• Asia pacific journal of information systems
• /
• 제16권1호
• /
• pp.85-101
• /
• 2006

Actual type of aggregation performed by an ordered weighted averaging (OWA) operator heavily depends upon the weighting vector. A number of approaches have been suggested for obtaining the associated weights. In this paper, we present analytic forms of OWA operator weighting functions, each of which has such properties as rank-based weights and constant value of orness, irrespective of number of objectives aggregated. Specifically, we propose four analytic forms of OWA weighting functions that can be positioned at 0.25, 0.334, 0.667, and 0.75 on the orness scale. The merits for using these weights over other weighting schemes can be mentioned in a couple of ways. Firstiy, we can efficiently utilize the analytic forms of weighting functions without solving complicated mathematical programs once the degree of orness is specified a priori by decision maker. Secondly, combined with well-known OWA operator weights such as max, min, and average, any weighting vectors, having a desired value of orness and being independent of the number of objectives, can be generated. This can be accomplished by convex combinations of predetermined weighting functions having constant values of orness. Finally, in terms of a measure of dispersion, newly generated weighting vectors show just a few discrepancies with weights generated by maximum entropy OWA.

• 한국지능시스템학회논문지
• /
• 제19권2호
• /
• pp.273-278
• /
• 2009

The determination of the associated weights in the theory of ordered weighted averaging (OWA) operators is one of the important issue. Recently, Wang and Parkan [Information Sciences 175 (2005) 20-29] proposed a minimax disparity approach for obtaining OWA operator weights and the approach is based on the solution of a linear program (LP) model for a given degree of orness. Recently, Liu [International Journal of Approximate Reasoning, accepted] showed that the minimum variance OWA problem of Fuller and Majlender [Fuzzy Sets and Systems 136 (2003) 203-215] and the minimax disparity OWA problem of Wang and Parkan always produce the same weight vector using the dual theory of linear programming. In this paper, we give an improved proof of the minimax disparity problem of Wang and Parkan while Liu's method is rather complicated. Our method gives the exact optimum solution of OWA operator weights for all levels of orness, $0\leq\alpha\leq1$, whose values are piecewise linear and continuous functions of $\alpha$.

• Journal of the Korean Data and Information Science Society
• /
• 제17권2호
• /
• pp.537-541
• /
• 2006

In this note, we give an elementary simple proof of the main result of $Full{\acute{e}}rand$ Majlender [Fuzzy Sets and systems 124(2001) 53-57] concerning obtaining maximal entropy OWA operator weights.

• 한국항해항만학회지
• /
• 제31권6호
• /
• pp.537-543
• /
• 2007

다기준 의사결정 문제에서 요인간의 가중치 계산과 계산된 요인의 평가값 종합화는 매우 중요하다. 본 연구에서는 다기준 의사결정 문제에 있어서 의사결정자의 의사전략 결합기법과 다기준의사결정 문제로의 적용을 연구하였다. 복잡한 환경에서 의사결정을 할 때 발생되는 모호함을 해결하기 위해 주관적 의견을 결합한 퍼지지합 이론을, 다기준 문제의 요인을 퍼지값으로 계층화하기 위해 계층분석법을 적용하였다. 또한, 의사결정자의 의사전략을 결합하기 위해 순위 가중치평균법을 이용하였다. 순위가 있는 가중치 평균방법은 퍼지집합의 orness 특성을 이용하여 의사결정자의 주관적 의지를 반영할 수 있는 기법으로, 순위가중치평균(OWA) 연산자에 따른 낙관적 혹은 비관적인 정도에 따라 주관적인 의도를 반영할 수 있는 방법이다. 다기준의사결정 문제의 적용사례로서 해상교통안전을 위한 대기정박지의 위치분석 문제를 본 연구에서 제시한 방법에 따라 적용하였다.