An expert weighting method based on affinity propagation clustering algorithm

Since the expert weighting method based on fuzzy kernel clustering algorithm is sensitive to initializing the clustering center, it is difficult to converge the iterative results to the global optimum. In this paper, an expert weighting method based on affinity propagation (AP) clustering algorithm is proposed to solve the problem of unreasonable clustering. This method uses AP clustering algorithm to cluster experts, since the number of clusters does not need to be set in advance, the clustering result is prevented from being limited by the selection of the initial cluster center, and improves the rationality of clustering. At the same time, the deviation entropy model is constructed to obtain the weights of experts, and effectively avoids the problem of the weighting method based on consistency ratio and information entropy that the consistency ratio and information entropy are equal but the expert opinions are different, and makes the expert weighting more scientific. The example indicates that the proposed method is feasible and effective.