关键词: 多属性群决策, 不确定型, 投影, 权重, Dice相似度

Abstract: To the uncertain multi-attribute group decision-making with unknown attribute weights and decision makers weights, nonlinear optimization models have been established for determining the corresponding ideal solution weights of each decision maker after the attribute values are normalized. The group attribute weights are obtained through the projection on the above ideal attribute weights of the decision makers. And each decision maker's weight is also obtained by using the projection models. Then all individual normalized decision matrices are aggregated into a collective one. Thus the Dice similarity measures are also calculated between each alternative and group ideal solution. Therefore all the alternatives can be ranked according to their Dice similarity measures. The detailed process of the method is also given for the practical applications. Finally, a numerical example demonstrates the feasibility and effectiveness of the presented approach.

Key words: multi-attribute group decision-making, uncertain interval numbers, projection, weights, Dice similarity measure