NGTSOM: A Novel Data Clustering Algorithm Based on Game Theoretic and Self-Organizing Map

Identifying clusters is an important aspect of data analysis. This paper proposes a novel data clustering algorithm to increase the clustering accuracy. A novel game theoretic self-organizing map (NGTSOM ) and neural gas (NG) are used in combination with Competitive Hebbian Learning (CHL) to improve the quality of the map and provide a better vector quantization (VQ) for clustering data. Different strategies of Game Theory are proposed to provide a competitive game for nonwinning neurons to participate in the learning phase and obtain more input patterns. The performance of the proposed clustering analysis is evaluated and compared with that of the K-means, SOM and NG methods using different types of data. The clustering results of the proposed method and existing state-of-the-art clustering methods are also compared which demonstrates a better accuracy of the proposed clustering method.