动态贝叶斯网络一种自适应的局部抽样粒子滤波算法*

针对传统自适应粒子滤波（APF）对于动态贝叶斯网络推理中高维的问题,提出动态贝叶斯网络一种自适应的局部抽样粒子滤波算法(LSAPF)。LSAPF算法将BK算法分团的思想引入到粒子抽样中,利用策略相关性和局部模型的弱交互性为指导对动态贝叶斯网络进行分割,以降低抽样规模和抽样的状态空间;进而对局部模型用自适应粒子滤波算法进行近似推理,并以粒子的因式积形式近似系统的状态信度。实验结果表明,该算法能很好地兼顾推理精度和推理时间,其性能优于普通PF算法;与APF算法相比,在不增加推理误差的情况下推理时间也有较大的提高。     

复杂系统的图模型多智能体协同故障诊断

为解决复杂、不确定系统的故障诊断实时推理问题,提出了基于图模型-多连片贝叶斯网络架构下多智能体协同推理的故障诊断方法。该方法将一个复杂贝叶斯网分割成若干有重叠的贝叶斯子网,使监控网络的单个智能体被抽象为一个拥有局部知识的贝叶斯网,利用成熟的贝叶斯网推理算法可完成智能体的自主推理。随后,通过重叠的子网接口进行多智能体间消息的传播,实现了多智能体协同故障诊断推理。实验结果表明了基于图模型多智能体的协同故障诊断方法的正确性和有效性。     

基于局部解释能力的贝叶斯网络隐藏变量学习

目前,在贝叶斯网络中插入隐藏变量的主要目的是简化贝叶斯网络结构,从而提高推理效率,但隐藏变量使用不当会降低推理的可靠性.本文以提高贝叶斯网络的局部最优解释推理能力为标准插入隐藏变量,并将最优解释、星形结构和Gibbs抽样相结合来确定隐藏变量的位置、取值和维数,因此,通过隐藏变量的引入,在能够提高推理效率的同时,还可改进推理的可靠性.     

支持短时交通流量预测的概率图模型构建与推理

短时交通流量预测,是交通系统信息化和智能化交通运输管理技术领域研究的关键问题.目前的方法对历史数据具有较高的依赖程度,或者具有较高的计算成本,或者不能有效反映实际中较复杂的交通网络及各结点之间的相互关系、以及依赖的不确定性,或者多种模型的组合使得预测方法较复杂.贝叶斯网是一种重要的概率图模型,本文以交通网络结构为基础,利用概率图模型在不确定性知识表示和推理方面的良好性质,考虑路口交通流量及其预测的时序依赖特征,构建了带有时序条件依赖关系的交通贝叶斯网.进而针对短时交通流量预测的实时性和高效性要求,提出了基于Gibbs采样的交通贝叶斯网近似概率推理算法,并进行交通流量的短时预测.实验结果表明,本文提出的交通贝叶斯网构建、近似推理以及相应的短时交通流量的预测方法,具有高效性、准确性和可用性.     

基于结构分析的局部Gibbs抽样自动推理算法

提出一种基于结构分析的局部Gibbs抽样的贝叶斯网络推理算法(S-LGSI).S-LGSI算法基于联合树算法的概率图模型分析思想,对贝叶斯网络进行精确分解,然后根据查询结点和证据结点生成具有强相关性的局部网络模型,进而对局部网络模型进行Gibbs抽样推理.与当前基于抽样的其它近似推理算法相比,该算法降低推理的计算维数.同时,由于局部抽样模型包含了与查询结点相关的重要信息,因此该算法保证局部抽样推理的精度.算法分析和在Alarm网的实验结果表明,S-LGSI算法较显著降低时间复杂度,同时也提高推理精度.S-LGSI算法应用于上海证券交易所股票网络的推理结果与实际情况基本一致,表现出较强的实用性.     

基于AODE和再抽样的软件缺陷预测模型

为了确切地估计软件缺陷分布,提出了基于AODE和再抽样的软件缺陷预测模型。分析了几种常用贝叶斯分类器的优缺点,以及软件缺陷度量元和再抽样方法,设计了多AODE分类器,该分类器是由多个AODE二分类器组成的。在以上基础上,建立了采用多AODE分类器和再抽样方法的软件缺陷预测模型,实验结果表明,该分类器的分类准确度较常用贝叶斯分类器高。通过收集到的缺陷数据样本比较结果表明,该模型比一些常用贝叶斯模型具有更好的预测准确性和稳定性。     

基于Markov毯分解的抽样近似推理算法

现有的贝叶斯推理算法不同程度地存在推理精度低或推理时间长的问题。文中提出一种基于Markov毯分解的抽样近似推理算法(LSIA-MB)。LSIA-MB算法利用HITON_MB算法寻找查询结点的Markov毯, 进而利用动态规划方法学习边的后验概率, 确定变量之间的因果关系, 获得一个关于查询结点的Markov局部网络模型。最后, 在Markov局部模型上执行Gibbs Sampling。通过对Markov局部模型的抽样, 极大降低推理的计算维数。同时, 由于Markov局部网络模型包含与目标结点相关的完整信息, 从而保证局部抽样推理的精度。算法分析和在标准Alarm网的实验结果均表明, LSIA-MB算法降低推理时间, 且提高推理精度。LSIA-MB算法在上海股票交易网络上的推理预测结果显示出较强的实用性。     

贝叶斯算法在网络安全预测中的运用研究

随着网络的普及,对网络攻击也越来越猖獗,成为人们工作、生活和学习的潜在威胁。贝叶斯算法作为搭建预测模型的一种有效方法,以其独特的双向推理能力和坚实的概率统计基础,在网络安全预测研究领域中受到广泛的关注并成为研究热点。该文首先介绍了贝叶斯算法原理及其在络风险安全评估中较传统评估方法的优势,文章接着又介绍了基于贝叶斯算法的网络安全预测系统模型的构建方法,最后文章对贝叶斯算法在网络安全预测中的运用做出了展望。贝叶斯算法作为当前的新兴研究内容,是一个多学科交叉的研究课题,在网络安全预测研究中将有很大的发展空间。     

基于贝叶斯网络的煤与瓦斯突出预测研究

贝叶斯网络是目前不确定知识和推理领域最有效的理论模型之一。为了正确预测煤与瓦斯突出的危险性,提出了一种基于贝叶斯网络的煤与瓦斯突出预测方法。在综合影响煤与瓦斯突出的因素和领域专家知识的基础上建立了网络结构,通过对先验知识和样本数据的学习,实现了煤与瓦斯突出的预测,取得了较好的效果。实验表明,该模型网络学习速度快,准确性高,是一种有效的煤与瓦斯突出危险性预测方法。     

基于改进贝叶斯方法的轨迹预测算法研究

针对传统轨迹预测方法在历史轨迹数目有限时,预测准确度较低的问题,提出一种改进的贝叶斯推理(MBI)方法,MBI构建了马尔可夫模型来量化相邻位置的相关性,并通过对历史轨迹进行分解来获得更准确的马尔可夫模型,最后得到改进的贝叶斯推理公式。实验结果表明,MBI方法比现有方法的预测速度快2到3倍,并且有较高的准确度和稳定性。MBI方法充分利用现有轨迹信息,不仅提高了查询效率,还保证了较高的预测精度。     

Time series prediction using belief network models

We address the problem of generating normative forecasts efficiently from a Bayesian belief network. Forecasts are predictions of future values of domain variables conditioned on current and past values of domain variables. To address the forecasting problem, we have developed a probability forecasting methodology, Dynamic Network Models (DNMs), through a synthesis of belief network models and classical time-series models. The DNM methodology is based on the integration of fundamental methods of Bayesian time-series analysis, with recent additive generalizations of belief network representation and inference techniques.We apply DNMs to the problem of forecasting episodes of apnea, that is, regular intervals of breathing cessation in patients afflicted with sleep apnea. We compare the one-step-ahead forecasts of chest volume, an indicator of apnea, made by autoregressive models, belief networks, and DNMs. We also construct a DNM to analyse the multivariate time series of chest volume, heart rate and oxygen saturation data.     

Application of Bayesian Network Learning Methods to Waste Water Treatment Plants

Bayesian Networks have been proposed as an alternative to rule-based systems in domains with uncertainty. Applications in monitoring and control can benefit from this form of knowledge representation. Following the work of Chong and Walley, we explore the possibilities of Bayesian Networks in the Waste Water Treatment Plants (WWTP) monitoring and control domain. We show the advantages of modelling knowledge in such a domain by means of Bayesian networks, put forth new methods for knowledge acquisition, describe their applications to a real waste water treatment plant and comment on the results. We also show how a Bayesian Network learning environment was used in the process and which characteristics of data in the domain suggested new ways of representing knowledge in network form but with uncertainty representations formalisms other than probability. The results of applying a possibilistic extension of current learning methods are also shown and compared.     

基于贝叶斯网络的学生模型在测试系统的应用研究

在网络课程及虚拟课堂中,在线测试是一个重要组成部分。本文对贝叶斯网络及其概率推理进行了简述,提出了基于贝叶斯网络的学生模型,并将其应用于自适应在线测试系统中。该系统不仅能够因人施测,而且具有预测能力,同时还可以排除学生猜对试题答案的非真实能力。     

A new real-coded stochastic Bayesian optimization algorithm for continuous global optimization

Estimation of distribution algorithms are considered to be a new class of evolutionary algorithms which are applied as an alternative to genetic algorithms. Such algorithms sample the new generation from a probabilistic model of promising solutions. The search space of the optimization problem is improved by such probabilistic models. In the Bayesian optimization algorithm (BOA), the set of promising solutions forms a Bayesian network and the new solutions are sampled from the built Bayesian network. This paper proposes a novel real-coded stochastic BOA for continuous global optimization by utilizing a stochastic Bayesian network. In the proposed algorithm, the new Bayesian network takes advantage of using a stochastic structure (that there is a probability distribution function for each edge in the network) and the new generation is sampled from the stochastic structure. In order to generate a new solution, some new structure, and therefore a new Bayesian network is sampled from the current stochastic structure and the new solution will be produced from the sampled Bayesian network. Due to the stochastic structure used in the sampling phase, each sample can be generated based on a different structure. Therefore the different dependency structures can be preserved. Before the new generation is generated, the stochastic network’s probability distributions are updated according to the fitness evaluation of the current generation. The proposed method is able to take advantage of using different dependency structures through the sampling phase just by using one stochastic structure. The experimental results reported in this paper show that the proposed algorithm increases the quality of the solutions on the general optimization benchmark problems.     

Research on the Application of Bayesian Network in Agriculture Intelligent System

Bayesian network is a strong tool for uncertain knowledge representation and inference. This paper mainly introduces some technologies and methods about Bayesian network based on intelligent system. In the construction of Bayesian network, divorcing technology and noisy-or technology are used. In the inference of Bayesian network, VE algorithm and sampling algorithm are introduced. Finally, Bayesian network construction component and inference component are developed. Then an expert system about cow disease diagnosis is constructed based on the two components.     

一种改进的自适应流量采样方法

高速链路对实时网络流量监测提出挑战.由于流量采集分析设备性能的限制,采用精确、高效的采样方法进行流量监测分析已成为必然.最简单的固定概率采样能监测较大业务流,但往往忽略掉比例几乎超过80%的较小业务流.数据流算法可以实时高效采集高速链路数据,基于该算法的SGS(sketch guided sampling)采样技术可以实时准确估计流大小分布,但当采样速率增大到监测系统处理能力最大值时,该方法的准确性迅速降低.基于SGS方法,提出一种自适应实时网络流量的采样方法SRGS(sketch and resources guided sampling).该方法将监测系统处理能力作为采样概率调节的一个重要参数.实验结果显示,SRGS方法能够及时根据当前流大小和监测系统处理能力,调节数据包采样概率,准确性高于SGS方法.     

Bayesian model assessment and comparison using cross-validation predictive densities

In this work, we discuss practical methods for the assessment, comparison, and selection of complex hierarchical Bayesian models. A natural way to assess the goodness of the model is to estimate its future predictive capability by estimating expected utilities. Instead of just making a point estimate, it is important to obtain the distribution of the expected utility estimate because it describes the uncertainty in the estimate. The distributions of the expected utility estimates can also be used to compare models, for example, by computing the probability of one model having a better expected utility than some other model. We propose an approach using cross-validation predictive densities to obtain expected utility estimates and Bayesian bootstrap to obtain samples from their distributions. We also discuss the probabilistic assumptions made and properties of two practical cross-validation methods, importance sampling and k-fold cross-validation. As illustrative examples, we use multilayer perceptron neural networks and gaussian processes with Markov chain Monte Carlo sampling in one toy problem and two challenging real-world problems.     

Advanced computer programs for drug dosing that combine pharmacokinetic and symbolic modeling of patients.

In this paper, we describe our design for advanced drug dosing programs that "reason" using a combination of Bayesian pharmacokinetic modeling and symbolic modeling of patient status and drug response. Our design is similar to the design of the Digitalis Therapy Advisor program, but extends this previous work by incorporating a Bayesian pharmacokinetic model, performing a "meta-level" analysis of drug concentrations to identify sampling errors and changes in pharmacokinetics, and including the results of this analysis in reasoning for dosing and therapeutic monitoring recommendations. The design has been implemented in a program for aminoglycoside antibiotics called Aminoglycoside Therapy Manager. The program is user-friendly and runs on low-cost general-purpose hardware. The initial validation study showed that the program was as accurate in predicting future drug concentrations as an expert using commercial Bayesian forecasting software and that its dosing recommendations were similar to those of an expert.     

Supervised pre-processing approaches in multiple class variables classification for fish recruitment forecasting

A multi-species approach to fisheries management requires taking into account the interactions between species in order to improve recruitment forecasting of the fish species. Recent advances in Bayesian networks direct the learning of models with several interrelated variables to be forecasted simultaneously. These models are known as multi-dimensional Bayesian network classifiers (MDBNs). Pre-processing steps are critical for the posterior learning of the model in these kinds of domains. Therefore, in the present study, a set of ‘state-of-the-art’ uni-dimensional pre-processing methods, within the categories of missing data imputation, feature discretization and feature subset selection, are adapted to be used with MDBNs. A framework that includes the proposed multi-dimensional supervised pre-processing methods, coupled with a MDBN classifier, is tested with synthetic datasets and the real domain of fish recruitment forecasting. The correctly forecasting of three fish species (anchovy, sardine and hake) simultaneously is doubled (from 17.3% to 29.5%) using the multi-dimensional approach in comparison to mono-species models. The probability assessments also show high improvement reducing the average error (estimated by means of Brier score) from 0.35 to 0.27. Finally, these differences are superior to the forecasting of species by pairs.     

Bayesian forecaster using class-based optimization

Suppose that several forecasters exist for the problem in which class-wise accuracies of forecasting classifiers are important. For such a case, we propose to use a new Bayesian approach for deriving one unique forecaster out of the existing forecasters. Our Bayesian approach links the existing forecasting classifiers via class-based optimization by the aid of an evolutionary algorithm (EA). To show the usefulness of our Bayesian approach in practical situations, we have considered the case of the Korean stock market, where numerous lag-l forecasting classifiers exist for monitoring its status.