直觉模糊环境下考虑有限理性特征的决策方法

针对决策者具有有限理性的心理特征且属性权重和自然状态发生概率完全未知的直觉模糊多属性决策问题,提出了一种基于前景理论和证据理论的多属性决策方法。首先,利用证据理论得到各自然状态发生的概率,进而确定自然状态的决策权重函数;其次,运用正态分布概率密度函数设计直觉模糊决策参考点,并依据属性值与决策参考点之间的差异计算价值函数矩阵,从而获得前景价值矩阵;以综合前景价值最大化为准则构建最优化模型用以确定属性权重,并依据各方案的综合前景价值进行优劣排序。最后,将所提方法应用于对游戏产品的选择开发实例中。对比实验表明,运用所提方法得到的决策结果合理可靠,且更能体现决策者的原始决策信息。     

Robustness analysis for systems with ellipsoidal uncertainty

This note derives an explicit expression for computing the robustness margin for affine systems whose real and complex coefficients are related by an ellipsoidal constraint. The expression, which is an application of a result by Chen, Fan, and Nett for rank-one generalized structured singular-value problems, extends and unifies previous results on robustness margin computation for systems with ellipsoidal uncertainty. © 1998 John Wiley & Sons, Ltd.     

On the methods of decision making under uncertainty with probability information

By considering the decision maker's attitude of profit and risk, we propose an alternative selection method that can include the methods of decision making under ignorance and decision making under risk as special cases. An index to measure the decision maker's risk‐averse degree is proposed. With a given optimistic level of profit and risk, the evaluation results of the alternatives can be obtained with a geometric ordered weighted average (OWA) operator and a basic defuzzification distribution (BADD) neat OWA operator. Some properties of these two kinds of OWA operator in the problem of decision making under uncertainty are also proposed. © 2004 Wiley Periodicals, Inc. Int J Int Syst 19: 1217–1238, 2004.     

Adaptive suboptimal tracking under bounded Lipshitz uncertainty in a discrete minimum-phase object

We consider a deterministic problem of asymptotically suboptimal tracking of a bounded reference signal with the output of a scalar discrete minimum-phase object with unknown transition function under a bounded external disturbance and bounded nonlinear stationary uncertainty satisfying a generalized Lipschitz condition. Suboptimality of the tracking is achieved with online estimation and compensation for nonparametric Lipschitz uncertainty in addition to estimating an unknown transition function. To solve the problem we use two parallel estimation algorithms, one of which provides stability for the closed adaptive system, the other, asymptotic tracking optimality with desired accuracy.     

Speech enhancement using MMSE estimation under phase uncertainty

Most of the speech enhancement algorithms process the amplitudes of speech, but the phase of noisy speech is left unprocessed as it may cause undesired artifacts. Recently, short time Fourier transform based single channel speech enhancement algorithms are developed by considering uncertain prior knowledge of phase. The uncertain knowledge of the phase is obtained from the phase reconstruction algorithms. The goal of this paper is to develop joint minimum mean square error estimate of complex speech coefficients given uncertainty phase (CUP) information by considering Nagakami probability density function (PDF) and gamma PDF as speech spectral amplitude priors and generalized gamma PDF for noise prior. Estimators like amplitudes given uncertainty phase, which uses uncertain phase only for amplitude estimation and not for phase improvement are developed. Experimental results shows that incorporating uncertain phase information improves quality and intelligibility of speech. Also novel phase-blind estimators are developed using Nagakami PDF/gamma as speech priors and generalized gamma as noise prior. Finally comparison of all estimators using uncertain prior phase information is discussed and how initial phase information affects the enhancement process is analyzed with novel estimators. For comparison of all the derived estimators, the speech signals uttered by male and female speakers are taken from TIMIT database. The proposed CUP estimators outperforms the existing algorithms in terms of objective performance measure segmental signal to noise ratio, phase signal to noise ratio, perceptual evaluation of speech quality, short time objective intelligibility.     

Exploring scientific information for policy making under deep uncertainty

Each actor evaluating potential management strategies brings her/his own distinct set of objectives to a complex decision space of system uncertainties. The diversity of these objectives and uncertainties requires detailed and rigorous analyses that respond to multifaceted challenges. The utility of this information depends on the accessibility of scientific information to decision makers. This paper demonstrates data visualization tools for presenting scientific results to decision makers in two case studies, La Paz/El Alto, Bolivia, and Yuba County, California. Visualization output from the case studies combines spatiotemporal, multivariate and multirun/multiscenario information to produce information corresponding to the objectives and uncertainties described by key actors. These tools can manage complex data and distill scientific information into accessible formats. Using the visualizations, scientists and decision makers can navigate the decision space and potential objective trade-offs to facilitate discussion and consensus building. These efforts can help identify stable negotiated agreements between different stakeholders.     

Adaptive stabilization of minimum phase plant under Lipschitz uncertainty

Consideration was given to the problem of adaptive stabilization of the minimum phase plant under Lipschitz uncertainty and bounded external disturbance with unknown upper bound. The proposed adaptive stabilization algorithm is based on the recurrent set estimation of the unknown plant parameters, Lipschitz uncertainty, and the upper bound of the external disturbance and includes the online verification of the control plant model.     

Comparing paradigms for strategy learning of route choice with traffic information under uncertainty

This paper aims to model the traveller's day-to-day route choice in the case of an Advanced Traveller Information System (ATIS) through two learning paradigms: reinforcement-based and belief-based. The reinforcement learning approach is adopted in both a basic version and an extended one. Similarly, the belief-learning approach is adopted in both a Joint Strategy Fictitious Play version and in a Bayesian-learning one. All the models are compared and validated based on data collected by means of a stated preference experiment. The models explicitly account for the reliability of the information system, as this interacts with the inherent dispersion of network travel times and determines the overall level of uncertainty affecting the travellers’ adaptive learning behaviour. The experiment is then designed to simulate different levels of reliability for the ATIS. Results show that for intermediate and high levels of information accuracy, joint strategy fictitious play best predicts the respondents’ route choice behaviour under information provision, suggesting that a best-reply strategy is used by travellers for their route choices. In low information accuracy, the result suggests the payoff variability moves the choice behaviour toward randomness. The proposed approach provides useful tools to model travellers’ adaptive route choice behaviour and contributes to the support of effective ATIS design.     

Identification and prediction propagation of uncertainty in models with bounded noise

The identification of measurement, parametric, and structural model uncertainty is considered for models from observations with bounded noise. A min-max estimate for the upper bound of the structural model uncertainty is presented. The propa- gation of the parametric and structural model uncertainty, as a result of the obser- vation uncertainty bounds to the model prediction error, is examined. A simple water quality model is used to illustrate the different steps.     

The effectiveness of strategic information systems planning under environmental uncertainty

Researchers have suggested that more extensive strategic information systems planning (SISP) in an uncertain environment produces greater planning success. Managers must decide whether, and if so when, to perform such SISP. Our study tested the effect of SISP phases on planning success in more and less uncertain environments.A questionnaire assessed SISP in terms of strategic awareness, situation analysis, strategy conception, strategy formulation, and strategy implementation planning phases. It inquired about environmental uncertainty as dynamism, heterogeneity, and hostility. Finally, it measured SISP success as a composite of alignment, analysis, cooperation, and capabilities. One hundred and sixty-one IS executives provided data in a postal survey.More extensive strategy formulation uniformly predicted successful planning in more uncertain environments, whereas strategic awareness generally predicted it in less uncertain ones. Strategy conception predicted it in neither more nor less uncertain environments. More extensive planning is thus not uniformly successful in either environment but depends on the nature of the uncertainty.     

Planning under uncertainty using model predictive control for information gathering

This paper considers trajectory planning problems for autonomous robots in information gathering tasks. The objective of the planning is to maximize the information gathered within a finite time horizon. It is assumed that either the Extended Kalman Filter (EKF) or the Extended Information Filter (EIF) is applied to estimate the features of interest and the information gathered is expressed by the covariance matrix or information matrix. It is shown that the planning process can be formulated as an optimal control problem for a nonlinear control system with a gradually identified model. This naturally leads to the Model Predictive Control (MPC) planning strategy, which uses the updated knowledge about the model to solve a finite horizon optimal control problem at each time step and only executes the first control action. The proposed MPC framework is demonstrated through solutions to two challenging information gathering tasks: (1) Simultaneous planning, localization, and map building (SPLAM) and (2) Multi-robot Geolocation. It is shown that MPC can effectively deal with dynamic constraints, multiple robots/features and a range of objective functions.     

Robustness of non-linear stochastic optimal control for quasi-Hamiltonian systems with parametric uncertainty

The robustness of non-linear stochastic optimal control for quasi-Hamiltonian systems with uncertain parameters is studied. Based on the independence of uncertain parameters and stochastic excitations, the non-linear stochastic optimal control for the nominal quasi-Hamiltonian system with average-value parameters is first obtained by using the stochastic averaging method and stochastic dynamical programming principle. Then, the means and standard deviations of root-mean-square responses, control effectiveness and control efficiency for the uncertain quasi-Hamiltonian system are calculated by using the stochastic averaging method and the probabilistic analysis. By introducing the sensitivity of the variation coefficients of controlled root-mean-square responses, control effectiveness and control efficiency to those of uncertain parameters, the robustness of the non-linear stochastic optimal control is evaluated. Two examples are given to illustrate the proposed control procedure and its robustness.     

Robustness of model-based fault diagnosis: Decisions with information-gap models of uncertainty

Fault diagnosis is analysed here as a decision between alternative hypotheses, based on uncertain evidence. W e consider severe lack of information, and perceive the uncertainty as an information gap between what is known, and what needs to be known for a perfect decision. This uncertainty is quantified with info-gap models of uncertainty, which require less information than probabilistic models. Previous work with convex set-models is extended to linear info-gap models which are not necessarily convex, as well as to more general info-gap models with arbitrary expansion properties. We define a decision algorithm based on info-gap models and prove three theorems, one establishing the connection with the earlier work on convex models, the other two showing that the algorithm is maximally robust for linear info-gap models as well as for general infogap models of uncertainty. An illustrative example is presented which shows how these results can be used for optimizing the design of a model-based fault diagnosis algorithm.     

Robustness considerations for p-step matrix integrators with uncertainty in the continuous system mode

Robustness measures for p-step matrix integrators are established. These measures are the quantitative bounds for either structured or unstructured perturbations existing in continuous-time systems to ensure that discrete versions of those systems obtained using p-step matrix integrators remain stable. Examples are given to illustrate the usefulness of the proposed measures. The effect of the sampling time T, the choice of the discretizing scheme, and the integrator step size on these robustness measures is discussed through examples.     

Progress under bounded fairness

Summary. Progress is investigated for a shared-memory distributed system with a weak form of fault tolerance that allows processes to stop and restart functioning without notification. The concept of bounded fairness is introduced to formalize bounded delay under the assumption that each family of related processes continuously contains at least one active member. This is a generalization of wait-freedom, and also of a finitary form of weak fairness. Several useful proof rules are stated and proved. In a system with bounded fairness, a wait-free process can be constructed by forming a new process in which processes from the various families are scheduled in a round robin way. The theory is applied to prove progress within bounded delay for a linearizing concurrent data-object in shared memory. The safety properties of this algorithm have been treated elsewhere. Received: April 1998 / Accepted: March 1999     

Fixed-point smoothing with non-independent uncertainty using covariance information

Recursive filtering and fixed-point smoothing algorithms, using covariance information, are designed in systems with uncertain observations, when the variables describing the uncertainty are not necessarily independent. It is assumed that the observations are perturbed by white plus coloured noises, and the autocovariance functions of the signal and coloured noise are given in a semidegenerate kernel form. The estimators are obtained by the orthogonal projection technique and using an invariant imbedding method. The algorithms can be applied for estimating stationary and non-stationary signals.