Design a new mixed expert decision aiding system using fuzzy ELECTRE III method for vendor selection.
ABSTRACT Any decision process deals with two different concerns as its cornerstones, evaluating the alternatives and ranking them based on their performances. In any decision process, the former phase is usually the premise of the latter one. Alternatives’ evaluation is the concept that largely depends on the experts and their expertise, which increase uncertainty in the decision-making process. In addition to all proposed methods for having the experts’ knowledge as evaluations of the alternatives, utilizing expert decision support systems (EDSS) can be a sensible response to such a need. Having evaluated the alternatives in the first phase of a decision-making process, the second phase of the process deals with the ranking the alternatives based on their performances obtained from the first phase. In this paper, we discuss the architecture of a fuzzy system including both modules, utilizing fuzzy concept for dealing with the uncertainty of the problem. Concerning the problem we had been dealt with, our system comprises a fuzzy evaluation module, which is a fuzzy expert system and an appropriate tool for evaluating the existing alternatives promptly and smoothly, without the imposed time delays by the experts to propose their comments and the uncertainty of such expertise-based comments, and a fuzzy ranking module, which is a fuzzy version of ELECTRE III method ranking the alternatives based on their outranking relations and by considering the existing uncertainty in their performances. This way the final ranking is resulted from an independent fuzzy system, which has considered the existing uncertainty in the evaluations not once but twice. Our proposed system has been applied to a real case of vendor selection process in one of the greatest and the most famous companies in the Iranian oil industry, OIEC, and the results are discussed.
- SourceAvailable from: citeseerx.ist.psu.edu[show abstract] [hide abstract]
ABSTRACT: An outsourcing contract problem has been analyzed. This is a typical problem when dealing with outsourcing vendor selection. For each alternative of an outsourcing contract there is an evaluation of both cost and quality of service. The latter may include probabilistic delivery time and confidence in quality commitment. The decision-maker takes into account multicriteria evaluation through ELECTRE method. Besides, each criterion is evaluated through a utility function. The model integrates both approaches to indicate a contract proposal. This paper presents the formulation for the decision model and a numerical application to illustrate the use of the model.Computers & Operations Research. 01/2007;
- [show abstract] [hide abstract]
ABSTRACT: A fuzzy logic toolkit has been developed for the formal specification language Z. It permits the incorporation of fuzzy concepts into the language while retaining the precision of any Z specification. The toolkit provides the necessary operators, measures and modifiers for the definition and manipulation of fuzzy sets and relations. This paper illustrates how the toolkit can be used to specify a simple fuzzy expert system. The focus is on the specification of the rule base and the operations necessary for fuzzy inferencing. In particular the example illustrates the use of the fuzzy cartesian product and fuzzy set truncation operators and offers a generic definition for a centroid defuzzification function.Information & Software Technology. 01/2003; 45:419-429.
Article: Operations on fuzzy numbers[show abstract] [hide abstract]
ABSTRACT: A fuzzy number is a fuzzy subset of the real line whose highest membership values are clustered around a given real number called the mean value ; the membership function is monotonia on both sides of this mean value. In this paper, the usual algebraic operations on real numbers are extended to fuzzy numbers by the use of a fuzzification principle. The practical use of fuzzified operations is shown to be easy, requiring no more computation than when dealing with error intervals in classic tolerance analysis. The field of applications of this approach seems to be large, since it allows many known algorithms to be fitted to fuzzy data.International Journal of Systems Science 06/1978; 9(6):613-626. · 1.31 Impact Factor