Induced Ordered Weighted Averaging Operators In Comprehensive Evaluation

As one of essential factors of comprehensive evaluation, aggregation operators can aggregate the arguments to obtain an aggregated value, which can reflect the overall level of alternatives. The induced ordered weighted averaging (IOWA) operator is an important aggregation operator, which is often applied to solve the comprehensive evaluation problems. The main feature of the IOWA operator is that the ordering of the arguments is induced by the order inducing variables, rather than the values of the arguments, and the IOWA weight is associated with a particular ordered position.In this thesis, the research on the IOWA operators in comprehensive evaluation is reviewed. The limitations in the existing research are as follows:The aggregation results depend upon the weighting vector and the order inducing variable, but few studies have been conducted on the determination of the order inducing variable in the induced OWA operator; In the weight determination methods, attitudinal character is important, and it can constrain the favoritism towards the bigger or smaller argument values, but few methods have been introduced to determine it.With regard to the limitations in the existing research, a series of research works are conducted as follows:(1) The research provides a special type of induced ordered weighted averaging (IOWA) operator called density induced OWA (DIOWA) operator, which takes the density around the arguments as the inducing variables to reorder the arguments. The density around the argument, which can measure the degree of similarity between the argument and its nearest neighbors, is associated with both the number of its nearest neighbors and its weighted average distance to these neighbors.(2) Basing on cluster size and cluster cohesion, the research proposes a cluster-reliability (CR) measure, which indicates the overall reliability of arguments in a cluster. Taking the reliability of clusters as order inducing variables, the research introduces a cluster-reliability-induced OWA (CRIOWA) operator from the viewpoint of combining representative arguments of clusters.(3) The research analyzes the impact of attitudinal character on the comprehensive evaluation with OWA operators. According to the impact of attitudinal character analyzed by the proposed method, the set of alternatives can be reduced, when the range of attitudinal character is specified, and the best and worst ranges of attitudinal character for each alternative can be identified in self-evaluation.(4) Attitudinal character plays an important role in the maximum entropy OWA (MEOWA) approach. The research proposes a self-evaluation model to determine the attitudinal character for each alternative in comprehensive evaluation with MEOWA operators. The value of attitudinal character determined for each alternative by self-evaluation may be different. And each alternative can reach its highest rank with MEOWA weights, when the attitudinal character is determined for it. Then, to obtain an overall set of MEOWA weights by different attitudinal character values, the preemptive goal programming (PGP) model proposed by Wang can be used.(5) Two methods are proposed to determine the IOWA weights.Finally, the main conclusions are summarized and the prospect of the research is given.