关键词: 数据竞争, 数据场, 自动聚类, 密度不均匀

Abstract: Aiming at the similarity of Euclidean distance calculation, the number of clustering clusters and the clustering center can not be determined automatically and accurately, a data competition clustering algorithm is proposed to automatically determine the clustering center. Firstly, the concept of the data field is introduced so that the calculated potential value is more consistent with the true distribution of the data set. At the same time, the automatic determination of the clustering center is completed by combining the potential energy of the data point with the local minimum distance to form the decision graph. Principle to complete the cluster. The experimental results on the artificial and real data sets show that the proposed algorithm has better clustering performance than the original data competition algorithm.

Key words: data competition, data field, automatic clustering, density inhomogeneous