An evolutionary Bayesian belief network methodology for optimum management of groundwater contamination

An integrated methodology, based on Bayesian belief network (BBN) and evolutionary multi-objective optimization (EMO), is proposed for combining available evidence to help water managers evaluate implications, including costs and benefits of alternative actions, and suggest best decision pathways under uncertainty. A Bayesian belief network is a probabilistic graphical model that represents a set of variables and their probabilistic relationships, which also captures historical information about these dependencies. In complex applications where the task of defining the network could be difficult, the proposed methodology can be used in validation of the network structure and the parameters of the probabilistic relationship. Furthermore, in decision problems where it is difficult to choose appropriate combinations of interventions, the states of key variables under the full range of management options cannot be analyzed using a Bayesian belief network alone as a decision support tool. The proposed optimization method is used to deal with complexity in learning about actions and probabilities and also to perform inference. The optimization algorithm generates the state variable values which are fed into the Bayesian belief network. It is possible then to calculate the probabilities for all nodes in the network (belief propagation). Once the probabilities of all the linked nodes have been updated, the objective function values are returned to the optimization tool and the process is repeated. The proposed integrated methodology can help in dealing with uncertainties in decision making pertaining to human behavior. It also eliminates the shortcoming of Bayesian belief networks in introducing boundary constraints on probability of state values of the variables. The effectiveness of the proposed methodology is examined in optimum management of groundwater contamination risks for a well field capture zone outside Copenhagen city.     

基于贝叶斯方法的分类预测

介绍了基本的贝叶斯分类模型和贝叶斯信念网络模型,对网络模型的学习进行了讨论。并从实际出发,提出了几种可以简化模型结构、降低学习复杂性的可行方法,简要说明了这些方法在网络模型中的应用。对贝叶斯分类模型的准确性及其主要特点进行了分析。     

Enhancing ontology-based antipattern detection using Bayesian networks

Antipatterns provide information on commonly occurring solutions to problems that generate negative consequences. The antipattern ontology has been recently proposed as a knowledge base for SPARSE, an intelligent system that can detect the antipatterns that exist in a software project. However, apart from the plethora of antipatterns that are inherently informal and imprecise, the information used in the antipattern ontology itself is many times imprecise or vaguely defined. For example, the certainty in which a cause, symptom or consequence of an antipattern exists in a software project. Taking into account probabilistic information would yield more realistic, intelligent and effective ontology-based applications to support the technology of antipatterns. However, ontologies are not capable of representing uncertainty and the effective detection of antipatterns taking into account the uncertainty that exists in software project antipatterns still remains an open issue. Bayesian Networks (BNs) have been previously used in order to measure, illustrate and handle antipattern uncertainty in mathematical terms. In this paper, we explore the ways in which the antipattern ontology can be enhanced using Bayesian networks in order to reinforce the existing ontology-based detection process. This approach allows software developers to quantify the existence of an antipattern using Bayesian networks, based on probabilistic knowledge contained in the antipattern ontology regarding relationships of antipatterns through their causes, symptoms and consequences. The framework is exemplified using a Bayesian network model of 13 antipattern attributes, which is constructed using BNTab, a plug-in developed for the Protege ontology editor that generates BNs based on ontological information.     

Uncertainty-aware soft sensor using Bayesian recurrent neural networks

Data-driven soft sensors have been widely used to measure key variables for industrial processes. Soft sensors using deep learning models have attracted considerable attention and shown superior predictive performance. However, if a soft sensor encounters an unexpected situation in inferring data or if noisy input data is used, the estimated value derived by a standard soft sensor using deep learning may at best be untrustworthy. This problem can be mitigated by expressing a degree of uncertainty about the trustworthiness of the estimated value produced by the soft sensor. To address this issue of uncertainty, we propose using an uncertainty-aware soft sensor that uses Bayesian recurrent neural networks (RNNs). The proposed soft sensor uses a RNN model as a backbone and is then trained using Bayesian techniques. The experimental results demonstrated that such an uncertainty-aware soft sensor increases the reliability of predictive uncertainty. In comparisons with a standard soft sensor, it shows a capability to use uncertainties for interval prediction without compromising predictive performance.     

Modelling functional resilience of microbial ecosystems: Analysis of governing processes

Functional stability of microbial ecosystems subjected to disturbances is essential for maintaining microbial ecosystem services such as the biodegradation of organic contaminants in terrestrial environments. Functional responses to disturbances are thus an important aspect which is, however, not well understood yet. Here, we present a microbial simulation model to investigate key processes for the recovery of biodegradation. We simulated single disturbances with different spatiotemporal characteristics and monitored subsequent recovery of the biodegradation dynamics. After less intense disturbance events local regrowth governs biodegradation recovery. After highly intense disturbance events the disturbance pattern's spatial configuration is decisive and processes governing local functional recovery vary depending on habitat location with respect to the spatial disturbance pattern. Local regrowth may be unimportant when bacterial dispersal from undisturbed habitats is high. Hence, our results suggest that spatial dynamics are crucial for the robust delivery of the ecosystem service biodegradation under disturbances in terrestrial environments.     

Applying Bayesian networks to performance forecast of innovation projects: A case study of transformational leadership influence in organizations oriented by projects

The focus of this work is the analysis of the influence of transformational leadership on organizational factors, and their impacts on the project performance. The factors considered are communication, flexibility, continuous delivery and continuous improvement, overlap of activities, and maturity of the team, in projects with a high degree of innovation. Bayesian networks were chosen as a simulation tool. Results showed that for a moderate level of overlap of activities, the maximum project performance is obtained when the leadership components individual consideration, inspirational motivation, idealized influence and intellectual stimulation, are either at moderate levels. This leads to high levels of team maturity, flexibility and continuous delivery, while continuous improvement and communication tend to be moderate. It is highlighted the characterization of the individual contribution of the variables to the project performance and the empirical application of Bayesian networks, as an alternative to statistical methods commonly employed in leadership and management studies.     

Intelligent fault inference for rotating flexible rotors using Bayesian belief network

Flexible rotor is a crucial mechanical component of a diverse range of rotating machineries and its condition monitoring and fault diagnosis are of particular importance to the modern industry. In this paper, Bayesian belief network (BBN) is applied to the fault inference for rotating flexible rotors with attempt to enhance the reasoning capacity under conditions of uncertainty. A generalized three-layer configuration of BBN for the fault inference of rotating machinery is developed by fully incorporating human experts’ knowledge, machine faults and fault symptoms as well as machine running conditions. Compared with the Naive diagnosis network, the proposed topological structure of causalities takes account of more practical and complete diagnostic information in fault diagnosis. The network tallies well with the practical thinking of field experts in the whole processes of machine fault diagnosis. The applications of the proposed BBN network in the uncertainty inference of rotating flexible rotors show good agreements with our knowledge and practical experience of diagnosis.     

PRL: A probabilistic relational language

In this paper, we describe the syntax and semantics for a probabilistic relational language (PRL). PRL is a recasting of recent work in Probabilistic Relational Models (PRMs) into a logic programming framework. We show how to represent varying degrees of complexity in the semantics including attribute uncertainty, structural uncertainty and identity uncertainty. Our approach is similar in spirit to the work in Bayesian Logic Programs (BLPs), and Logical Bayesian Networks (LBNs). However, surprisingly, there are still some important differences in the resulting formalism; for example, we introduce a general notion of aggregates based on the PRM approaches. One of our contributions is that we show how to support richer forms of structural uncertainty in a probabilistic logical language than have been previously described. Our goal in this work is to present a unifying framework that supports all of the types of relational uncertainty yet is based on logic programming formalisms. We also believe that it facilitates understanding the relationship between the frame-based approaches and alternate logic programming approaches, and allows greater transfer of ideas between them. Editors: Hendrik Blockeel, David Jensen and Stefan Kramer An erratum to this article is available at .     

Uncertainty in cloud service relationships: Uncovering the differential effect of three social influence processes on potential and current users

Consumer cloud services are characterized by uncertainty before usage but also for individuals who are already using the service. Our cloud service relationship model posits that individuals facing continuous uncertainty during adoption and continuance decisions rely on their social environment to make evaluations and decisions. Drawing on a representative dataset of 2011 Internet users, we distinguish three social influence processes from social influence theory (identification, internalization, and compliance) and uncover their differential effect on potential and current users’ uncertainty evaluations and on usage intentions. Our results can help cloud providers to successfully manage their relationships with potential and current users.     

A Bayesian approach to model dispersal for decision support

In agricultural and environmental sciences dispersal models are often used for risk assessment to predict the risk associated with a given configuration and also to test scenarios that are likely to minimise those risks. Like any biological process, dispersal is subject to biological, climatic and environmental variability and its prediction relies on models and parameter values which can only approximate the real processes. In this paper, we present a Bayesian method to model dispersal using spatial configuration and climatic data (distances between emitters and receptors; main wind direction) while accounting for uncertainty, with an application to the prediction of adventitious presence rate of genetically modified maize (GM) in a non-GM field. This method includes the design of candidate models, their calibration, selection and evaluation on an independent dataset. A group of models was identified that is sufficiently robust to be used for prediction purpose. The group of models allows to include local information and it reflects reliably enough the observed variability in the data so that probabilistic model predictions can be performed and used to quantify risk under different scenarios or derive optimal sampling schemes.     

Bayesian spatial modeling and interpolation using copulas

Classical Bayesian spatial interpolation methods are based on the Gaussian assumption and therefore lead to unreliable results when applied to extreme valued data. Specifically, they give wrong estimates of the prediction uncertainty. Copulas have recently attracted much attention in spatial statistics and are used as a flexible alternative to traditional methods for non-Gaussian spatial modeling and interpolation. We adopt this methodology and show how it can be incorporated in a Bayesian framework by assigning priors to all model parameters. In the absence of simple analytical expressions for the joint posterior distribution we propose a Metropolis-Hastings algorithm to obtain posterior samples. The posterior predictive density is approximated by averaging the plug-in predictive densities. Furthermore, we discuss the deficiencies of the existing spatial copula models with regard to modeling extreme events. It is shown that the non-Gaussian χ²-copula model suffers from the same lack of tail dependence as the Gaussian copula and thus offers no advantage over the latter with respect to modeling extremes. We illustrate the proposed methodology by analyzing a dataset here referred to as the Helicopter dataset, which includes strongly skewed radioactivity measurements in the city of Oranienburg, Germany.     

Multi-scale land-use disaggregation modelling: Concept and application to EU countries

Changes of carbon stocks in agricultural soils, emissions of greenhouse gases from agriculture, and the delivery of ecosystem services of agricultural landscapes depend on combinations of land-use, livestock density, farming practices, climate and soil types. Many environmental processes are highly non-linear. If the analysis of the environmental impact is based on data at a relatively coarse-scale (e.g. farm, country, or large administrative regions), conclusions can be misleading. For an accurate assessment of agri-environmental indicators, data of agricultural activities and their dynamics are needed at high spatial resolution. In this paper, we develop and validate a spatial model for predicting the agricultural land-use areas within the homogenous spatial units (HSUs). For the EU-28 countries, we distinguish about 1.5 × 10⁵ HSUs and we consider 30 possible land-uses to match with the classification used in the Common Agricultural Policy Regionalized Impact (CAPRI) model. The comparison of model predictions with independent observations and with a simple rule-based approach at HSU level demonstrates that the predictions are generally accurate in more than 75 % of HSUs. The frequent crops or land-use are better predicted. For non-frequent crops and/or crops requiring specific cultivation conditions, the model needs further fine-tuning.     

Moving SWAT model calibration and uncertainty analysis to an enterprise Hadoop-based cloud

With enhanced availability of high spatial resolution data, hydrologic models such as the Soil and Water Assessment Tool (SWAT) are increasingly used to investigate effects of management activities and climate change on water availability and quality. The advantages come at a price of greater computational demand and run time. This becomes challenging to model calibration and uncertainty analysis as these routines involve a large number of model runs. For efficient modelling, a cloud-based Calibration and Uncertainty analysis Tool for SWAT (CUT-SWAT) was implemented using Hadoop, an open source cloud platform, and the Generalized Likelihood Uncertainty Estimation method. Test results on an enterprise cloud showed that CUT-SWAT can significantly speedup the calibration and uncertainty analysis processes with a speedup of 21.7–26.6 depending on model complexity and provides a flexible and fault-tolerant model execution environment (it can gracefully and automatically handle partial failure), thus would be an ideal method to solve computational demand problems in hydrological modelling.     

Integrating ontological modelling and Bayesian inference for pattern classification in topographic vector data

This paper presents an ontology-driven approach for spatial database enrichment in support of map generalisation. Ontology-driven spatial database enrichment is a promising means to provide better transparency, flexibility and reusability in comparison to purely algorithmic approaches. Geographic concepts manifested in spatial patterns are formalised by means of ontologies that are used to trigger appropriate low level pattern recognition techniques. The paper focuses on inference in the presence of vagueness, which is common in definitions of spatial phenomena, and on the influence of the complexity of spatial measures on classification accuracy. The concept of the English terraced house serves as an example to demonstrate how geographic concepts can be modelled in an ontology for spatial database enrichment. Owing to their good integration into ontologies, and their ability to deal with vague definitions, supervised Bayesian inference is used for inferring complex concepts. The approach is validated in experiments using large vector datasets representing buildings of four different cities. We compare classification results obtained with the proposed approach to results produced by a more traditional ontology approach. The proposed approach performed considerably better in comparison to the traditional ontology approach. Besides clarifying the benefits of using ontologies in spatial database enrichment, our research demonstrates that Bayesian networks are a suitable method to integrate vague knowledge about conceptualisations in cartography and GIScience.     

Managing uncertainty in location services using rough set and evidence theory

Uncertainty in service management stems from the incompleteness and vagueness of the conditioning attributes that characterize a service. In particular, location based services often have complex interaction mechanisms in terms of their neighborhood relationships. Classical location service models require rigorous parameters and conditioning attributes and offers limited flexibility to incorporate imprecise or ambiguous evidences. In this paper we have developed a formal model of uncertainty in service management. We have developed a rough set and Dempster–Shafer’s evidence theory based formalism to objectively represent uncertainty inherent in the process of service discovery, characterization, and classification. Rough set theory is ideally suited for dealing with limited resolution, vague and incomplete information, while Dempster–Shafer’s evidence theory provides a consistent approach to model an expert’s belief and ignorance in the classification decision process. Integrating these two formal approaches in spatial domain provides a way to model an expert’s belief and ignorance in service classification. In an application scenario of the model we have used a cognitive map of retail site assessment, which reflects the partially subjective assessment process. The uncertainty hidden in the cognitive map can be consistently formalized using the proposed model. Thus we provide a naturalistic means of incorporating both qualitative aspects of intuitive knowledge as well as hard empirical information for service management within a formal uncertainty framework.     

FAULT-TOLERANT MULTI-AGENT EXACT BELIEF PROPAGATION

Multiply sectioned Bayesian networks (MSBNs) support multi-agent probabilistic inference in distributed large problem domains, where agents (subdomains) are organized by a tree structure (called hypertree). In earlier work, all belief updating methods on a hypertree are made of two rounds of propagation, each of which is implemented as a recursive process. Both processes need to be started from the same designated (root) hypernode. Agents perform local belief updating at most in a partial parallel manner. Such methods may not be suitable for practical multi-agent environments because they are easy to crush for the problems happened in communication or local belief updating. In this paper, we present a fault-tolerant belief updating method for multi-agent probabilistic inference. In this method, multiple agents concurrently perform exact belief updating in a complete parallel. Temporary problems happened from time to time at some agents or some communication channels would not prevent agents from eventually converging to the correct beliefs. Permanently disconnected communication channels would not keep the properly connected portions of the system from appropriately finishing their belief updating within portions. Compared to the previous traversal-based belief updating, the proposed approach is not only fault-tolerant but also robust and scalable.     

动态贝叶斯网络在战术态势估计中的应用*

针对战术态势估计的特点和要求,分析和建立了应用于态势估计的动态贝叶斯网络模型。该模型以离散变量集为研究对象。由于该动态贝叶斯网络满足Markovian特性和平稳特性,降低了网络的复杂度。相比较于贝叶斯网络模型,该动态贝叶斯网络模型考虑了时序因素,将前时刻的态势因素作为当前时刻态势估计的证据的一部分,并能对下一时刻的态势进行预测。文中采用集树（junction tree）算法,利用相关的贝叶斯网络推理软件进行了实验,实验结果表明基于动态贝叶斯网络的估计结果较贝叶斯网络的估计结果好,验证了该模型的有效性。     

Linear uncertain extensions of the minimum cost consensus model based on uncertain distance and consensus utility

Uncertainty theory adopts the belief degree and uncertainty distribution to ensure good alignment with a decision-maker’s uncertain preferences, making the final decisions obtained from the consensus-reaching process closer to the actual decision-making scenarios. Under the constraints of the uncertain distance measure and consensus utility, this article explores the minimum-cost consensus model under various linear uncertainty distribution-based preferences. First, the uncertain distance is used to measure the deviation between individual opinions and the consensus through uncertainty distributions. A nonlinear analytical formula is derived to avoid the computational complexity of integral and piecewise function operations, thus reducing the calculation cost of the uncertain distance measure. The consensus utility function defined in this article characterizes the adjustment value and degree of aggregation of individual opinions. Three new consensus models are constructed based on the consensus utility and linear uncertainty distribution. The results show that, in complex group decision-making contexts, the uncertain consensus models are more flexible than traditional minimum-cost consensus models: compared with the high volatility of the adjusted opinions in traditional deterministic consensus models with crisp number-based preferences, the variation trends of both individual adjusted opinions and the collective opinion with a linear uncertainty distribution are much smoother and the fitting range is closer to reality. The introduction of the consensus utility not only reflects the relative changes of individual opinions, but also accounts for individual psychological changes during the opinion-adjustment process. Most importantly, it reduces the cost per unit of consensus utility, facilitates the determination of the optimal threshold for the consensus utility, and improves the efficiency of resource allocation.     

Applications of Bayesian belief networks in water resource management: A systematic review

Bayesian belief networks (BBNs) are probabilistic graphical models that can capture and integrate both quantitative and qualitative data, thus accommodating data-limited conditions. This paper systematically reviews applications of BBNs with respect to spatial factors, water domains, and the consideration of climate change impacts. The methods used for constructing and validating BBN models, and their applications in different forms of decision-making support are examined. Most reviewed publications originate from developed countries (70%), in temperate climate zones (42%), and focus mainly on water quality (42%). In 60% of the reviewed applications model validation was based on the expert or stakeholder evaluation and sensitivity analysis, and whilst in 27% model performance was not discussed. Most reviewed articles applied BBNs in strategic decision-making contexts (52%). Integrated modelling tools for addressing challenges of dynamically complex systems were also reviewed by analysing the strengths and weaknesses of BBNs, and integration of BBNs with other modelling tools.     

A Bayesian approach to information fusion for evaluating the measurement uncertainty

The Bayesian approach to uncertainty evaluation is a classical example of the fusion of information from different sources. Basically, it is founded on both the knowledge about the measurement process and the influencing quantities and parameters. The knowledge about the measurement process is primarily represented by the so-called model equation, which forms the basic relationship for the fusion of all involved quantities. The knowledge about the influencing quantities and parameters is expressed by their degree of belief, i.e. appropriate probability density functions that usually are obtained by utilizing the principle of maximum information entropy and the Bayes theorem. Practically, the Bayesian approach to uncertainty evaluation is put into effect by employing numerical integration techniques, preferably Monte-Carlo methods. Compared to the ISO-GUM procedure, the Bayesian approach does not have any restrictions with respect to nonlinearities and calculation of confidence intervals.