Bayesian data assimilation provides rapid decision support for vector-borne diseases

Predicting the spread of vector-borne diseases in response to incursions requires knowledge of both host and vector demographics in advance of an outbreak. Although host population data are typically available, for novel disease introductions there is a high chance of the pathogen using a vector for which data are unavailable. This presents a barrier to estimating the parameters of dynamical models representing host–vector–pathogen interaction, and hence limits their ability to provide quantitative risk forecasts. The Theileria orientalis (Ikeda) outbreak in New Zealand cattle demonstrates this problem: even though the vector has received extensive laboratory study, a high degree of uncertainty persists over its national demographic distribution. Addressing this, we develop a Bayesian data assimilation approach whereby indirect observations of vector activity inform a seasonal spatio-temporal risk surface within a stochastic epidemic model. We provide quantitative predictions for the future spread of the epidemic, quantifying uncertainty in the model parameters, case infection times and the disease status of undetected infections. Importantly, we demonstrate how our model learns sequentially as the epidemic unfolds and provide evidence for changing epidemic dynamics through time. Our approach therefore provides a significant advance in rapid decision support for novel vector-borne disease outbreaks.     

Integrated decision support framework for distribution network design

In the current business environment of competition shifting from company-to-company to supply chain against supply chain, there is an increasing need for logistics providers (LSP) to gain cost effectiveness with no compromise on service levels. One key initiative that LSP can undertake is to allocate and utilise their storage and transportation assets optimally. The current work is an attempt in that direction and provides a hands-on decision support framework that integrates MCDM, network optimisation, and discrete event simulation to address distribution network design and transport optimisation. The use case of PT Pos Indonesia in the metropolitan area of Greater Surabaya highlights the benefits of combining ICT tools with well-established best practices in supply chain management. Findings of this work highlight that the number of distribution facilities for the case at hand should be reduced from nine to four. Compared to the existing, the identified network configuration unlocks potential cost saving in transportation and warehousing of 18%–22%, reduces CO₂ emissions by nearly 30%, with no deterioration in service level. Managerial implications about transportation policies are highlighted in the conclusive part of this paper.     

Bayesian decision method applied to a problem in gear train design

The problem of backlash in gear mechanisms is approached from the point, of view of a decision-maker, The elements of Bayesian Decision Theory are described and their significance is related to the backlash problem. The Normal statistical model is motivated as the basis for decision analysis with and without observational data. Each step of the analysis is examined in detail for the backlash problem, and is illustrated by a simple but realistic numerical example.     

A decision support system for the design of unpaced production lines

Consider a realistic unpaced-line problem: there is a set of discrete tasks, whose task-time distributions have diverse shapes. The line designer must (i) decide to which work station to assign each task, and (ii) specify the size of each buffer area in such a way that the configuration has the ‘best’ operating characteristics. This paper describes a decision support package that can efficiently generate the operating characteristics of the many alternative line designs which the line designer may want to try. We also show that the package can be conveniently used to extend earlier results in theoretical unpaced-line research.     

Determining design requirements in QFD using fuzzy mixed-integer goal programming: application of a decision support system

In product development, the identification of critical design requirements (DRs) is key to satisfying customer needs because it helps produce more successful products in a shorter time. Quality function deployment (QFD) is a tool used in product development to systematically determine the DRs so as to attain higher customer satisfaction. In the QFD process, the simultaneous optimisation of more than one conflicting objective is generally required. However, it is very difficult for decision makers to determine the goal value of each objective in imprecise and uncertain environments. In order to overcome this problem, the present study proposes a fuzzy mixed-integer goal programming model that determines a combination of optimal DR values. Different from the existing fuzzy goal programming models, the values of the DRs in the proposed model are taken as discrete. Finally, a new Decision Support System is developed. The new system integrates QFD and mathematical programming, enabling the design team to effectively compare product design alternatives and make product development easier and faster. The proposed methodology is illustrated using a real-world application in the Turkish white goods industry.     

A cost estimation model to support automation decision in assembly systems design

Cost analysis is crucial in the design of assembly systems and the decision on their level of automation (LoA). This paper presents a cost estimation model of assembly system that is used to decide their LoA during the early phase of projects. Based on an extensive literature review, a complete cost model integrating multiple cost drivers is proposed. This model is then exploited to create the objective function of an integer linear programme model utilised to solve the LoA decision problem. The work provides a way to perform cost estimation of assembly systems alternatives and to decide the most appropriate LoA in assembly. The cost estimation model is built with a parametric approach allowing the definition of various optimisation objectives. The proposed integer programme, complement this approach by proposing the suitable constraints set, that describes the LoA decision problem.     

Robust design using Bayesian Monte Carlo

In this paper, we propose an efficient strategy for robust design based on Bayesian Monte Carlo simulation. Robust design is formulated as a multiobjective problem to allow explicit trade‐off between the mean performance and variability. The proposed method is applied to a compressor blade design in the presence of manufacturing uncertainty. Process capability data are utilized in conjunction with a parametric geometry model for manufacturing uncertainty quantification. High‐fidelity computational fluid dynamics simulations are used to evaluate the aerodynamic performance of the compressor blade. A probabilistic analysis for estimating the effect of manufacturing variations on the aerodynamic performance of the blade is performed and a case for the application of robust design is established. The proposed approach is applied to robust design of compressor blades and a selected design from the final Pareto set is compared with an optimal design obtained by minimizing the nominal performance. The selected robust blade has substantial improvement in robustness against manufacturing variations in comparison with the deterministic optimal blade. Significant savings in computational effort using the proposed method are also illustrated. Copyright © 2007 John Wiley & Sons, Ltd.     

Multi-criteria fuzzy decision support for conceptual evaluation in design of mechatronic systems: a quadrotor design case study

Designing mechatronic systems is known to be a very complex and tedious process due to the high number of system components, their multi-physical aspects, the couplings between the different domains involved in the product, and the interacting design objectives. This inherent complexity calls for the crucial need of a systematic and multi-objective design thinking methodology to replace the often-used sequential design approach that tends to deal with the different domains and their corresponding design objectives separately leading to functional but not necessarily optimal designs. Thus, a new approach based on a multi-criteria profile for mechatronic systems is presented in this paper for the conceptual design stage. Additionally, to facilitate fitting the intuitive requirements for decision-making in the presence of interacting criteria, three different methods are proposed and compared using a case study of designing a vision-guided quadrotor drone system. These methods benefit from three different aggregation techniques such as Choquet integral, Sugeno integral and fuzzy-based neural network. To validate the decision yielded by the results of global concept score for each aggregation methods, a computer simulation of a visual servoing system on all design alternatives for quadrotor drone has been performed. It is shown that although the Sugeno fuzzy can be a useful aggregation function for decisions under uncertainty, but the approaches using Choquet fuzzy and fuzzy integral-based neural network seem to be more precise and reliable in a multi-criteria design problem where interaction between the objectives cannot be overlooked.     

A strategic decision support system for logistics and supply chain network design

This paper aims to develop a strategic decision support system for logistics and supply chain network design of a multi-stage, multi-commodity, and multi-period distribution and transportation system. A mixed integer linear programming model is proposed to tackle the problem while minimizing the operating, transportation and handling cost through all tiers of the supply chain network. A genetic algorithm based method has been proposed to solve the problem in a large scale realistic environment. The efficacy of the developed strategic decision support model in achieving better utilization of network and resources to fulfil the customer demand is demonstrated using illustrative scenarios inspired from the real case of a logistics company.     

Building prior distributions to support Bayesian reliability growth modelling using expert judgement

A sound methodology for the elicitation of subjective expert judgement is a pre-requisite for specifying prior distributions for the parameters of reliability growth models. In this paper, we describe an elicitation process that is developed to ensure valid data are collected by suggesting how possible bias might be identified and managed. As well as discussing the theory underpinning the elicitation process, the paper gives practical guidance concerning its implementation during reliability growth testing. The collection of subjective data using the proposed elicitation process is embedded within a Bayesian reliability growth modelling framework and reflections upon its practical use are described.     

Robust parameter extraction for decision support using multimodal intensive care data

Digital information flow within the intensive care unit (ICU) continues to grow, with advances in technology and computational biology. Recent developments in the integration and archiving of these data have resulted in new opportunities for data analysis and clinical feedback. New problems associated with ICU databases have also arisen. ICU data are high-dimensional, often sparse, asynchronous and irregularly sampled, as well as being non-stationary, noisy and subject to frequent exogenous perturbations by clinical staff. Relationships between different physiological parameters are usually nonlinear (except within restricted ranges), and the equipment used to measure the observables is often inherently error-prone and biased. The prior probabilities associated with an individual's genetics, pre-existing conditions, lifestyle and ongoing medical treatment all affect prediction and classification accuracy. In this paper, we describe some of the key problems and associated methods that hold promise for robust parameter extraction and data fusion for use in clinical decision support in the ICU.     

Predicting motor vehicle collisions using Bayesian neural network models: an empirical analysis

Statistical models have frequently been used in highway safety studies. They can be utilized for various purposes, including establishing relationships between variables, screening covariates and predicting values. Generalized linear models (GLM) and hierarchical Bayes models (HBM) have been the most common types of model favored by transportation safety analysts. Over the last few years, researchers have proposed the back-propagation neural network (BPNN) model for modeling the phenomenon under study. Compared to GLMs and HBMs, BPNNs have received much less attention in highway safety modeling. The reasons are attributed to the complexity for estimating this kind of model as well as the problem related to "over-fitting" the data. To circumvent the latter problem, some statisticians have proposed the use of Bayesian neural network (BNN) models. These models have been shown to perform better than BPNN models while at the same time reducing the difficulty associated with over-fitting the data. The objective of this study is to evaluate the application of BNN models for predicting motor vehicle crashes. To accomplish this objective, a series of models was estimated using data collected on rural frontage roads in Texas. Three types of models were compared: BPNN, BNN and the negative binomial (NB) regression models. The results of this study show that in general both types of neural network models perform better than the NB regression model in terms of data prediction. Although the BPNN model can occasionally provide better or approximately equivalent prediction performance compared to the BNN model, in most cases its prediction performance is worse than the BNN model. In addition, the data fitting performance of the BPNN model is consistently worse than the BNN model, which suggests that the BNN model has better generalization abilities than the BPNN model and can effectively alleviate the over-fitting problem without significantly compromising the nonlinear approximation ability. The results also show that BNNs could be used for other useful analyses in highway safety, including the development of accident modification factors and for improving the prediction capabilities for evaluating different highway design alternatives.     

Fitting empirical potentials: Challenges and methodologies

Although fitting potentials for atomic-level simulations is a complex process, there is little literature on the procedures involved. A general methodology for fitting atomic-level simulation method potentials is given, including a strategy for focusing on the specific properties needed to fit particular potential parameters, what to include in the training set, and how to set up an effective cost function. A brief review of optimization strategies is presented along with a discussion of testing and finalizing potential sets. The current capabilities and challenges associated with each step in the procedure are discussed.     

The development of a decision support framework for a quantitative risk assessment in multimodal green logistics: an empirical study

The objective of this research was to develop a decision support framework (DSF) to assess quantitative risk in multimodal green logistics. This risk assessment is the combination of a number of models, the failure mode and effects analysis, the risk contour plot, the quantitative risk assessment, the analytic hierarchy process and the data envelopment analysis which can support a user to perform risk assessment in various decisions. The contribution of this research is that the risk assessment model can generate an optimal green logistics route in accordance with weight from the user. The highlight of this DSF is that the quantitative assessment model can reduce bias on risk assessment of logistics route. An in-depth case study, recommendations, limitations and further research are also provided.     

基于公理设计和相容决策支持问题法的稳健优化设计方法

 针对多目标稳健优化问题,建立了多目标稳健优化的损失函数,利用灵敏度分析方法确定各设计变量对各设计目标的影响程度,确定主要的设计参数,便于调整和控制设计参数的公差.根据信息公理与损失函数的一致性关系,建立以最小化各目标的总损失函数为目标函数.并在相容决策支持问题法框架基础上,提出一种基于公理设计和相容决策支持问题法的多目标稳健优化设计模型.实例分析表明,提出的方法是可行的.     

Gradient projection for reliability-based design optimization using evidence theory

Uncertainty quantification and risk assessment in the optimal design of structural systems has always been a critical consideration for engineers. When new technologies are developed or implemented and budgets are limited for full-scale testing, the result is insufficient datasets for construction of probability distributions. Making assumptions about these probability distributions can potentially introduce more uncertainty to the system than it quantifies. Evidence theory represents a method to handle epistemic uncertainty that represents a lack of knowledge or information in the numerical optimization process. Therefore, it is a natural tool to use for uncertainty quantification and risk assessment especially in the optimization design cycle for future aerospace structures where new technologies are being applied. For evidence theory to be recognized as a useful tool, it must be efficiently applied in a robust design optimization scheme. This article demonstrates a new method for projecting the reliability gradient, based on the measures of belief and plausibility, without gathering any excess information other than what is required to determine these measures. This represents a huge saving in computational time over other methods available in the current literature. The technique developed in this article is demonstrated with three optimization examples.     

Value analysis as a decision support tool in cruise ship design

In the cruise ship industry product development and production activities are really complex and must follow strict rules imposed by naval registries. Designers are frequently required to choose among several alternative solutions (e.g., materials, components, layouts, etc.). Because of time constraints, as a matter of fact, design decisions are made fast and in a reactive way, according to the particular case, without considering decisions made in the past and without using specific decision support tools. The final choice is often left to a single designer's experience, whose selection criteria are unknown and not formalised. As a consequence there is no shared knowledge justifying the reason why a design solution has been chosen and whether it is the best one. We developed and implemented in Fincantieri S.p.A. – a leading company in the cruise ship industry – an original decision support tool, based on value analysis, designers can use to document and formalise their choices. Value analysis is a well known structured method to increase product value and/or cut costs, thus supporting the selection of the most valuable solution by means of objective parameters. We demonstrate that the proposed tool can also facilitate reuse of the available knowledge base on decisional criteria, increase interactions between people (design staff, buyers, shipyard personnel, etc.) involved in different stages of different value analysis projects, and reduce decision time.     

Use of QRA for decision support in the design of an offshore oil production installation

QRA is today widely used as a tool for decision support in the offshore industry. Its use has gradually changed from a prescribed analysis for verification purposes to a tool being actively used in an integrated mode. The paper describes its use in the design of a modern offshore platform. The paper addresses work methodology, selection of tools and data, organisation of QRA with other activities. Specific examples are given.     

Bayesian risk-based decision method for model validation under uncertainty

This paper develops a decision-making methodology for computational model validation, considering the risk of using the current model, data support for the current model, and cost of acquiring new information to improve the model. A Bayesian decision theory-based method is developed for this purpose, using a likelihood ratio as the validation metric for model assessment. An expected risk or cost function is defined as a function of the decision costs, and the likelihood and prior of each hypothesis. The risk is minimized through correctly assigning experimental data to two decision regions based on the comparison of the likelihood ratio with a decision threshold. A Bayesian validation metric is derived based on the risk minimization criterion. Two types of validation tests are considered: pass/fail tests and system response value measurement tests. The methodology is illustrated for the validation of reliability prediction models in a tension bar and an engine blade subjected to high cycle fatigue. The proposed method can effectively integrate optimal experimental design into model validation to simultaneously reduce the cost and improve the accuracy of reliability model assessment.