Parametric regression analysis of imprecise and uncertain data in the fuzzy belief function framework

In this paper, parametric regression analyses including both linear and nonlinear regressions are investigated in the case of imprecise and uncertain data, represented by a fuzzy belief function. The parameters in both the linear and nonlinear regression models are estimated using the fuzzy evidential EM algorithm, a straightforward fuzzy version of the evidential EM algorithm. The nonlinear regression model is derived by introducing a kernel function into the proposed linear regression model. An unreliable sensor experiment is designed to evaluate the performance of the proposed linear and nonlinear parametric regression methods, called parametric evidential regression (PEVREG) models. The experimental results demonstrate the high prediction accuracy of the PEVREG models in regressions with crisp inputs and a fuzzy belief function as output.     

Topological structures of complex belief systems

The concepts of substantive beliefs and derived beliefs are defined, a set of substantive beliefs S like open set and the neighborhood of an element substantive belief. A semantic operation of conjunction is defined with a structure of an Abelian group. Mathematical structures exist such as poset beliefs and join‐semilattttice beliefs. A metric space of beliefs and the distance of belief depending on the believer are defined. The concepts of closed and opened ball are defined. S′ is defined as subgroup of the metric space of beliefs Σ and S′ is a totally limited set. The term s is defined (substantive belief) in terms of closing of S′. It is deduced that Σ is paracompact due to Stone's Theorem. The pseudometric space of beliefs is defined to show how the metric of the nonbelieving subject has a topological space like a nonmaterial abstract ideal space formed in the mind of the believing subject, fulfilling the conditions of Kuratowski axioms of closure. To establish patterns of materialization of beliefs we are going to consider that these have defined mathematical structures. This will allow us to understand better cultural processes of text, architecture, norms, and education that are forms or the materialization of an ideology. This materialization is the conversion by means of certain mathematical correspondences, of an abstract set whose elements are beliefs or ideas, in an impure set whose elements are material or energetic. Text is a materialization of ideology. © 2013 Wiley Periodicals, Inc. Complexity 19: 46–62, 2013     

Forecasting with imprecise probabilities

We review de Finetti’s two coherence criteria for determinate probabilities: coherence₁ defined in terms of previsions for a set of events that are undominated by the status quo – previsions immune to a sure-loss – and coherence₂ defined in terms of forecasts for events undominated in Brier score by a rival forecast. We propose a criterion of IP-coherence₂ based on a generalization of Brier score for IP-forecasts that uses 1-sided, lower and upper, probability forecasts. However, whereas Brier score is a strictly proper scoring rule for eliciting determinate probabilities, we show that there is no real-valued strictly proper IP-score. Nonetheless, with respect to either of two decision rules – Γ-maximin or (Levi’s) E-admissibility-+-Γ-maximin – we give a lexicographic strictly proper IP-scoring rule that is based on Brier score.     

Parameter estimation based on interval-valued belief structures

Parameter estimation based on uncertain data represented as belief structures is one of the latest problems in the Dempster–Shafer theory. In this paper, a novel method is proposed for the parameter estimation in the case where belief structures are uncertain and represented as interval-valued belief structures. Within our proposed method, the maximization of likelihood criterion and minimization of estimated parameter’s uncertainty are taken into consideration simultaneously. As an illustration, the proposed method is employed to estimate parameters for deterministic and uncertain belief structures, which demonstrates its effectiveness and versatility.     

Decision making with imprecise parameters

We analyze the impact of imprecise parameters on performance of an uncertainty-modeling tool presented in this paper. In particular, we present a reliable and efficient uncertainty-modeling tool, which enables dynamic capturing of interval-valued clusters representations sets and functions using well-known pattern recognition and machine learning algorithms. We mainly deal with imprecise learning parameters in identifying uncertainty intervals of membership value distributions and imprecise functions. In the experiments, we use the proposed system as a decision support tool for a production line process. Simulation results indicate that in comparison to benchmark methods such as well-known type-1 and type-2 system modeling tools, and statistical machine-learning algorithms, proposed interval-valued imprecise system modeling tool is more robust with less error.     

Data envelopment analysis with imprecise data

In original data envelopment analysis (DEA) models, inputs and outputs are measured by exact values on a ratio scale. Cooper et al. [Management Science, 45 (1999) 597–607] recently addressed the problem of imprecise data in DEA, in its general form. We develop in this paper an alternative approach for dealing with imprecise data in DEA. Our approach is to transform a non-linear DEA model to a linear programming equivalent, on the basis of the original data set, by applying transformations only on the variables. Upper and lower bounds for the efficiency scores of the units are then defined as natural outcomes of our formulations. It is our specific formulation that enables us to proceed further in discriminating among the efficient units by means of a post-DEA model and the endurance indices. We then proceed still further in formulating another post-DEA model for determining input thresholds that turn an inefficient unit to an efficient one.     

An uncertainty interchange format with imprecise probabilities

This paper addresses the problem of exchanging uncertainty assessments in multi-agent systems. Since it is assumed that each agent might completely ignore the internal representation of its partners, a common interchange format is needed. We analyze the case of an interchange format defined by means of imprecise probabilities, pointing out the reasons of this choice. A core problem with the interchange format concerns transformations from imprecise probabilities into other formalisms (in particular, precise probabilities, possibilities, belief functions). We discuss this so far little investigated question, analyzing how previous proposals, mostly regarding special instances of imprecise probabilities, would fit into this problem. We then propose some general transformation procedures, which take also account of the fact that information can be partial, i.e. may concern an arbitrary (finite) set of events.     

The conjunctive combination of interval-valued belief structures from dependent sources

To combine belief functions from reliable dependent sources, Denoeux proposed an operator called the cautious conjunctive rule. In this paper, the conjunctive combination of interval-valued belief structures (IBSs) from reliable dependent sources is investigated. Nonlinear optimization problems based on the cautious rule are constructed and solved to generate an unnormalized and a normalized cautious combination of two IBSs. In a similar manner, optimization problems used to combine multiple IBSs are also constructed. Furthermore, to deal with some situations in which the relative weights of IBSs must be considered, optimization problems considering relative weights are constructed to implement the unnormalized and normalized weighted cautious combination of IBSs. To verify the validity and usefulness of the conjunctive combination of IBSs, a trustworthiness evaluation problem of hospital information systems, which is employed in many hospitals of the Anhui province in China, is solved based on the normalized weighted cautious combination of IBSs.     

Data envelopment scenario analysis with imprecise data

In the existing DEA models, we have a centralized decision maker (DM) who supervises all the operating units. In this paper, we solve a problem in which the centralized DM encounters limited or constant resources for total inputs or total outputs. We establish a DEA target model that solves and deals with such a situation. In our model, we consider the decrease of total input consumption and the increase of total output production; however, in the existing DEA models, total output production is guaranteed not to decrease. Considering the importance of imprecise data in organizations, we define our model so as to deal with interval and ordinal data. A numerical illustration is provided to show the application of our model and the advantages of our approach over the previous one.     

A choice model with imprecise ordinal evaluations

We consider multicriteria choice problems where the actions are evaluated on ordinal criteria and where they can be assessed imprecisely. In order to select the subset of best actions, the pairwise comparisons between the actions on each criterion are modeled by basic belief assignments (BBAs). Dempsterʼs rule of combination is used for the aggregation of the BBAs of each pair of alternatives in order to express a global comparison between them on all the criteria. A model inspired by ELECTRE I is also proposed and illustrated by a pedagogical example.     

Additive DEA based on MCDA with imprecise information

This work exploits links between Data Envelopment Analysis (DEA) and multicriteria decision analysis (MCDA), with decision making units (DMUs) playing the role of decision alternatives. A novel perspective is suggested on the use of the additive DEA model in order to overcome some of its shortcomings, using concepts from multiattribute utility models with imprecise information. The underlying idea is to convert input and output factors into utility functions that are aggregated using a weighted sum (additive model of multiattribute utility theory), and then let each DMU choose the weights associated with these functions that minimize the difference of utility to the best DMU. The resulting additive DEA model with oriented projections has a clear rationale for its efficiency measures, and allows meaningful introduction of constraints on factor weights.     

Simulated annealing with noisy or imprecise energy measurements

The annealing algorithm (Ref. 1) is modified to allow for noisy or imprecise measurements of the energy cost function. This is important when the energy cannot be measured exactly or when it is computationally expensive to do so. Under suitable conditions on the noise/imprecision, it is shown that the modified algorithm exhibits the same convergence in probability to the globally minimum energy states as the annealing algorithm (Ref. 2). Since the annealing algorithm will typically enter and exit the minimum energy states infinitely often with probability one, the minimum energy state visited by the annealing algorithm is usually tracked. The effect of using noisy or imprecise energy measurements on tracking the minimum energy state visited by the modified algorithms is examined.The research reported here has been supported under Contracts AFOSR-85-0227, DAAG-29-84-K-0005, and DAAL-03-86-K-0171 and a Purdue Research Initiation Grant.     

Topological structures of complex belief systems (II): Textual materialization

Mythical and religious belief systems in a social context can be regarded as a conglomeration of sacrosanct rites, which revolve around substantive values that involve an element of faith. Moreover, we can conclude that ideologies, myths and beliefs can all be analyzed in terms of systems within a cultural context. The significance of being able to define ideologies, myths and beliefs as systems is that they can figure in cultural explanations. This, in turn, means that such systems can figure in logic‐mathematical analyses. © 2013 Wiley Periodicals, Inc. Complexity 19: 50–62, 2013     

Using probability trees to compute marginals with imprecise probabilities

This paper presents an approximate algorithm to obtain a posteriori intervals of probability, when available information is also given with intervals. The algorithm uses probability trees as a means of representing and computing with the convex sets of probabilities associated to the intervals.     

Structural reliability analysis with imprecise random and interval fields

This paper investigates the issue of reliability assessment for engineering structures involving mixture of stochastic and non-stochastic uncertain parameters through the Finite Element Method (FEM). Non-deterministic system inputs modelled by both imprecise random and interval fields have been incorporated, so the applicability of the structural reliability analysis scheme can be further promoted to satisfy the intricate demand of modern engineering application. The concept of robust structural reliability profile for systems involving hybrid uncertainties is discussed, and then a new computational scheme, namely the unified interval stochastic reliability sampling (UISRS) approach, is proposed for assessing the safety of engineering structures. The proposed method provides a robust semi-sampling scheme for assessing the safety of engineering structures involving multiple imprecise random fields with various distribution types and interval fields simultaneously. Various aspects of structural reliability analysis with multiple imprecise random and interval fields are explored, and some theoretically instructive remarks are also reported herein.     

Elitist genetic algorithm for assignment problem with imprecise goal

The objective of this research paper is to solve a generalized assignment problem with imprecise cost(s)/time(s) instead of precise one by elitist genetic algorithm (GA). Here, the impreciseness of cost(s)/time(s) has been represented by interval valued numbers, as interval valued numbers are the best representation than others like random variable representation with a known probability distribution and fuzzy representation. To solve these types of problems, an elitist GA has been developed with interval valued fitness function. In this developed GA, the existing ideas about the order relations of interval valued numbers have been modified from the point of view of two types of decision making viz., optimistic decision making and pessimistic decision making. This modified approach has been used in the selection process for selecting better chromosomes/individuals for the next generation and in finding the best as well as the worst chromosomes/individuals in each generation. Here two new crossover schemes and two new mutation schemes have been introduced. In order to maintain the feasibility with crossover operations, a repair algorithm has been suggested. Extensive comparative computational studies based on different parameters of our developed algorithm on one illustrative example have also been reported.     

Influence diagrams with super value nodes involving imprecise information

The concept of super value nodes was established to allow dynamic programming to be performed within the theory of influence diagrams and to reduce the computational complexity in solving problems by means of influence diagrams. This paper is focused on how influence diagrams with super value nodes are affected by the presence of imprecise information. We analyze how to reduce the complexity when evaluating an influence diagram in this framework by modelling these kinds of nodes and random magnitudes in terms of fuzzy random variables. Finally, an applied example of the theoretical results is developed.     

A fuzzy goal programming method with imprecise goal hierarchy

Two most widely used approaches to treating goals of different importance in goal programming (GP) are: (1) weighted GP, where importance of goals is modelled using weights, and (2) preemptive priority GP, where a goal hierarchy is specified implying infinite trade-offs among goals placed in different levels of importance. These approaches may be too restrictive in modelling of real life decision making problems. In this paper, a novel fuzzy goal programming method is proposed, where the hierarchical levels of the goals are imprecisely defined. The imprecise importance relations among the goals are modelled using fuzzy relations. An additive achievement function is defined, which takes into consideration both achievement degrees of the goals and degrees of satisfaction of the fuzzy importance relations. Examples are given to illustrate the proposed method.     

Reasoning with contextual graphs

Decision trees allow the modeling of event-dependent reasoning, but do not consider the dynamics of contextual changes in reasoning. In the framework of the SART project, which aims at the design and development of an intelligent support system for subway regulators, we have to model highly contextual reasoning. We introduce the notion of contextual graph to take into account temporal and context-based reasoning. This model relies on observed reasoning modes in which the context and its dynamics are essential.