Validating fuzzy decision model using risk and confidence analysis

Objective. In many real-world decision tasks, the information available to the decision maker is incomplete. To account for this uncertainty, we associate a degree of confidence to every decision, representing the likelihood of that decision being correct. In this study, we analyse electroencephalography (EEG) data from 68 participants undertaking eight different perceptual decision-making experiments. Our goals are to investigate (1) whether subject- and task-independent neural correlates of decision confidence exist, and (2) to what degree it is possible to build brain computer interfaces that can estimate confidence on a trial-by-trial basis. The experiments cover a wide range of perceptual tasks, which allowed to separate the task-related, decision-making features from the task-independent ones. Approach. Our systems train artificial neural networks to predict the confidence in each decision from EEG data and response times. We compare the decoding performance with three training approaches: (1) single subject, where both training and testing data were acquired from the same person; (2) multi-subject, where all the data pertained to the same task, but the training and testing data came from different users; and (3) multi-task, where the training and testing data came from different tasks and subjects. Finally, we validated our multi-task approach using data from two additional experiments, in which confidence was not reported. Main results. We found significant differences in the EEG data for different confidence levels in both stimulus-locked and response-locked epochs. All our approaches were able to predict the confidence between 15% and 35% better than the corresponding reference baselines. Significance. Our results suggest that confidence in perceptual decision making tasks could be reconstructed from neural signals even when using transfer learning approaches. These confidence estimates are based on the decision-making process rather than just the confidence-reporting process.

Governments and large private satellite operators face a strategic decision for multipayload satellite programs: whether to use large consolidated satellites with multiple payloads or constellations of a few smaller spacecraft (here a “distributed” system). One advantage of the latter is that it allows faster replacement of failed payloads and more efficient insertion of new technologies. The costs and the benefits of each option are a function of a myriad of uncertain factors, including the sequence of decisions that have to be made during the lifetime of the program. We present a general model based on decision and risk analysis to support the choice between these two satellite architectures for a long-term program in Earth's orbit. This model is built on probabilistic risk analysis of satellite vehicles and includes the operational decisions that may have to be made later, such as the construction and launch of new satellites, either because one fails or because a new technology has become available. The value of each architecture is based on that of the data that the satellite system provides when it is operated according to an optimal policy. We compute the value of each satellite architecture, reflecting the uncertainties involved and the decision maker's risk attitude in optimal management decisions. This model thus yields the sensitivity of both satellite architecture and operational decisions to factors such as risk aversion and the anticipated rate of technology advancement. We find that in many circumstances, more risk-averse decision makers may prefer distributed satellite architectures and the flexibility that they provide, even at a potentially higher initial cost. We also show that distributed systems tend to be preferred when the payload technology is expected to improve rapidly over time

A regional information-based multi-attribute and multi-objective decision-making approach for sustainable supplier selection and order allocation

Optimal condition-based maintenance decisions for systems with dependent stochastic degradation of components

Purpose– The purpose of this paper is to identify the salient risks borne by private firms and to investigate their effective risk response strategies in public-private partnership (PPP) low-cost housing (LCH) projects in Thailand.Design/methodology/approach– The paper employs grounded theory and case study methodologies to extensively analyze ten private firms’ risks and their strategic risk mitigation. As a result, the matrix of imperative risks’ root causes and the area of the project life cycle most exposed to their impacts were proposed. This included the framework of the risk response strategy application.Findings– The private firm's risk mitigation strategies depended on the salient risks’ impact and the private firms’ predictability and controllability of the risk outcome. This included the private firm's participating objectives and core business, decision maker's risk attitude, risk perception, experience of risk, and risk assessment skill, and the project life cycle phase of risk occurrence.Practical implications– Under the same characteristics of the immature PPP market in developing countries, the contractors’ effective risk management framework can be used as a guideline to complement the contractors’ decision making on risk response strategy selection and resource allocation in the PPP project life cycle.Originality/value– Despite working under the familiar environment of construction risk and generous payment method in PPP-LCH projects, only few contractors were successful. The examination of risks borne and effectively responded by the private sector increases the likelihood of the project success.

A spectral risk measure (SRM) is a weighted average of value at risk where the weighting function (also known as risk spectrum or distortion function) characterizes a decision maker's risk attitude. In this paper, we consider the case where the decision maker's risk spectrum is ambiguous and introduce a robust SRM model based on the worst risk spectrum from a ball of risk spectra centered at a nominal risk spectrum. When the ball consists of step-like risk spectra, we show that the robust SRM can be computed by solving a linear programming problem. For the general case, we propose a step-like approximation scheme and derive an error bound for the approximation. As an application, we apply the proposed robust SRM to one-stage stochastic optimization with the objective of minimizing the robust SRM and propose an alternating iterative algorithm for solving the resulting minimax optimization problem. Moreover, to examine stability of the robust spectral risk optimization model with respect to perturbation of observed data from the underlying exogenous uncertainty in data-driven environments, we investigate statistical robustness of the model and derive sufficient conditions for the required stability.

In this paper we provide a computational intelligence methodology for risk and disaster management using attitudinal and fuzzy modeling. We provide a paradigm representing the relationship among threats, events, control alternatives and losses. In evaluating a control alternative we look beyond the traditional expected value as a summary measure of expectation and the traditional variance as a measure of dispersion. We introduce a new measure of dispersion which incorporates the decision maker's attitude. We present a fuzzy model to use this attitudinal variance in conjunction with the attitudinal expected value in order to assess the overall value of control alternatives.

This paper develops a hybrid multiattribute decision‐making methodology for ranking project proposals (PPs) through a judicious usage of historical data of completed projects to determine attribute weights, enabling elimination of problems associated with projected data such as cost and schedule overruns of real‐world projects. The weights generated from data envelopment analysis are explicitly utilized for ranking PPs while allowing subjectivity to be ingeniously incorporated into the decision process. The new approach is implemented for ranking 25 PPs, and the rankings it yields are found indifferent to the decision maker's attitude, which ascertains the robustness of the ranking methodology.

We study a production lot-sizing problem inspired by a veterinary pharmaceutical plant in which demands are uncertain. First, we develop a deterministic capacitated lot-sizing model for the production of animal pesticides, performed in three machine-specific stages. Second, we propose a traditional robust optimisation formulation following the popular budget-of-uncertainty approach. Third, we derive a novel fragility-based approach that circumvents well-known issues with traditional robust optimisation approaches, such as the estimation of budgets of uncertainty, the over-conservatism of robust solutions and the sensitivity of solutions to the decision maker's risk attitude. The fragility-based approach is grounded in the idea of minimising violations, over the full uncertainty support, from a user-specified cost target. It avoids the estimation of budgets of uncertainty and produces less conservative solutions via explicit modelling of constraint violation. We demonstrate the effectiveness of our approach on instances built upon real data provided by our industrial partner, a major player in the Brazilian veterinary pharmaceutical sector. The results show that our fragility-based approach reduces average total costs across all instances and maintains greater model stability under different target estimations. It also preserves cost savings when bottlenecks are introduced in production and when inventory costs and capacities are varied.

Since Facility Layout Problem (FLP) affects the total manufacturing cost significantly, it can be considered as a critical issue in the early stages of designing Flexible Manufacturing Systems (FMSs), particularly in volatile environments where uncertainty in product demands is inevitable. This paper proposes a new mathematical model by using the Quadratic Assignment Problem formulation for designing an optimal machine layout for each period of a dynamic machine layout problem in FMSs. The product demands are considered as independent normally distributed random variables with known Probability Density Function (PDF), which changes from period to period at random. In this model, the decision maker's defined confidence level is also considered. The confidence level represents the decision maker's attitude about uncertainty in product demands in such a way that it affects the results of the problem significantly. To validate the proposed model, two different size test problems are generated at random. Since the FLP, especially in multi-period case is a hard Combinatorial Optimization Problem (COP), Simulated Annealing (SA) meta-heuristic resolution approach programmed in Matlab is used to solve the mathematical model in a reasonable computational time. Finally, the computational results are evaluated statistically.

Hydrothermal optimization of SiO2/water nanofluids based on attitudes in decision making

Investment Under Ambiguity with the Best and Worst in Mind

Decision-making for Civil Infrastructures Incorporating the time-Varying Effect of Risk Preference

We explore the challenge of selecting the best among a set of alternative IT investments. Solving this problem is important since the difference between alternative investment options may be drastic in terms of business results, both positive and negative. The resulting model takes as input a set of investment alternatives and a parameterized description of IT services, and provides as output a Preference Index for each alternative. The solution takes into account such characteristics as epistemic and aleatory uncertainty as well as the decision maker's attitude toward risk. Through a case study and a sensitivity analysis, we conclude that the model is useful in practice and robust; we also describe its domain of validity.

Managing reservoir uncertainty in petroleum field development: Defining a flexible production strategy from a set of rigid candidate strategies