A two-stage consensus-based approach for determining collective knowledge

Abstract

Generally, the knowledge of a collective is understood as a representative for a set of knowledge states of a collective. In this paper, we present a two-stage consensus-based approach for determining the knowledge of a large collective. For this aim, k-means algorithm is used to cluster the collective into smaller ones. The representatives of new smaller collectives are determined in the first stage of consensus choice. Next, each representative is assigned a weight value depending on the number of members in the corresponding collective, which is formed a new collective (clustered-collective). Then the second stage of consensus choice serves for determining the representative for the clustered- collective. The experimental results reveal that the weighted approach is helpful in reducing the difference between the two-stage and the single-stage consensus choice in determining the knowledge of a large collective in reference to non-weighted approach.