Uncertainty In Expert Systems Research Articles

Neutrosophic Logic Approach for Evaluating Learning Management Systems

Uncertainty in expert systems is essential re- search point in artificial intelligence domain. Uncertain knowledge representation and analysis in expert systems is one of the challenges that takes researchers concern as different uncertainty types which are imprecision, vague- ness, ambiguity, and inconsistence need different han- dling models. This paper reviews some of the multi- valued logic models which are fuzzy set, intuitionistic fuzzy set, and suggests a new approach which is neutro- sophic set for handling uncertainty in expert systems to derive decisions. The paper highlights, compares and clarifies the differences of these models in terms of the application area of problem solving. The results shows that neutrosophic expert system for learning manage- ment systems evaluation as a better option to simulate human thinking than fuzzy and intuitionistic fuzzy logic because fuzzy logic can't express false membership and intuitionistic fuzzy logic is not able to handle indetermi- nacy of information.

A practical review and taxonomy of fuzzy expert systems: methods and applications

PurposeExpert systems are computer-based systems that mimic the logical processes of human experts or organizations to give advice in a specific domain of knowledge. Fuzzy expert systems use fuzzy logic to handle uncertainties generated by imprecise, incomplete and/or vague information. The purpose of this paper is to present a comprehensive review of the methods and applications in fuzzy expert systems.Design/methodology/approachThe authors have carefully reviewed 281 journal publications and 149 conference proceedings published over the past 37 years since 1982. The authors grouped the journal publications and conference proceedings separately accordingly to the methods, application domains, tools and inference systems.FindingsThe authors have synthesized the findings and proposed useful suggestions for future research directions. The authors show that the most common use of fuzzy expert systems is in the medical field.Originality/valueFuzzy logic can be used to manage uncertainty in expert systems and solve problems that cannot be solved effectively with conventional methods. In this study, the authors present a comprehensive review of the methods and applications in fuzzy expert systems which could be useful for practicing managers developing expert systems under uncertainty.

Interval-type and affine arithmetic-type techniques for handling uncertainty in expert systems

Expert knowledge consists of statements S j (facts and rules). The facts and rules are often only true with some probability. For example, if we are interested in oil, we should look at seismic data. If in 90% of the cases, the seismic data were indeed helpful in locating oil, then we can say that if we are interested in oil, then with probability 90% it is helpful to look at the seismic data. In more formal terms, we can say that the implication “if oil then seismic” holds with probability 90%. Another example: a bank A trusts a client B, so if we trust the bank A, we should trust B too; if statistically this trust was justified in 99% of the cases, we can conclude that the corresponding implication holds with probability 99%. If a query Q is deducible from facts and rules, what is the resulting probability p ( Q ) in Q? We can describe the truth of Q as a propositional formula F in terms of S j , i.e., as a combination of statements S j linked by operators like &, ∨ , and ¬ ; computing p ( Q ) exactly is NP-hard, so heuristics are needed. Traditionally, expert systems use technique similar to straightforward interval computations: we parse F and replace each computation step with corresponding probability operation. Problem: at each step, we ignore the dependence between the intermediate results F j ; hence intervals are too wide. Example: the estimate for P ( A ∨ ¬ A ) is not 1. Solution: similar to affine arithmetic, besides P ( F j ) , we also compute P ( F j & F i ) (or P ( F j 1 & ⋯ & F j d ) ), and on each step, use all combinations of l such probabilities to get new estimates. Results: e.g., P ( A ∨ ¬ A ) is estimated as 1.

Uncertainty in expert systems and credit granting decisions

One of the most popular utilization of expert systems is supporting credit granting decisions. Usually, certain systems without possibilities of representing of uncertain knowledge are used. The main aim of this paper is to compare certain and uncertain expert systems supporting credit granting decisions, and stating which one is superior over another.

Affine arithmetic-type techniques for handling uncertainty in expert systems

Expert knowledge consists of statements S(subscript j): facts and rules. The expert's degree of confidence in each statement S(subscript j) can be described as a (subjective) probability. For example, if we are interested in oil, we should look at seismic data (confidence 90%); a bank A trusts a client B, so if we trust A, we should trust B too (confidence 99%). If a query Q is deducible from facts and rules, what is our confidence p(Q) in Q? We can describe Q as a propositional formula F in terms of Si; computing p(Q) exactly is N P-hard, so heuristics are needed. Traditionally, expert systems use technique similar to straightforward interval computations: we parse F and replace each computation step with corresponding probability operation. The problem with this approach is that at each step, we ignore the dependence between the intermediate results F(subscript j); hence intervals are too wide. For example, the estimate for P(AV-A) is not 1. In this thesis, we propose a new solution to this problem; similarly to affine arithmetic, besides P(F(subscript j)), we also compute P(F(subscript j) & F(subscript i)) (or P(F(subscript j1) & ... & F(subscript jk)), and on each step, use all combinations of l such probabilities to get new estimates. As a result, for the above stated e.g., P(Av-A) is estimated as 1.

Combining belief functions when evidence conflicts

The use of belief functions to represent and to manipulate uncertainty in expert systems has been advocated by some practitioners and researchers. Others have provided examples of counter-intuitive results produced by Dempster's rule for combining belief functions and have proposed several alternatives to this rule. This paper presents another problem, the failure to balance multiple evidence, then illustrates the proposed solutions and describes their limitations. Of the proposed methods, averaging best solves the normalization problems, but it does not offer convergence toward certainty, nor a probabilistic basis. To achieve convergence, this research suggests incorporating average belief into the combining rule.

Inference in belief networks: A procedural guide

Belief networks are popular tools for encoding uncertainty in expert systems. These networks rely on inference algorithms to compute beliefs in the context of observed evidence. One established method for exact inference on belief networks is the probability propagation in trees of clusters (PPTC) algorithm, as developed by Lauritzen and Spiegelhalter and refined by Jensen et al. PPTC converts the belief network into a secondary structure, then computes probabilities by manipulating the secondary structure. In this document, we provide a self-contained, procedural guide to understanding and implementing PPTC. We synthesize various optimizations to PPTC that are scattered throughout the literature. We articulate undocumented “open secrets” that are vital to producing a robust and efficient implementation of PPTC. We hope that this document makes probabilistic inference more accessible and affordable to those without extensive prior exposure.

Measures of uncertainty in expert systems

This paper compares four measures that have been advocated as models for uncertainty in expert systems. The measures are additive probabilities (used in the Bayesian theory), coherent lower (or upper) previsions, belief functions (used in the Dempster-Shafer theory) and possibility measures (fuzzy logic). Special emphasis is given to the theory of coherent lower previsions, in which upper and lower probabilities, expectations and conditional probabilities are constructed from initial assessments through a technique of natural extension. Mathematically, all the measures can be regarded as types of coherent lower or upper previsions, and this perspective gives some insight into the properties of belief functions and possibility measures. The measures are evaluated according to six criteria: clarity of interpretation; ability to model partial information and imprecise assessments, especially judgements expressed in natural language; rules for combining and updating uncertainty, and their justification; consistency of models and inferences; feasibility of assessment; and feasibility of computations. Each of the four measures seems to be useful in special kinds of problems, but only lower and upper previsions appear to be sufficiently general to model the most common types of uncertainty.

Modeling uncertainty using enhanced tree structures in expert systems

Network structures, called belief networks, have been shown to be effective for representing uncertainty in expert systems. A problem faced when making inferences in belief networks is that schemes to propagate beliefs are generally of exponential complexity. A special class of networks, called trees, have been shown to provide an efficient framework for propagating beliefs. In this paper, we present a scheme called star-decomposition, originally proposed by Lazarsfeld [1966], to convert belief networks into trees. This scheme introduces auxiliary variables to represent higher order dependencies in tree structures. Such structures are called enhanced tree structures. We also describe a simple partitioning technique that creates local event groups which extends the applicability of star-decomposition. A framework is presented that identifies classes of belief networks that may be exactly represented using enhanced tree structures. For belief networks that are not amenable to exact representation, an enhanced tree structure preserves more dependencies in the belief network than representations that do not use the star-decomposition technique. The potential benefit of using enhanced trees as compared to simple tree structures is demonstrated.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Log‐Linear Models in Expert Systems

Abstract: The paper describes how log‐linear models can be used to deal with uncertainty in expert systems, avoiding the common problems of many probability‐based expert systems. After a general introduction to log‐linear models, including hierarchical models, maximum likelihood estimation for poissonian and multinomial sampling is described and parametric and structural learning methods are illustrated by simple examples. Finally, a traffic engineering example is given.

Mental health care for depressed older adults

change and uterine activity as predictors of preterm delivery. American Journal of Perinatology, 6. 185-190. Copper, R., Goldberg, R., Davis, R., Cutter, G., DuBard, M., Corliss, D., & Andrews, J. (1990). Warning symptoms: uterine contractions, and cervical exam findings in women at risk for preterm labor. American Journal of Obstetrics and Gynecology, 162, 748-754. Grzymala-Busse, .I. (1991). Managing Uncertainty in Expert Systems. Boston, MA: Kluwer Academic Publishers. Hinshaw, A. (1989). Nursing science: The Challenge to develop knowledge. Nursing Science Quarterly, 2, 162-171. Holbrook, R., Laros, R., & Creasy, R. (1989). Evaluation of a risk-scoring system for prediction of preterm labor. American Journal of Perinatology, 6, 62-68. Johnson, P. (1983). What kind of expert should a system be? The Journal of Medicine and Philosophy, 8, 17-97. Keirse, M. (1989). An evaluation of formal risk scoring for preterm birth. American Journal of Perinatology. 6, 226-233. Lockwood, C., Senyei, A., Dische, M., Casal, D., Shah. K., Thung, S., Jones, L., Deligdisch, L., & Garite, T. (1991). Fetal fibronectin in cervical and’vaginal secretions as a predictor of preterm delivery. New England Journal of Medicine, 315, 669-614. McGregor, J., French, J., Richter, R., France-Buff, A., Johnson, A., Hillier, S., Judson, F., & Todd, J. (1990). Antenatal microbiologic and maternal risk factors associated with prematurity. American Journal of Obstetrics and Gynecology, 163, 1465-1473. Nunnally, J. (1978). Psychometric theory. New York. NY: McGraw-Hill. Polanyi, M. (1958). Personal knowledge: Towards a postcritical philosophy. Chicago, IL: University of Chicago Press. Quinlan, R. (1983). Learning efficient classification procedures and their application to chess end games. In Michalski, Carbonelli, & Mitchell (Eds.) Machine learning: An artificial intelligence approach (pp. 463-482). Palo Alto, CA: Tioga Publishing Company. Woolery, L. (1992) Knowledge acquisitionfor assessmenr of preterm labor risk. Unpublished doctoral dissertation. University of Kansas, Lawrence, KS.

On uncertainty management in fuzzy inference procedures

Fuzzy inference procedures are becoming more useful in the management of uncertainty in expert systems. In this paper, we describe a fuzzy inference procedure which deals with the management of uncertainty in rule-based expert systems. The advantage of this procedure is its simplicity, which in turn makes this architecture easily extendible and useful in real-time environments. The advantage of using fuzzy logic is discussed and illustrated. Potential applications for real-time environments include decision making in the fields of intelligent controllers, command, control, and intelligent robotics systems.

Theory of evidence ? A survey of its mathematical foundations, applications and computational aspects

The mathematical theory of evidence has been introduced by Glenn Shafer in 1976 as a new approach to the representation of uncertainty. This theory can be represented under several distinct but more or less equivalent forms. Probabilistic interpretations of evidence theory have their roots in Arthur Dempster's multivalued mappings of probability spaces. This leads to random set and more generally to random filter models of evidence. In this probabilistic view evidence is seen as more or less probable arguments for certain hypotheses and they can be used to support those hypotheses to certain degrees. These degrees of support are in fact the reliabilities with which the hypotheses can be derived from the evidence. Alternatively, the mathematical theory of evidence can be founded axiomatically on the notion of belief functions or on the allocation of belief masses to subsets of a frame of discernment. These approaches aim to present evidence theory as an extension of probability theory. Evidence theory has been used to represent uncertainty in expert systems, especially in the domain of diagnostics. It can be applied to decision analysis and it gives a new perspective for statistical analysis. Among its further applications are image processing, project planning and scheduling and risk analysis. The computational problems of evidence theory are well understood and even though the problem is complex, efficient methods are available.

Certainty Factor Algebras: Comparing Conventional Mappings and Experimental Results

AbstractAmong the various means that have been advanced for handling uncertainty in expert systems, certainty factor (CF) approaches have been widely adopted in both individual expert system applications and shells for building such systems. Nevertheless, CF approaches have been challenged on analytical grounds. This paper examines the descriptive efficacy of CF approaches from an empirical standpoint. Specifically, it compares conventional CF methods for certainty‐combining situations in a rule's premise with experimentally observed behaviors. The experimental data are subjected to ‘hit’ analyses that present the percentages of experts adhering to conventional algebraic means for combining CFs. The findings indicate that anywhere from about one‐fourth up to nine‐tenths of subjects combine certainties in a way consistent with CF algebras conventionally mapped into various certainty‐combining situations. Put another way, conventional CF algebra mappings are inadequate for describing anywhere from 10% to 75% of human behaviors across the situations studied here. This empirical evidence suggests that knowledge engineers should be cautious about adopting conventional CF algebras, particularly under certain circumstances identified in this study. It also suggests the prudence of considering uncertainty treatments other than conventional certainty factor algebras.

Backpropagation neural networks for fuzzy logic

Expert systems play a crucial role in the application of artificial intelligence to real problems. There are numerous methods of dealing with uncertainty in expert systems. Fuzzy logic is one such approach, in which the uncertainty is represented by possibility distributions for the antecedents and consequent of a rule. An uncertain input can be propagated to the consequent by a variety of mechanisms. This generality results in a higher computational burden for the system. More importantly, a means of controlling the response of the system to variations in input conditions is needed. In this paper, feedforward neural networks are proposed as a means of controlling this generality as well as providing the parallel computation necessary for fuzzy logic. It is demonstrated that these networks can learn and extrapolate complex relationships between antecedents and consequents for rules containing single and conjunctive antecedent clauses. Also, multiple compatible rules can be stored in a single network structure, increasing the efficiency of rule storage, and providing a natural mechanism for conflict resolution.

Using certainty factors and possibility theory methods in a tillage selection expert system

Both certainty factors and possibility theory have been successfully used to represent uncertainty in expert systems. Both of these methods were investigated during the development of a rule-based expert system for selecting tillage alternatives for corn and soybean production in Ontario. The expert system was used to test uncertainty management methods and to determine the appropriateness of possibility theory and certainty factors for representing and combining uncertainty in the knowledge base. Several techniques for representing uncertainty with these two methods are reviewed and the strengths and weaknesses of the two approaches, in terms of this project, are discussed. For expert systems in which evidence from many sources is accumulated toward a hypothesis, certainty factors appear to be more responsive than possibility theory methods. The system was validated against human experts and found to perform extremely well.

Medical Informatics and Clinical Decision Making: The Science and the Pragmatics

There are important scientific and pragmatic synergies between the medical decision making field and the emerging discipline of medical informatics. In the 1970s, the field of medicine forced clinically oriented artificial intelligence (AI) researchers to develop ways to manage explicit statements of uncertainty in expert systems. Classic probability theory was considered and discussed, but it tended to be abandoned because of complexities that limited its use. In medical AI systems, uncertainty was handled by a variety of ad hoc models that simulated probabilistic considerations. To illustrate the scientific interactions between the fields, the author describes recent work in his laboratory that has attempted to show that formal normative models based on probability and decision theory can be practically melded with AI methods to deliver effective advisory tools. In addition, the practical needs of decision makers and health policy planners are increasingly necessitating collaborative efforts to develop a computing and communications infrastructure for the decision making and informatics communities. This point is illustrated with an example drawn from outcomes management research.

Combining evidences for evidential reasoning

An iterative procedure is described as a generalization of Bayes' method of updating an a priori assignment over the power set of the frame of discernment using uncertain evidence. In the context of probability kinematics the law of commutativity holds and the convergence is well behaved. the probability assignments of each updating evidence is retained. A general assignment method is also discussed for combining evidences without reference to any prior. the methods described here can be used in the field of Artificial Intelligence for common-sense reasoning and more specifically for treating uncertainty in Expert Systems. They are also relevant for nonmonotonic reasoning, abduction, and learning theory.

Fuzzy logic in commercial expert systems — Results and prospects

This paper surveys the use of fuzzy methods in commercial applications of the technology of expert systems and in commercial products which aim to support such applications. It attempts to evaluate the utility of such an approach to uncertainty management compared to other well known methods of handling uncertainty in expert systems. Starting from this base it attempts an evaluation of the prospects for fuzzy expert systems in the medium term. As a survey it attempts to list applications and commercial products as comprehensively as is practical and includes an extensive bibliography on the topic.

Psychological validity of uncertainty combining rules in expert systems

Abstract: In recent years, an increasing amount of research in Artificial Intelligence has focused on the representation and manipulation of uncertainty in expert systems. New approaches have been developed and justified because of their mathematical rigor or simplicity, cautiousness, programmability, and/or ability to capture the essence of natural language. Little attention has been paid to the psychological validity of any approach, new or old. To explore the psychological validity of rules that combine uncertainties, Oak Ridge National Laboratory (ORNL) has developed a computer program known as LES. Four applications of LES revealed that subjects’ natural combining rules are (1) not best modeled by any generally accepted uncertainty approach and (2) may be highly idiosyncratic. Knowledge Engineers should be aware that cognitive representations of knowledge in expert systems are not routinely being matched with combining rules actually used by experts. Frustrating development activities and highly unsatisfactory expert system performance may result.