Finally two numerical examples are examined to illustrate the applications and advantages of the Bayesian revision method.