A real-time temporal Bayesian architecture for event surveillance and its application to patient-specific multiple disease outbreak detection

Reliable and accurate detection of disease outbreaks remains an important research topic in disease outbreak surveillance. A temporal surveillance system bases its analysis on data not only from the most recent time period, but also on data from previous time periods. A non-temporal system only looks at data from the most recent time period. There are two difficulties with a non-temporal system when it is used to monitor real data which often contain noise. First, it is prone to produce false positive signals during non-outbreak time periods. Second, during an outbreak, it tends to release false negative signals early in the outbreak, which can adversely affect the decision making process of the user of the system. We conjecture that by converting a non-temporal system to a temporal one, we may attenuate these difficulties inherent in a non-temporal system. In this paper, we propose a Bayesian network architecture for a class of temporal event surveillance models called BayesNet-T. Using this Bayesian network architecture, we can convert certain non-temporal surveillance systems to temporal ones. We apply this architecture to a previously developed non-temporal multiple-disease outbreak detection system called PC and create a temporal system called PCT. PCT takes Emergency Department (ED) patient chief complaint data as its input. The PCT system was constructed using both data (non-outbreak diseases) and expert assessments (outbreak diseases). We compare PCT to PC using a real influenza outbreak. Furthermore, we compare PCT to both PC and the classic statistical methods CUSUM and EWMA using a total of 240 influenza and Cryptosporidium disease outbreaks created by injecting stochastically simulated outbreak cases into real ED admission data. Our results indicate that PCT has a smaller mean time to detection than PC at low false alarm rates, and that PCT is more stable than PC in that once an outbreak is detected, PCT is better at maintaining the detection signal on future days.     

The centralized intake model for drug abuse treatment: The role of computerized data management

Several large research programs are underway that evaluate the centralized intake model for drug abuse treatment. In this model, the drug abuse treatment facilities in a city do not operate independently; their efforts are coordinated through a small number of intake centers, which handle all patient intake and data management activities. The success of such a coordinated approach to drug abuse treatment depends in large measure upon an adequate flow of patient information. For that reason, the centralized intake model brings new challenges for the field of computerized data management. The present article describes the management information system that is being used in a large research program called the District of Columbia Initiative (DCI). The methods of this system could be applied in cities where the centralized intake model for drug abuse treatment is adopted.     

Bayesian Networks for Data Mining

A Bayesian network is a graphical model that encodesprobabilistic relationships among variables of interest. When used inconjunction with statistical techniques, the graphical model hasseveral advantages for data modeling. One, because the model encodesdependencies among all variables, it readily handles situations wheresome data entries are missing. Two, a Bayesian network can be used tolearn causal relationships, and hence can be used to gain understanding about a problem domain and to predict the consequencesof intervention. Three, because the model has both a causal andprobabilistic semantics, it is an ideal representation for combiningprior knowledge (which often comes in causal form) and data. Four,Bayesian statistical methods in conjunction with Bayesian networksoffer an efficient and principled approach for avoiding theoverfitting of data. In this paper, we discuss methods for constructing Bayesian networks from prior knowledge and summarizeBayesian statistical methods for using data to improve these models.With regard to the latter task, we describe methods for learning boththe parameters and structure of a Bayesian network, includingtechniques for learning with incomplete data. In addition, we relateBayesian-network methods for learning to techniques for supervised andunsupervised learning. We illustrate the graphical-modeling approachusing a real-world case study.     

Fuzzy functional dependencies and Bayesian networks

Bayesian networks have become a popular technique for representing and reasoning with probabilistic information.The fuzzy functional dependency is an important kind of data dependencies in relational databases with fuzzy values,The purpose of this paper is to set up a connection between these data dependencies and Bayesian networks.The connection is done through a set of methods that enable pepople to obtain the most information of independent conditions from fuzzy functional dependencies.     

贝叶斯学习,贝叶斯网络与数据采掘

自从50～60年代贝叶斯学派形成后,关于贝叶斯分析的研究久盛不衰。早在80年代,贝叶斯网络就成功地应用于专家系统,成为表示不确定性专家知识和推理的一种流行方法。90年代以来,贝叶斯学习一直是机器学习研究的重要方向。由于概率统计与数据采掘的     

PREDICTION OF JAPANESE ENCEPHALITIS VECTORS IN KURNOOL DISTRICT OF ANDHRA PRADESH,INDIA BY USING BAYESIAN NETWORK

Japanese encephalitis (JE), a complex viral disease transmitted by mosquitoes. Determination of vector (mosquito) density is a prerequisite for devising effective control measures against this disease. Bayesian network is a widely used tool that has recently found application in the epidemiological surveillance studies. This article describes the application of Bayesian network tool to predict the Japanese encephalitis vector density using the longitudinal data collected from the Kurnool district of Andhra Pradesh, India, from 2001 to 2006. The entomological parameter from the study area indicates that various contributing factors are responsible for the prevalence of these vectors, making it difficult to estimate the importance of any particular parameter contributing to the increase of vector density. The application of this approach resulted in 73.12% to 95.12% accuracy compared to the test data with the corrected data.     

Control loop diagnosis with ambiguous historical operating modes: Part 2, information synthesis based on proportional parametrization

Control loop diagnosis has become an increasingly important tool for improving the efficiency, reliability and safety for a variety of processes. While a number of model-based diagnosis methods have been proposed, constructing models may be a difficult task. An alternative approach is to use data-driven control-loop diagnosis, a family of diagnosis methods that make use of historical data for training the diagnostic models. Bayesian methods have been applied to data-driven control loop diagnosis to combine prior process knowledge with historical data, and can be used to assign probabilities to different modes (or operation statuses) after combination. However, one difficulty with Bayesian methods is that there must be exact knowledge of the underlying mode so that the corresponding monitor readings in the historical data can be used. If there is uncertainty about the underlying mode, the mode becomes ambiguous, which Bayesian methods do not deal with. An alternative method is proposed in this paper that exploits the properties of data-driven Bayesian methods, and can be applied for diagnosis in the presence of ambiguity. The proposed method is evaluated through simulation examples as well as applied to industrial process data.     

Long-term HIV dynamic models incorporating drug adherence and resistance to treatment for prediction of virological responses

Long-term therapy with antiretroviral (ARV) agents in HIV-infected patients often results in failure to suppress the viral load. Imperfect adherence and drug susceptibility to prescribed antiviral drugs are important factors explaining the resurgence of virus. A better understanding of the factors responsible for the virological failure is critical for the development of new treatment strategies. In this paper, we develop a mechanism-based reparameterized differential equation model for characterizing long-term viral dynamics with ARV therapy. In this model we directly incorporate drug susceptibility and drug adherence (measured by medication event monitoring system (MEMS) and questionnaires) into a function of treatment efficacy. A Bayesian nonlinear mixed-effects modeling approach is investigated for estimating dynamic parameters by fitting the model to viral load data from an AIDS clinical trial. The effects of drug adherence interaction with drug resistance-based models are compared using (i) the sum of the squared residual (SSR) from individual subjects and (ii) the deviance information criterion (DIC), a Bayesian version of the classical deviance for model assessment, designed from complex hierarchical model settings. The results indicate that the drug adherence combined with confounding factor, drug resistance in viral dynamic modeling significantly predict virologic responses. Our study suggests that long-term reparameterized dynamic models are powerful and effective in establishing a relationship of antiviral responses with drug adherence and susceptibility.     

Bayesian reliability-based design optimization using eigenvector dimension reduction (EDR) method

In practical engineering design, most data sets for system uncertainties are insufficiently sampled from unknown statistical distributions, known as epistemic uncertainty. Existing methods in uncertainty-based design optimization have difficulty in handling both aleatory and epistemic uncertainties. To tackle design problems engaging both epistemic and aleatory uncertainties, reliability-based design optimization (RBDO) is integrated with Bayes theorem. It is referred to as Bayesian RBDO. However, Bayesian RBDO becomes extremely expensive when employing the first- or second-order reliability method (FORM/SORM) for reliability predictions. Thus, this paper proposes development of Bayesian RBDO methodology and its integration to a numerical solver, the eigenvector dimension reduction (EDR) method, for Bayesian reliability analysis. The EDR method takes a sensitivity-free approach for reliability analysis so that it is very efficient and accurate compared with other reliability methods such as FORM/SORM. Efficiency and accuracy of the Bayesian RBDO process are substantially improved after this integration.     

关于动力环境监控贝叶斯预测系统中参数获取的研究

针对目前动力环境监控系统中存在的一些问题,采用贝叶斯推理的方式处理一些不确定的信息,用于指导系统维护和决策。简单叙述了目前常见的一些抽样方法和预测方法,从统计学的角度讨论了如何对监控数据进行抽样才能更好的获取贝叶斯网络的先验概率和后验概率,并结合一些其他预测方法来完善推理系统,以实现对系统故障的有效预测。     

Variational Bayesian methods for spatial data analysis

With scientific data available at geocoded locations, investigators are increasingly turning to spatial process models for carrying out statistical inference. However, fitting spatial models often involves expensive matrix decompositions, whose computational complexity increases in cubic order with the number of spatial locations. This situation is aggravated in Bayesian settings where such computations are required once at every iteration of the Markov chain Monte Carlo (MCMC) algorithms. In this paper, we describe the use of Variational Bayesian (VB) methods as an alternative to MCMC to approximate the posterior distributions of complex spatial models. Variational methods, which have been used extensively in Bayesian machine learning for several years, provide a lower bound on the marginal likelihood, which can be computed efficiently. We provide results for the variational updates in several models especially emphasizing their use in multivariate spatial analysis. We demonstrate estimation and model comparisons from VB methods by using simulated data as well as environmental data sets and compare them with inference from MCMC.     

基于预测能力的贝叶斯网络分类器学习*

分析了贝叶斯分类器家族中有代表性的分类器;给出变量之间预测能力的概念及估计方法,在此基础上建立了基于变量间预测能力的贝叶斯网络分类器结构学习方法,并使用UCI数据进行分类实验.实验结果显示,该方法能够有效地进行贝叶斯网络分类器学习,使得贝叶斯网络分类器倾向于简单化,具有较强的分类能力.     

小数据集的贝叶斯网络结构学习

针对直接基于小数据集贝叶斯网络结构学习不可靠, 以及目前对小数据集的处理只强调扩展而忽略对扩展数据的修正等, 提出了将扩展与修正相结合的小数据集处理机制, 以及在此基础上的基于结点排序和局部打分--搜索的贝叶斯网络结构学习方法. 可不需要完全结点顺序的先验知识, 但能够结合专家的部分结点顺序信息. 实验结果显示了这种方法的有效性和可靠性.     

基于贝叶斯网络的数据挖掘方法

常用的数据挖掘方法有许多,贝叶斯网络(Bayesian Networks,BN)方法在数据挖掘中的应用是当前研究的热点问题.贝叶斯网络是一种进行不确定性推理和知识表示的有力工具,当与统计方法结合使用时,显示出许多关于数据处理的优势.首先介绍了BN的定义、方法的优点以及目前网络学习的各种算法,最后用一个实际中的案例进行试验,指出了在数据挖掘技术中的具体应用.得到了将贝叶斯网络应用于数据挖掘当中,充分挖掘数据的隐含信息和内在本质,具备良好地预测能力等优点,实验证明这种方法实用、有效.     

Unsupervised and simultaneous training of multiple object detectors from unlabeled surveillance video

Object detection is an essential component in automated vision-based surveillance systems. In general, object detectors are constructed using training examples obtained from large annotated data sets. The inevitable limitations of typical training data sets make such supervised methods unsuitable for building generic surveillance systems applicable to a wide variety of scenes and camera setups. In our previous work we proposed an unsupervised method for learning and detecting the dominant object class in a general dynamic scene observed by a static camera. In this paper, we investigate the possibilities to expand the applicability of this method to the problem of multiple dominant object classes. We propose an idea on how to approach this expansion, and perform an evaluation of this idea using two representative surveillance video sequences.     

A heuristic method for learning Bayesian networks using discrete particle swarm optimization

Bayesian networks are a powerful approach for representing and reasoning under conditions of uncertainty. Many researchers aim to find good algorithms for learning Bayesian networks from data. And the heuristic search algorithm is one of the most effective algorithms. Because the number of possible structures grows exponentially with the number of variables, learning the model structure from data by considering all possible structures exhaustively is infeasible. PSO (particle swarm optimization), a powerful optimal heuristic search algorithm, has been applied in various fields. Unfortunately, the classical PSO algorithm only operates in continuous and real-valued space, and the problem of Bayesian networks learning is in discrete space. In this paper, two modifications of updating rules for velocity and position are introduced and a Bayesian networks learning based on binary PSO is proposed. Experimental results show that it is more efficient because only fewer generations are needed to obtain optimal Bayesian networks structures. In the comparison, this method outperforms other heuristic methods such as GA (genetic algorithm) and classical binary PSO.     

协同疾病监测与处置系统的设计与实现

为解决在传统疾病监测系统与处置系统完全分离的过程中产生的敏感性与时效性问题,在C/S框架下设计一种基于互联网络和移动网络的协同疾病监测和处置系统,建立一套适应于监测预警、现场调查、应急处置的完整工作流程,实现监测与处置协同工作的原型系统。该系统的监测算法采用空间/时空扫描统计方法,而在应急处置中,疾病智能诊断模块采用贝叶斯分析算法。     

Robust Learning with Missing Data

This paper introduces a new method, called the robust Bayesian estimator (RBE), to learn conditional probability distributions from incomplete data sets. The intuition behind the RBE is that, when no information about the pattern of missing data is available, an incomplete database constrains the set of all possible estimates and this paper provides a characterization of these constraints. An experimental comparison with two popular methods to estimate conditional probability distributions from incomplete data—Gibbs sampling and the EM algorithm—shows a gain in robustness. An application of the RBE to quantify a naive Bayesian classifier from an incomplete data set illustrates its practical relevance.     

A Bayesian Method for the Induction of Probabilistic Networks from Data

This paper presents a Bayesian method for constructing probabilistic networks from databases. In particular, we focus on constructing Bayesian belief networks. Potential applications include computer-assisted hypothesis testing, automated scientific discovery, and automated construction of probabilistic expert systems. We extend the basic method to handle missing data and hidden (latent) variables. We show how to perform probabilistic inference by averaging over the inferences of multiple belief networks. Results are presented of a preliminary evaluation of an algorithm for constructing a belief network from a database of cases. Finally, we relate the methods in this paper to previous work, and we discuss open problems.