مدل اندازه گیری برای الگوریتم سیستم های خبره مبتنی بر دانش با استفاده از فرایند تحلیل شبکه ای فازی

This study proposes an experts knowledge-based systems measurement model, the model using fuzzy analytic network process (FANP) to resolve the uncertainty and imprecision of evaluations during pre-negotiation stages, where the comparison judgments of a decision maker are represented as fuzzy triangular numbers. A novel fuzzy prioritization method, which derives crisp priorities (criteria weights and scores of alternatives) from consistent and inconsistent fuzzy comparison matrices, is also proposed. The applicability of the proposed model is demonstrated in a government purchase digital video recorder (DVR) system project study. The stability tests indicate the advantages of the proposal model in determining the value of model. Importantly, the proposed model can provide decision makers a reference material, making it highly applicable for academic and commercial purposes.

Multiple attribute decision making (MADM) is a methodology that helps decision makers building experts knowledge-based systems regarding a finite set of available alternatives (courses of action) characterized by multiple, potentially conflicting criteria or attributes (Belton and Stewart, 2002 and Mollaghasemi and Pet-Edwards, 1997). MADM provides a formal framework for modeling multi-attribute decision problems, particularly problems whose nature demands systematic analysis, including analysis of decision complexity, regularity, significant consequences, and the need for accountability (Belton & Stewart, 2002). MADM provides a formal framework for modeling multi-criteria decision problems, particularly problems demanding a systematic analysis, including analysis of the decision complexity, regularity, significant consequences, and the need for accountability (Belton & Stewart, 2002). Existing experts knowledge-based systems evaluates models which include: (1) The Weighted Sum Model (WSM) (Sobczak and Berry, 2007): In a weighted sum, each element of a sum is multiplied by its weight. (2) Grey Relational Analysis (GRA) Model (Chang et al., 2008, Chiu, 2009, Huang et al., 2008 and Lin et al., 2009): The concept of grey relational space was proposed by Deng based on the combined concepts of system theory, space theory and control theory. It can be used to capture the correlations between the references factor and other compared factors of a system (Deng, 1989). (3) Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) Model (Celik et al., 2009, Dagdeviren et al., 2009, Li et al., 2008 and Tsou, 2008): TOPSIS is based on the concept that the most preferred alternative should not only have the shortest distance from the positive ideal solution, but also have the longest distance from the negative ideal solution (Yoon & Hwang, 1995). (4) Analytic Hierarchy Process (AHP) Model (Jose and Ines, 2005 and Kolat et al., 2006; Sobczak and Berry, 2007; Hsu and Pan, 2009, Li and Li, 2009 and Wang and Yang, 2007): AHP is also a measurement theory that prioritizes the hierarchy and consistency of judgmental data provided by a group of decision makers. AHP incorporates the evaluations of all decision makers into a final decision, without having to elicit their utility functions on subjective and objective criteria, by pair-wise comparisons of the alternatives (Saaty, 1980). (5) Analytic network process (ANP) model (Chang et al., 2007; Lee and Kim, 2001, Lee et al., 2009 and Lin and Tsai, 2009): ANP was expanding AHP, ANP allows for more complex interrelationships among decision levels and attributes (Saaty, 1996). MADM has thus been successfully applied to a diverse array of problems. Despite its popularity, MADM cannot adequately resolve the inherent uncertainty and imprecision associated with the mapping of an expert or decision maker’s perception to exact numbers. In the traditional formulation of MADM, human judgment is represented as exact numbers. Fuzzy multi-criteria decision making (FMADM) methods have been developed owing to the imprecision in assessing the relative importance of attributes and the performance ratings of alternatives with respect to attributes. Imprecision may arise from a variety of reasons: unquantifiable information, incomplete information, unobtainable information and partial ignorance. Conventional MADM methods cannot effectively handle problems with such imprecise information (Chang, Wu, & Lin, 2009). To resolve this difficulty, fuzzy set theory, first introduced by Zadeh (1965), has been used and is adopted herein. Fuzzy set theory attempts to select, prioritize or rank a finite number of courses of action by evaluating a group of predetermined criteria (Chen et al., 2006 and Moon and Lee, 2005). Solving this problem thus requires constructing an evaluation procedure to rate and rank, in order of preference, the set of alternatives. This study proposes an experts knowledge-based systems measurement model, the model using fuzzy analytic network process (FANP) to resolve the uncertainty and imprecision of evaluations during pre-negotiation stages, where the comparison judgments of a decision maker are represented as fuzzy triangular numbers. A novel fuzzy prioritization method, which derives crisp priorities (criteria weights and scores of alternatives) from consistent and inconsistent fuzzy comparison matrices, is also proposed. The applicability of the proposed model is demonstrated in a government purchase digital video recorder (DVR) system project study. The stability tests indicate the advantages of the proposal model in determining the value of model. Importantly, the proposed model can provide decision makers a reference material, making it highly applicable for academic and commercial purposes.

This study proposes an experts knowledge-based systems measurement model and algorithm. The case study is capable of effectively evaluating DVR systems from the perspective of users or purchasers, thus enabling administrators or decision makers to identify optimum DVR systems. Significantly, this study provides procurement personnel with an easily applied and objective method of assessing the appropriateness of DVR systems. The surveillance market includes many DVR systems, each with unique functions, thus easily causing confusion when evaluating them. To determine the value of FANP, the results of the normalized relative weights of the DVR systems were obtained from FANP. The systems of all four firms were stable for four weeks in the test (see Table 9). Test results clearly indicate that Firm B’s product is more stable than that of Firm A, C, D. However, System B should be the optimum system, since it is more stable than Firm B in terms of mean CPU efficiency, greatest efficiency, mean MEM loading, top loading and frequency of system crashes. Fuzzy theory can adequately resolve the inherent uncertainty and imprecision associated with the mapping of a decision maker’s perception to exact numbers. Besides, ANP decision model considers the interdependencies among selection criteria that exert additional effect on the model. Combining ANP and fuzzy theory (FANP), the results of systems stable testing provide guidance for building experts knowledge-based systems in accepting ranks when its criteria consider interrelationship and uncertainty judgment. This study has found that FANP is a building expert knowledge-based methodology for evaluating appropriate DVR systems candidate. This study proposes further FANP theory to resolve other problems.