Methods Based On Dempster-Shafer Theory For Multi-attribute Decision Making

The MAGDM (Multi-attribute Group Decision Making), is the multi-attribute decisions-making(MADM)and the group decision-making(GDM)overlapping research area. It mainly studies the group of decision-making to be partial to the structure according to some kind,to includes many attribute object question.In most practical process of GDM, we often meet that decision makers give linguistic preference information when they make judgments to alternatives or criteria. Therefore, we need thorough research on theory and methods of MAGDM problem with linguistic assessment information.This paper focuses on MAGDM problems and mainly researches some theories and merhods based on Dempster-Shafer theory(DST).The main research work is as follows.(1) The theories and methods of group decision making theory are discussed, such as generation and development, and basic specialties and elements of decision-making problems. Group decision-making is defined in this dissertation.(2) Study on the methods to dispel the absurdities of D-S combination rule. The result of each decision-maker is influenced by the decision-maker's knowledge, preference, and judgment ability. Each decision made by the single decision-maker may conflict to others. When the evidences contradict to others, some absurdities might be generated if the DS formula is used to combine the evidences. In order to settle this problem, this dissertation presents several methods to dispel the absurdities. These methods are universal methods to dispel the absurdities.(3) Study on the steps of using the group-decision method based on the D-S theory in actual decision problems. Detailed steps of using the group-decision method based on the D-S theory and the systematical construction are presented.The paper first analyzes the deficiency of the existing decision making rules based on evidence structure. Then the paper synthetically considers the role of belief function (Bel) and plausibility function (Pls) to the alternatives, and proposes a MADM rule based on belief interval. Study on the consistency analysis of single decision-maker's decision. Finnally this dissertation presents a new method to measure the weights of decision makers based on the fuzzy distance.(4) A new decision making approach based on fuzzy distance and evidence theory is proposed for the multi-attribute group decision making problem with linguistic assessment information. Based on the fuzzy distance, the weights of decision makers are established first. Then, the values by analyzing the linguistic assessment information given by decision makers are integrated by D-S rule of combination. Finally, the values of belief function and plausibility function can be calculated and used to rank all decision alternatives.The last chapter summarizes all the work of this paper, and gives some useful suggestions for future research.